No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Computer vision based robotic weed control system for precision agriculture
... HTP, combined with quality curated data, can enhance our ability to dissect trait genetics, address environmental interactions, and support informed breeding decisions, ultimately leading to improved varieties with enhanced yield and quality characteristics (Bhandari et al., 2023). The integration of phenotype technology, encompassing advanced sensors and autonomous robotics, holds immense promise for unlocking the potential of plant systems (Arakeri et al., 2017;Eraslan et al., 2019). These technologies bridge the gap between genetics and phenotypic traits, offering unprecedented insights into plant behavior and interactions with the environment. ...
... in contrast to the unpredictable outdoor environments common in robotics and computer vision applications (Haug and Ostermann, 2015;Arakeri et al., 2017;Rose and Chilvers, 2018;Zhao et al., 2020;Abbasi et al., 2022). Furthermore, the dimensions of time and scale in these domains diverge. ...
... Furthermore, the dimensions of time and scale in these domains diverge. Computer vision and robotics often operate in rapid, dynamic time frames, requiring real-time decision-making (Arakeri et al., 2017). HTP, conversely, spans various temporal scales, from tracking minute physiological changes over weeks to studying plant evolution across generations. ...
Advances in gene editing and natural genetic variability present significant opportunities to generate novel alleles and select natural sources of genetic variation for horticulture crop improvement. The genetic improvement of crops to enhance their resilience to abiotic stresses and new pests due to climate change is essential for future food security. The field of genomics has made significant strides over the past few decades, enabling us to sequence and analyze entire genomes. However, understanding the complex relationship between genes and their expression in phenotypes-the observable characteristics of an organism-requires a deeper understanding of phenomics. Phenomics seeks to link genetic information with biological processes and environmental factors to better understand complex traits and diseases. Recent breakthroughs in this field include the development of advanced imaging technologies, artificial intelligence algorithms, and large-scale data analysis techniques. These tools have enabled us to explore the relationships between genotype, phenotype, and environment in unprecedented detail. This review explores the importance of understanding the complex relationship between genes and their expression in phenotypes. Integration of genomics with efficient high throughput plant phenotyping as well as the potential of machine learning approaches for genomic and phenomics trait discovery.
... HTP, combined with quality curated data, can enhance our ability to dissect trait genetics, address environmental interactions, and support informed breeding decisions, ultimately leading to improved varieties with enhanced yield and quality characteristics (Bhandari et al., 2023). The integration of phenotype technology, encompassing advanced sensors and autonomous robotics, holds immense promise for unlocking the potential of plant systems (Arakeri et al., 2017;Eraslan et al., 2019). These technologies bridge the gap between genetics and phenotypic traits, offering unprecedented insights into plant behavior and interactions with the environment. ...
... in contrast to the unpredictable outdoor environments common in robotics and computer vision applications (Haug and Ostermann, 2015;Arakeri et al., 2017;Rose and Chilvers, 2018;Zhao et al., 2020;Abbasi et al., 2022). Furthermore, the dimensions of time and scale in these domains diverge. ...
... Furthermore, the dimensions of time and scale in these domains diverge. Computer vision and robotics often operate in rapid, dynamic time frames, requiring real-time decision-making (Arakeri et al., 2017). HTP, conversely, spans various temporal scales, from tracking minute physiological changes over weeks to studying plant evolution across generations. ...
Advances in gene editing and natural genetic variability present significant opportunities to generate novel alleles and select natural sources of genetic variation for horticulture crop improvement. The genetic improvement of crops to enhance their resilience to abiotic stresses and new pests due to climate change is essential for future food security. The field of genomics has made significant strides over the past few decades, enabling us to sequence and analyze entire genomes. However, understanding the complex relationship between genes and their expression in phenotypes-the observable characteristics of an organism-requires a deeper understanding of phenomics. Phenomics seeks to link genetic information with biological processes and environmental factors to better understand complex traits and diseases. Recent breakthroughs in this field include the development of advanced imaging technologies, artificial intelligence algorithms, and large-scale data analysis techniques. These tools have enabled us to explore the relationships between genotype, phenotype, and environment in unprecedented detail. This review explores the importance of understanding the complex relationship between genes and their expression in phenotypes. Integration of genomics with efficient high throughput plant phenotyping as well as the potential of machine learning approaches for genomic and phenomics trait discovery.
... Because of these reasons, drastic improvements in agriculture are the need of the hour (Wang et al., 2019). The total population of the world will reach upto 9 billion by 2050, to meet the requirements of such a large population, the productivity and production must be increased exponentially (Arakeri et al., 2017;Bakhshipour et al., 2017). As of now, farming is encountering significant challenges such as environmental change, fragmentation in cultivable areas, a shortfall of irrigation supplies, and a lack of machinery for crop and land management. ...
... Over the past few decades, researchers have put in significant effort to improve the accuracy of weed detection using computer vision technology. Arakeri et al. (2017) integrated image processing, machine learning, and the Internet of Things (IoT) to develop a site-specific weed detection system for onion crops. The machine can identify weeds and onion crops with 96.8% accuracy in the field. ...
Weed control is a significant factor that could affect crop productivity. With the advancement in technology, computer vision becomes one of the meticulous methods for instantaneously detecting crop-weeds and providing vital data for spot-specific weed supervision. Computer vision is a technology that employs a computer and a camera, rather than relying on the sensory visuals of an individual, to distinguish, trace, and evaluate the target for a better picture through image processing. This review summarizes the advances and challenges in spot-specific crop-weed detection over the past four years using computer vision technology. The summary of this study discusses conventional methods in weed management, which aid in the development of automatic crop-weed detection for on-field real-time weed control. There are still major challenges for crop-weed classification, such as the overlapping of crop plant foliage and varying illumination levels, leading to the failure of detection algorithms. To achieve universal acceptance of the technology, it is necessary to establish a broader crop dataset. In the upcoming days, through thorough investigation, computer vision techniques will be better applied in autonomous crop-weed detection. With the advancements in computer vision technology, the efficacy and accuracy of crop-weed detection are further enhanced. It also focuses on providing better understanding to laymen for decision support, which aids in the rapid growth of agricultural automation.
... Because of these reasons, drastic improvements in agriculture are the need of the hour (Wang et al., 2019). The total population of the world will reach upto 9 billion by 2050, to meet the requirements of such a large population, the productivity and production must be increased exponentially (Arakeri et al., 2017;Bakhshipour et al., 2017). As of now, farming is encountering significant challenges such as environmental change, fragmentation in cultivable areas, a shortfall of irrigation supplies, and a lack of machinery for crop and land management. ...
... Over the past few decades, researchers have put in significant effort to improve the accuracy of weed detection using computer vision technology. Arakeri et al. (2017) integrated image processing, machine learning, and the Internet of Things (IoT) to develop a site-specific weed detection system for onion crops. The machine can identify weeds and onion crops with 96.8% accuracy in the field. ...
Weed control is a significant factor that could affect crop productivity. With the advancement in technology, computer vision becomes one of the meticulous methods for instantaneously detecting crop-weeds and providing vital data for spot-specific weed supervision. Computer vision is a technology that employs a computer and a camera, rather than relying on the sensory visuals of an individual, to distinguish, trace, and evaluate the target for a better picture through image processing. This review summarizes the advances and challenges in spot-specific crop-weed detection over the past four years using computer vision technology. The summary of this study discusses conventional methods in weed management, which aid in the development of automatic crop-weed detection for on-field real-time weed control. There are still major challenges for crop-weed classification, such as the overlapping of crop plant foliage and varying illumination levels, leading to the failure of detection algorithms. To achieve universal acceptance of the technology, it is necessary to establish a broader crop dataset. In the upcoming days, through thorough investigation, computer vision techniques will be better applied in autonomous crop-weed detection. With the advancements in computer vision technology, the efficacy and accuracy of crop-weed detection are further enhanced. It also focuses on providing better understanding to laymen for decision support, which aids in the rapid growth of agricultural automation.
... Because of these reasons, drastic improvements in agriculture are the need of the hour (Wang et al., 2019). The total population of the world will reach upto 9 billion by 2050, to meet the requirements of such a large population, the productivity and production must be increased exponentially (Arakeri et al., 2017;Bakhshipour et al., 2017). As of now, farming is encountering significant challenges such as environmental change, fragmentation in cultivable areas, a shortfall of irrigation supplies, and a lack of machinery for crop and land management. ...
... Over the past few decades, researchers have put in significant effort to improve the accuracy of weed detection using computer vision technology. Arakeri et al. (2017) integrated image processing, machine learning, and the Internet of Things (IoT) to develop a site-specific weed detection system for onion crops. The machine can identify weeds and onion crops with 96.8% accuracy in the field. ...
Weed control is a significant factor that could affect crop productivity. With the advancement in technology, computer vision becomes one of the meticulous methods for instantaneously detecting crop-weeds and providing vital data for spot-specific weed supervision. Computer vision is a technology that employs a computer and a camera, rather than relying on the sensory visuals of an individual, to distinguish, trace, and evaluate the target for a better picture through image processing. This review summarizes the advances and challenges in spot-specific crop-weed detection over the past four years using computer vision technology. The summary of this study discusses conventional methods in weed management, which aid in the development of automatic crop-weed detection for on-field real-time weed control. There are still major challenges for crop-weed classification, such as the overlapping of crop plant foliage and varying illumination levels, leading to the failure of detection algorithms. To achieve universal acceptance of the technology, it is necessary to establish a broader crop dataset. In the upcoming days, through thorough investigation, computer vision techniques will be better applied in autonomous crop-weed detection. With the advancements in computer vision technology, the efficacy and accuracy of crop-weed detection are further enhanced. It also focuses on providing better understanding to laymen for decision support, which aids in the rapid growth of agricultural automation.
... 3) Message Queue Telemetry Transport (MQTT): is a light and very simple publish/subscribe messaging protocol developed for unreliable networks with higher latency or low bandwidth. It is designed to ensure that network bandwidth and device resource requirements are minimized, while trying Crop-field monitoring and automation irrigation system Field monitoring [156]- [160] Unauthorised actions detection [161], [162] Remote sensing [64] Motion detection [163] Objects identification [32] Light, Gaz, PH and Temperature monitoring [85] Multimedia data acquisition [63] Smart irrigation [164]- [167] Desalination [90], [168] Soil moisture measurement [169] Weather forecast [170] Water quality and pressure monitoring [49] Humidity monitoring [171], [172] Decision support systems [105] Water loss control [173] Rain detection [174] Fertilization [175] Pest control [176] Herbicides application [177] Solar pest control light [178] UAV-based agrochemicals spraying [179] Weed detection [180] Insecticides application [181] Soil NPK sensing [182] Crop health monitoring [183]- [185] Livestock health monitoring [186], [187] Disease prediction [188] Behaviors monitoring [189] Disease detection [190] Disease prevention [191] Blood pressure and heart rate monitoring [192] Disease classification [193] Objects detection [194], [195] Robotics arms [69], [196] Motion control [197] Fruit detection and classification [198], [199] Colors and shapes recognition [200] Obstacles detection [201] Optimal harvest date [202] Products identification [33], [203] Traceability with blockchain Technology [204]- [207] Food safety and quality control [208]- [210] Agricultural mobile crowd sensing [40] Chain risk control [211] Agrivoltaic systems [212], [213] Photovoltaics farms [214], [215] Greenhouse [191], [215]- [218] Hydroponic [55], [219], [220] Aeroponics [221], [222] Aquaponics [223], [224] Vertical farming [225] Plant phenotyping [226] Fig. 7: Classification of IoT applications for smart agriculture to guarantee the reliability, and a degree of assurance in the delivery. These principles make the protocol perfect for Machine to Machine (M2M) or IoT connected devices, as well as for mobile applications, that require high bandwidth and battery power [28]. ...
... 3) Herbicides application: The most popular technique for weed control is herbicide spraying. In [177], a system based on IoT, image processing and, machine learning to identify weeds, and to selectively spray the right amount of herbicides. 4) Solar pest control light: is a green pest control method with Solar Insecticidal Lamps (SILs) [178]. ...
This paper presents a comprehensive review of emerging technologies for the Internet of Things-based smart agriculture. We begin by summarizing the existing surveys and describing emergent technologies for the agricultural Internet of Things (IoT), such as unmanned aerial vehicles, wireless technologies, open-source IoT platforms, Software Defined Networking (SDN) and Network Function Virtualization (NFV) technologies, cloud/fog computing, and middleware platforms. We also provide a classification of IoT applications for smart agriculture into seven categories, including, smart monitoring, smart water management, agrochemicals applications, disease management, smart harvesting, supply chain management, and smart agricultural practices. Moreover, we provide a taxonomy and a side-by-side comparison of the state-of-the-art methods toward supply chain management based on the blockchain technology for agricultural IoTs. Furthermore, we present real projects that use most of the technologies mentioned above, achieving great performance in the field of smart agriculture. Finally, we highlight open research challenges and discuss possible future research directions for agricultural IoTs.
... The authors reported successful weed identification in almost all cases and that the duration of identification and spraying is approximately 3 s. In a similar study, a prototype robot for detecting weeds in onion fields is presented in [22]. Their proposed vision-based weed identification system successfully identified weeds in the onion field with approximately 97% accuracy. ...
Weeds are one of the primary concerns in agriculture since they compete with crops for nutrients and water, and they also attract insects and pests and are, therefore, hindering crop yield. Moreover, seasonal labour shortages necessitate the automation of such agricultural tasks using machines. For this reason, advances in agricultural robotics have led to many attempts to produce autonomous machines that aim to address the task of weeding both effectively and efficiently. Some of these machines are implementing chemical-based weeding methods using herbicides. The challenge for these machines is the targeted delivery of the herbicide so that the environmental impact of the chemical is minimised. However, environmental concerns drive weeding robots away from herbicide use and increasingly utilise mechanical weeding tools or even laser-based devices. In this case, the challenge is the development and application of effective tools. This paper reviews the progress made in the field of weeding robots during the last decade. Trends during this period are identified, and the current state-of-the-art works are highlighted. Finally, the paper examines the areas where the current technological solutions are still lacking, and recommendations on future directions are made.
... It is grown across the world's tropics and subtropics when proper conditions exist [3,4]. Weeds significantly lower the crop's yield, quality, and value by competing with A. cepa for space, nutrients, light, and water [5,6], leading to substantial yield losses that have been reported to reach as high as 70-75% [7]. ...
... The paper provides a good overview of the proposed solution, but it lacks experimental results to support the proposed approach. Arakeri, M.P et al. is that it primarily focuses on the proposed system for computer vision-based robotic weed control, rather than providing a more comprehensive review of the field [4]. While the proposed system sounds promising, the paper could have provided more background on existing weed control methods and their limitations, as well as exploring other potential applications of computer vision and robotics in precision agriculture. ...
The growing global population demands increased agricultural production, necessitating the implementation of smart farming practices. The development of an automated crop monitoring system using computer vision and machine learning techniques can help to reduce the manual labor involved in crop management and enhance crop yield. This paper proposes a crop monitoring system that utilizes a camera mounted on a mobile robotic platform to capture images of crops at regular intervals. The images are analyzed using computer vision algorithms to detect and track plant growth, pest infestations, and nutrient deficiencies. Machine learning techniques are then applied to the data to predict crop yield. The system is designed to be scalable and can be deployed on a variety of crops, making it suitable for use in large-scale agricultural operations. Preliminary results demonstrate the system's effectiveness in detecting plant growth with an overall accuracy rate of 95%. The proposed system has the potential to significantly improve crop management practices and increase crop yield, thereby contributing to sustainable agriculture development.
... Robotic weed control that uses MCLRN and IoT to detect weeds in onion fields and ( Arakeri et al., 2017) spray them with the required herbicide. Installing a weed detecting system in a chilli (Islam et al., 2021) field using RADF, KNN, and SVM, among other MCLRN and image processing algorithms. ...
Today farmers around the world are gradually embracing Smart farming assisted by different cutting-edge technologies. The Internet of Things (IoT) is playing a major role in the development of smart agriculture applications. Artificial intelligence, edge computing, cloud computing, big data, etc are other forefront technologies used in smart agriculture. Stages of Agriculture activities for a certain crop can be broadly classified into three categories, viz, pre-harvest, during harvest and post-harvest phases. In each phase, many activities have to be performed. Pre-harvesting stage involves seed selection, land preparation, crop selection, etc., during harvesting includes irrigation, disease analysis, pathogens detection, etc. and Post harvesting involves storage, cooling, reaping, etc. In the current work, we have carried out a thorough literature review of these activities involving smart farming one by one. We have attempted to find the flaws in terms of IoT devices, security, dataset, and methodologies used in these existing works. Based on the research gaps a 5G-based smart farming framework has been proposed. We have also presented a brief comparative analysis between our survey and the existing surveys. Our survey has been found to be more comprehensive compared to the existing ones in many regards.
... Then the entire image is scanned and the bin corresponding to the intensity of the pixel is increased by one each time a pixel with that intensity is met. In this way, we get a histogram of the intensity of pixels in the image [15]. Histogram equalization is a contrast adjustment method in image processing that makes use of the image's histogram. ...
Computer vision is a subfield of artificial intelligence that allows computers and systems to extract meaning from digital images and video. It is used in a wide range of fields of study, including self-driving cars, video surveillance, medical diagnosis, manufacturing, law, agriculture, quality control, health care, facial recognition, and military applications. Aromatic medicinal plants are botanical raw materials used in cosmetics, medicines, health foods, essential oils, decoration, cleaning, and other natural health products for therapeutic and Aromatic culinary purposes. These plants and their products not only serve as a valuable source of income for farmers and entrepreneurs but also going to export for valuable foreign currency exchange. In Ethiopia, there is a lack of technologies for the classification and identification of Aromatic medicinal plant parts and disease type cured by aromatic medicinal plants. Farmers, industry personnel, academicians, and pharmacists find it difficult to identify plant parts and disease types cured by plants before ingredient extraction in the laboratory. Manual plant identification is a time-consuming, labor-intensive, and lengthy process. To alleviate these challenges, few studies have been conducted in the area to address these issues. One way to overcome these problems is to develop a deep learning model for efficient identification of Aromatic medicinal plant parts with their corresponding disease type. The objective of the proposed study is to identify the aromatic medicinal plant parts and their disease type classification using computer vision technology. Therefore, this research initiated a model for the classification of aromatic medicinal plant parts and their disease type by exploring computer vision technology. Morphological characteristics are still the most important tools for the identification of plants. Leaves are the most widely used parts of plants besides roots, flowers, fruits, and latex. For this study, the researcher used RGB leaf images with a size of 128x128 x3. In this study, the researchers trained five cutting-edge models: convolutional neural network, Inception V3, Residual Neural Network, Mobile Network, and Visual Geometry Group. Those models were chosen after a comprehensive review of the best-performing models. The 80/20 percentage split is used to evaluate the model, and classification metrics are used to compare models. 2 The pre-trained Inception V3 model outperforms well, with training and validation accuracy of 99.8% and 98.7%, respectively.
... Monitoring plant leaves helps eliminate the disease before spreading for which machine learning methods, including K-means clustering and Support Vector Machine (SVM), have been used for leaf segmentation and classification [9], and deep learning techniques have been employed particularly for tomato leaf disease classification [10,11,12]. Various navigation systems have been investigated for autonomous navigation for agricultural applications. ...
... Continued community efforts, education, training, economic incentives, and policies are of critical importance to move farmers to more sustainable weed management systems (Liu et al. 2020;Moss 2019;Peterson et al. 2018). Research, development, and successful implementation of innovative weed management tools such as biopesticides, computer vision, decision tools, robotics, and machine learning may also play important roles in near future and mitigate the reliance on herbicides (Arakeri et al. 2017;Coleman et al. 2019;Fennimore and Cutulle 2019;McCool et al. 2018;Panpatte and Ganeshkumar 2021;Westwood et al. 2018). ...
A comprehensive WI state-wide assessment of waterhemp response to a diverse group of herbicide sites of action (SOAs) has not been conducted. Our objective was to characterize the response of a WI state-wide collection of waterhemp accessions to postemergence (POST) and preemergence (PRE) herbicides commonly used in corn and soybean. Greenhouse experiments were conducted with more than 80 accessions from 27 counties. POST treatments were 2,4-D, atrazine, dicamba, fomesafen, glufosinate, glyphosate, imazethapyr, and mesotrione at 1× and 3× label rates. PRE treatments were atrazine, fomesafen, mesotrione, metribuzin, and S-metolachlor at 0.5×, 1×, and 3× label rates. Ninety-eight and 88% of the accessions exhibited ≥ 50% plant survival after exposure to imazethapyr and glyphosate POST 3× rate, respectively. Seventeen, 16, and 3% of the accessions exhibited ≥ 50% plant survival after exposure to 2,4-D, atrazine, and dicamba POST 1× rate, respectively. Survival of all accessions was ≤ 25% after exposure to 2,4-D or dicamba POST 3× rate, or glufosinate, fomesafen, and mesotrione POST at either rate evaluated. No plant of any accession survived exposure to glufosinate at either rate. Forty-five and 3% of the accessions exhibited < 90% plant density reduction after exposure to atrazine PRE 3× rate and fomesafen PRE 1× rate, respectively. Plant density reduction of all accessions was ≥ 96% after exposure to fomesafen PRE 3× rate, or metribuzin, S-metolachlor, and mesotrione PRE 1× rate. Our results suggest that waterhemp resistance to imazethapyr and glyphosate POST is widespread in WI, whereas resistance to 2,4-D, atrazine, and dicamba POST is present to a lower extent. One accession (A75, Fond du Lac County) exhibited multiple resistance to imazethapyr, atrazine, glyphosate, and 2,4-D POST. Overall, atrazine PRE was ineffective for waterhemp control in WI. Proactive resistance management and the use of effective PRE and POST herbicides are fundamental for waterhemp management in WI.
... Karim et al. designed [23][24][25] and tested a Cloud IoT-based, late scourge choice emotionally supportive network; they built a choice emotionally supportive network to reduce potato blight. A planned structure [26][27][28] served as a screen for a greenhouse, a hen house, and a fish tank; it made use of Raspberry Pi to track and regulate the weather. IoT sensors and actuators are important for screening and responding to the climate [29][30][31][32]. ...
Smart farming with precise greenhouse monitoring in various scenarios is vital for improved agricultural growth management. The Internet of Things (IoT) leads to a modern age in computer networking that is gaining traction. This paper used a regression-based supervised machine learning approach to demonstrate a precise control of sensing parameters, CO2, soil moisture, temperature, humidity, and light intensity, in a smart greenhouse agricultural system. The proposed scheme comprised four main components: cloud, fog, edge, and sensor. It was found that the greenhouse could be remotely operated for the control of CO2, soil moisture, temperature, humidity, and light, resulting in improved management. Overall implementation was remotely monitored via the IoT using Message Query Telemetry Transport (MQTT), and sensor data were analysed for their standard and anomalous behaviours. Then, for practical computation over the cloud layer, an analytics and decision-making system was developed in the fog layer and constructed using supervised machine learning algorithms for precise management using regression modelling methods. The proposed framework improved its presentation and allowed us to properly accomplish the goal of the entire framework.
... A monitoring agency collected data for certain harvests, then used AI to construct an alert notification which included the data and information. The architecture [9] attempts to provide a continual weed control in onions farms using a Image Processing based integrated weed control framework (WCS). Founded on the idea of LoRa and fog processing innovation, an automated agricultural platform [10] has been developed. ...
For improved agricultural growth control, smart farming with precise greenhouses is essential, as is precision agriculture monitoring in a variety of situations. The Internet of Things (IoT) is a new era in computer communication that is gaining pace as a result of its wide variety of project development applications. Individuals may benefit from the IoT through smart and remote ways such as smart agriculture, smart environment, smart security, and smart cities. These are the latest technologies that are making life simpler in today’s world. The IoT has significantly increased remote control and the variety of networked things or devices, which is a fascinating aspect. The hardware and internet connectivity to the real-time application make up the Internet of Things (IoT). The Internet of Things is made up of sensors, actuators, embedded systems, and a network connection. As a result, we’d want to develop an IoT application for smart farms. This paper demonstrated a remote parameter sensing system in smart greenhouse agriculture. The goal is to monitor greenhouse parameters like CO 2 , soil moisture, temperature, humidity, and light, with adjusting actions for greenhouse windows/doors based on crops. In this experimentation, Gerbera and Broccoli is considered. The primary purpose is to adjust greenhouse conditions in line with plant needs in order to increase production and provide organic farming. As a result of the findings, it appears that the greenhouse might be operated remotely for CO 2 , soil moisture, temperature, humidity and light, resulting in improved management. Overall implementation is remotely monitored via IoT using MQTT on Adafruit IO Cloud Platform and sensor data is analyzed for its normal and anomaly behavior.
... Robots use computer vision for disease detection and herbicide application. In this approach, small autonomous robots that can monitor and apply herbicides autonomously have already been proposed [25]. The researchers used Artificial Neural Networks for real-time disease detection in the field. ...
Strawberries are sensitive fruits that are afflicted by various pests and diseases. Therefore, there is an intense use of agrochemicals and pesticides during production. Due to their sensitivity, temperatures or humidity at extreme levels can cause various damages to the plantation and to the quality of the fruit. To mitigate the problem, this study developed an edge technology capable of handling the collection, analysis, prediction, and detection of heterogeneous data in strawberry farming. The proposed IoT platform integrates various monitoring services into one common platform for digital farming. The system connects and manages Internet of Things (IoT) devices to analyze environmental and crop information. In addition, a computer vision model using Yolo v5 architecture searches for seven of the most common strawberry diseases in real time. This model supports efficient disease detection with 92% accuracy. Moreover, the system supports LoRa communication for transmitting data between the nodes at long distances. In addition, the IoT platform integrates machine learning capabilities for capturing outliers in collected data, ensuring reliable information for the user. All these technologies are unified to mitigate the disease problem and the environmental damage on the plantation. The proposed system is verified through implementation and tested on a strawberry farm, where the capabilities were analyzed and assessed.
... Over the last decade, numerous promising attempts have been made by researchers for the development of intelligent spraying systems for different crops [14][15][16][17][18][19][20][21][22][23]. Surprisingly, not much work is found in the literature on vision-based site-specific spraying systems for crops. ...
Selective agrochemical spraying is a highly intricate task in precision agriculture. It requires spraying equipment to distinguish between crop (plants) and weeds and perform spray operations in real-time accordingly. The study presented in this paper entails the development of two convolutional neural networks (CNNs)-based vision frameworks, i.e., Faster R-CNN and YOLOv5, for the detection and classification of tobacco crops/weeds in real time. An essential requirement for CNN is to pre-train it well on a large dataset to distinguish crops from weeds, lately the same trained network can be utilized in real fields. We present an open access image dataset (TobSet) of tobacco plants and weeds acquired from local fields at different growth stages and varying lighting conditions. The TobSet comprises 7000 images of tobacco plants and 1000 images of weeds and bare soil, taken manually with digital cameras periodically over two months. Both vision frameworks are trained and then tested using this dataset. The Faster R-CNN-based vision framework manifested supremacy over the YOLOv5-based vision framework in terms of accuracy and robustness, whereas the YOLOv5-based vision framework demonstrated faster inference. Experimental evaluation of the system is performed in tobacco fields via a four-wheeled mobile robot sprayer controlled using a computer equipped with NVIDIA GTX 1650 GPU. The results demonstrate that Faster R-CNN and YOLOv5-based vision systems can analyze plants at 10 and 16 frames per second (fps) with a classification accuracy of 98% and 94%, respectively. Moreover, the precise smart application of pesticides with the proposed system offered a 52% reduction in pesticide usage by spotting the targets only, i.e., tobacco plants.
... It does not pollute land, water, crop, or any other substance. It is easy to monitor and operate in mobile application [5]. The mobile application adds an advantage to the efficiency of the robot [8]. ...
... In recent years, this evolved from farm scale to field and sub-field level differentiation. Recent GPS technologies such as real-time kinematics (RTK) can achieve accuracy down to 2 cm level, wireless sensor technology, variable rate application control devices allow the precise targeting of chemicals [4]- [7], while robot crop pickers and robotic weed removal devices [4], [8]- [10] allow the differential treatment of individual plants. ...
Precision agriculture is the collection of hardware and software technologies that allow a farmer to make informed, differentiated decisions regarding agricultural operations such as planting, fertilizing, pest control, and harvesting. In recent years, advances in agricultural machinery and the emergence of agricultural robots continuously increased the resolution at which differentiated treatment is possible. This creates a corresponding need for information at a fine spatial and temporal resolution. Autonomous multi-robot systems (e.g., unmanned ground and aerial vehicles) are some of the most promising approaches for such information collection in open-air farms. In this paper, we survey the current state and challenges of multi-robot information gathering for precision agriculture, with a special focus on maximizing information and ensuring the security of the collected data while simultaneously keeping energy consumption in check.
... For example, scientists from Romania are trying to create a simple solution for moving a mobile platform based on machine vision (Secuianu and Lupu, 2018), the cost of components (Raspberry Pi 3, ultrasonic sensors, Li-Po battery) and free software (OpenCV, Python, Unix) makes such an offer quite affordable for budget use. Such developments include the following works, for example, to determine the processes of fruit ripening (Mustaffa and Khairul, 2017), the application of mineral fertilizers to plants (Khan et al., 2018), the detection of weeds (Arakeri et al., 2017), and so on. ...
The article considers the possibilities of automated use of robotic equipment in order to form an infrastructure for moving goods at enterprises. Areas of application of algorithmic programming languages of object-oriented type in robotics are investigated. The algorithm of operation of a transport vehicle, the movement, which is based on the recognition of the line of motion, describing the route of movement, is presented. The analysis of the peculiarities of the implementation of such problems with the use of OpenCv software library was carried out. The structure of the vehicle is proposed, in particular: its driving mechanisms, control scheme, engines and wheelbase. Further development was made to the algorithms for the management of crawler lorries and the ways of their program realization in various spheres of entrepreneurial activity, where there is a need for the transfer of cargoes in the ordinary areas (construction sites, forest lands, open warehouses, airports, etc.). Based on the proposals for creating a cargo robot that can be moved according to a given route, the model of control system of conveyor systems, which solve the issues of automation of technological processes in the part of the addition of conveyor systems, is presented. The analysis of literary sources describing the necessity of creating mobile conveyor systems in production, which enables to quickly re-equip production processes to unforeseen needs, was carried out.
... The proposed system in [2] aims to develop a computer vision based robotic weed control system (WCS) for real-time control of weeds in onion fields. This system will be able to identify weeds and selectively spray right amount of the herbicide They [3] developed a low-cost automated drought detection system using computer vision coupled with machine learning (ML) algorithms that document the drought response in corn and soybeans field crops. ...
Satellite system advances, remote sensing and drone technology are continuing. These progresses produce high-quality images that need efficient processing for smart agricultural applications. These possibilities to merge computer vision and artificial intelligence in agriculture are exploited with recent deep educational technology. This involves essential phenomena of data and huge quantities of data stored, analysed and used when making decisions. This paper demonstrates how computer vision in agriculture can be used.
... e use of robotic weeding techniques can also improve production efficiency and effectively liberate the human's hands. erefore, under the natural growth environment conditions, accurate and rapid identification and removal of weeds in field crops play an important role in achieving intelligent field management [10][11][12][13][14]. ...
In order to improve the weeding efficiency and protect farm crops, accurate and fast weeds removal guidance to agricultural mobile robots is an utmost important topic. Based on this motivation, we propose a time-efficient quadratic traversal algorithm for the removal guidance of weeds around the recognized corn in the field. To recognize the weeds and corns, a Faster R-CNN neural network is implemented in real-time recognition. Then, an ultra-green characterization (EXG) hyperparameter is used for grayscale image processing. An improved OTSU (IOTSU) algorithm is proposed to accurately generate and optimize the binary image. Compared to the traditional OTSU algorithm, the improved OTSU algorithm effectively shortens the search speed of the algorithm and reduces the calculation processing time by compressing the range of the search grayscale range. Finally, based on the contour of the target plants and the Canny edge detection operator, the shortest weeding path guidance can be calculated by the proposed quadratic traversal algorithm. The experimental results proved that our search success rate can reach 90.0% on the testing date. This result ensured the accurate selection of the target 2D coordinates in the pixel coordinate system. Transforming the target 2D coordinate point in the pixel coordinate system into the 3D coordinate point in the camera coordinate system as well as using a depth camera can achieve multitarget depth ranging and path planning for an optimized weeding path.
... Currently, the task of detecting and navigate through visual paths, using computer vision techniques, has been widely used in different areas, such as industrial [10], automotive [17,18] and agriculture [1]. ...
Tracking a visual path to perform image-based control requires additional processing to extract valuable information even in the presence of inconveniences, such as failures or deformation in the lane line or even restrictive environmental conditions. Dealing with faulty in the path to be followed, non-homogeneous floors and bad lighting condition are some of the difficulties encountered that compromise the accurate of feature extraction and consequently the controller effectiveness. In this paper, a novel visual system is proposed to detect and extract useful lane line parameters and to use them in a NMPC-based Visual Path Following Control Scheme. To cope with the above-mentioned problems, the visual path is approximated by a quadratic function and to robustness improve, this novel algorithm was modified to use RANSAC as a model estimation approach instead of using the classical Least Square Method. Experimental results demonstrate the superiority of the proposed system with respect to two others, in environments with visual disturbance, faulty paths, noise and bad lighting conditions.
... False positive was the number of negative samples classified as positive, and false negative was number of positive samples classified as negative. The accuracy metric indicates the overall effectiveness of the system considering positive and negative samples [66]. ...
Abstract A combination of decision tree (DT) and fuzzy logic techniques was used to develop a fuzzy model for differentiating peanut plant from weeds. Color features and wavelet-based texture features were extracted from images of peanut plant and its three common weeds. Two feature selection techniques namely Principal Component Analysis (PCA) and Correlation-based Feature Selection (CFS) were applied on input dataset and three Decision Trees (DTs) including J48, Random Tree (RT), and Reduced Error Pruning (REP) were used to distinguish between different plants. In all cases, the best overall classification accuracies were achieved when CFS-selected features were used as input data. The obtained accuracies of J48-CFS, REP-CFS, and RT-CFS trees for classification of the four plant categories namely peanut plant, Velvetleaf, False daisy, and Nicandra, were 80.83%, 80.00% and 79.17% respectively. Along with these almost low accuracies, the structures of the decision trees were complex making them unsuitable for developing a fuzzy inference system. The classifiers were also used for differentiating peanut plant from the group of weeds. The overall accuracies on training and testing datasets were respectively 95.56% and 93.75% for J48-CFS; 92.78% and 91.67% for REP-CFS; and 93.33% and 92.59% for RT-CFS DTs. The results showed that the J48-CFS and REP-CFS were the most appropriate models to set the membership functions and rules of the fuzzy classifier system. Based on the results, it can be concluded that the developed DT-based fuzzy logic model can be used effectively to discriminate weeds from peanut plant in the form of machine vision-based cultivating systems.
... Substantial research has been carried out over more than one decade to use computer vision methods for weed detection. In [1], a weed control system is proposed based on a robot capable of detecting weeds in onion field and spraying herbicides according to weed density. The robot had monitored and controlled using a web server from a remote location. ...
... Com o desenvolvimento contínuo de robôs autônomos e um maior poder de decisão baseados em sistemas de visão, que tendem a aumentar a gama de aplicações potenciais, diversos são os estudos voltadosà detecção e navegação através de caminhos visuais Mammeri et al., 2014;Chen et al., 2010). algoritmos eficientes para detecção de características foram validados em diferentes tipos de cenários, tais como industrial (Gorbunov et al., 2018), transportes (Tianqi, 2017) e agricultura (Arakeri et al., 2017). A utilização destes algoritmos em técnicas de seguimento de caminhos visuais permite tornar as soluções menos sensíveisà perturbações variadas, como: imperfeições no ambiente de navegação, robô móvel e do próprio sistema visual.É possível encontrar na literatura métodos de extração de caminhos que utilizam técnicas de detecção por bordas, blobs (Corke, 2011), segmentação por cores (Sun et al., 2006), dentre outros. ...
Precision agriculture has brought a significant transformation towards optimizing modern agricultural practices to enhance crop yield and reduce resource wastage by leveraging advanced technologies like remote sensing, Geographic Information Systems (GIS), and the Internet of Things (IoT). However, the growing threat of weeds continues to pose a significant challenge of unwanted consumption of nutrient resources by weeds therefore affecting the overall quality and nutritional value of crop yields. The traditional methods of controlling weeds largely rely on the use of herbicides that can have adverse impacts on the crops and environment. This research article includes the study of existing techniques for weed control in modern agriculture and proposes an innovative approach to identify potential weed hazards in agricultural fields through the analysis of images. Leveraging advanced machine learning techniques like CNNs and other cutting-edge neural network structures, we develop a weed detection system that utilizes a comprehensive dataset of weed plants to detect areas within the agricultural landscape where the growth of weeds could pose a risk to crops. By training the model on a diverse range of weed species and conditions, we enable it to differentiate between crops and weed types and accurately predict potential threat zones. Our approach not only aids in early weed detection but also facilitates targeted intervention strategies, reducing the need for blanket herbicide application. The results of this study indicate the effectiveness of utilizing deep learning techniques for weed management, contributing to more efficient agricultural methods.
Advances in gene editing and natural genetic variability present significant opportunities to generate novel alleles and select natural sources of genetic variation for horticulture crop improvement. The genetic improvement of crops to enhance their resilience to abiotic stresses and new pests due to climate change is essential for future food security. The field of genomics has made significant strides over the past few decades, enabling us to sequence and analyze entire genomes. However, understanding the complex relationship between genes and their expression in phenotypes - the observable characteristics of an organism - requires a deeper understanding of phenomics. Phenomics seeks to link genetic information with biological processes and environmental factors to better understand complex traits and diseases. Recent breakthroughs in this field include the development of advanced imaging technologies, artificial intelligence algorithms, and large-scale data analysis techniques. These tools have enabled us to explore the relationships between genotype, phenotype, and environment in unprecedented detail. This review explores the importance of understanding the complex relationship between genes and their expression in phenotypes. Integration of genomics with efficient high throughput plant phenotyping as well as the potential of machine learning approaches for genomic and phenomics trait discovery.
Farmers use internet of things (IoT) devices to implement smart agriculture and optimize agricultural processes. This chapter identifies different types of IoT devices for smart agriculture. Then, advantages of using IoT-based smart agricultural systems are outlined. Subsequently, key issues to consider when deploying IoT for smart agriculture in developing countries are explored. Challenges such as limited number agricultural specialists, poor network infrastructure and internet connectivity, and farmers' inability to afford IoT devices are considered. Furthermore, techniques to use IoT systems to provide agricultural advisory services to smallholder farmers are discussed. Also, techniques to use IoT system for early detection of plant diseases are presented. Finally, based on the observations, recommendations are presented to promote the adoption of IoT solutions for agriculture in developing countries.
The Internet of Things (IoT) could be compared with electricity in the modern era. Over the past ten years, it has revolutionised modern society on a daily basis through a variety of applications in several crucial industries, including agriculture. People depend heavily on agriculture in order to survive in this world. The existence of mortals depends on the availability of food to feed them. Smart farming is frequently cited as one of the most viable long-term solutions to food scarcity. Modern technology, such as AI and IoT, has transformed the idea of agriculture into a new paradigm for greater resource utilisation, land production, and decision-making. Soil management, agricultural disease detection, weed detection, and management in conjunction with IoT devices are currently using AI techniques. IoT has been used for real-time monitoring and automated agricultural activities with a minimal workforce. The system as a whole is made more sustainable by the incorporation of numerous cutting-edge technologies, which also makes agriculture smarter and more effective. This study describes cutting-edge technologies, their ramifications, and the limitations involved in implementing them in the agricultural industry.
This chapter identifies climate-smart agriculture (CSA) practices and their impact on smallholder farmers in six African countries. Various CSA practices are discussed. Observations show that farmers who adopted CSA practices obtained positive results in terms of adaptability to climate change and productivity. Furthermore, internet of things (IoT)-enabled smart agricultural systems are explored. Observations indicate that IoT-based agricultural systems enable efficient utilization of farm inputs such as fertilizer, pesticides, herbicides, and water. Also, using IoT systems, it is possible to provide customized, location-specific, and easily understood climate data for smallholder farmers to facilitate decision making and planning of CSA practices. Therefore, this chapter has presented recommendations for the adoption of IoT-enabled CSA in African countries. IoT-enabled agricultural systems are recommended for a country like Senegal where climate data is considered an agricultural input and also for Tanzania where IoT devices such as UAVs are considered to be useful agricultural tools.
Smart farming with accurate greenhouses needs to be implemented for better farming growth management, and therefore, precision agriculture monitoring in diverse conditions is required. The Internet of Things (IoT) is a new era in computer communication that is gaining traction due to its vast range of applications in project development. The IoT provides individuals with smart and remote approaches, such as smart agriculture, smart environment, smart security, and smart cities. This is the most recent technology that is making things easier these days. The Internet of Things (IoT) has fundamentally expanded remote distance control and the diversity of networked things or devices, which is an intriguing element. The IoT comprises the hardware as well as the Internet connectivity to the real-time application. Sensors, actuators, embedded systems, and an Internet connection are the key components of the Internet of Things. As a result, we are interested in creating a smart farm IoT application. In greenhouse agriculture, this study presented a remote sensing of parameters and control system. The objective is to manage CO2, temperature, soil moisture, humidity, and light, with regulating actions for greenhouse windows/doors dependent on crops being carried out once a quarter throughout the year. The major goal is to properly regulate greenhouse conditions in accordance with plant requirements, in order to enhance output and provide organic farming. The results show that the greenhouse may be controlled remotely for CO2, temperature, soil moisture, humidity, and light, resulting in improved management.
The population of the world may reach almost 10 billion by 2050, and currently, approximately 37.7% of land is used for the production of crops. Agriculture is a major source of revenue for any country. Globally, automation in agriculture is in demand. Innovation and integration of technologies contributes for challenges faced by farmers with enlarged revenue and employment opportunities. Artificial intelligence has brought a revolution in agriculture. Crop wellbeing is important as it is a crucial factor that relates all parameters directly; therefore, crop health examination is mandatory. Premature detection of pests also reduces the quantity and frequent use of pesticides, but human intervention in process makes it time consuming and expensive. Time and techniques to use the pesticides in large farmland using AI along with computer vision and IoT converts traditional processes into smart agriculture. This chapter presents the assessment and implementation of an intelligent system for pesticide management.
Vision-based control has become an interesting alternative for increasing the autonomy of mobile robot navigation in many real scenarios. Classic path-following models did not originally predict a metric for reference forward velocity variation, and this becomes an even more pronounced problem when using visual techniques that are very sensitive to parameter calibration, such as curvature. This paper proposes a novel approach to reliable forward velocity variation in NMPC (nonlinear model predictive control)-based visual path-following controllers, directly from the image plane. The main contribution arises as improvements in the image processing stage for the acquisition of practicable reference velocities and a new state capable of capturing the characteristics of the path and calculating, at runtime, an optimal forward velocity capable of safely driving the robot around the visual path. The new set of internal control inputs defined for the NMPC framework allows the application of a computationally efficient technique to handle feasibility through the relaxation of input and state constraints. Simulations and experimental results with the Husky UGV platform navigating on an imperfect visual reference path and with an arbitrary curvature profile demonstrate the correctness of the proposed method.
Agriculture and agribusinesses suffer from many challenges, despite their significance to global economic growth. One of the challenges is the lack of appropriate technology to drive the industry to the next level of development. This technological gap contributes to reduced yield and profit without a reduction in manual labour, cost, and stress. Robotics have been explored to boost agricultural production and improve agribusiness productivity. Several weed control robots have been developed for research and field uses, but these systems are not suitable for weed control in large commercial farms or lack control schemes for navigation and weed control. This study presents the design of an autonomous robot system for chemical weed control. The system uses control theory, artificial intelligence, and image processing to navigate a farm environment, identify weeds, and apply herbicide where necessary. Upon implementation and adoption, this system would increase agricultural productivity with minimal human input, thereby leading to an increase in revenue and profit for agribusinesses.
Machine learning is one of the emerging technologies that has grabbed the attention of academicians and industrialists, and is expected to evolve in the near future. Machine learning techniques are anticipated to provide pervasive connections for wireless nodes. In fact, machine learning paves the way for the Internet of Things (IoT)—a network that supports communications among various devices without human interactions. Machine learning techniques are being utilized in several fields such as healthcare, smart grids, vehicular communications, and so on. In this paper, we study different IoT-based machine learning mechanisms that are used in the mentioned fields among others. In addition, the lessons learned are reported and the assessments are explored viewing the basic aim machine learning techniques are expected to play in IoT networks.
The aim of this chapter is to provide an application of UAV to support the agricultural domain in monitoring the land for checking and countering the presence of parasites that can damage the crop. However, to properly manage a UAVs team, equipped with multiple sensors and actuators, it is necessary to test these technologies and design proper strategies and coordination techniques able to efficiently manage the team. At this purpose, the chapter proposes a simulator suitable for the agriculture domain in order to design novel coordination and control techniques of a UAVs team.
In the context of precision agriculture, we have developed a machine vision system for a real time
precision sprayer. From a monochrome CCD camera located in front of the tractor, the discrimination
between crop and weeds is obtained with an image processing based on spatial information using a Gabor
filter. This method allows to detect the periodic signals from the non periodic one and it enables to enhance
the crop rows whereas weeds have patchy distribution. Thus, weed patches were clearly identified by a
blob-coloring method. Finally, we use a pinhole model to transform the weed patch coordinates image in
world coordinates in order to activate the right electro-pneumatic valve of the sprayer at the right moment.
Crop growth and weed infestation in a soybean field were monitored by processing low altitude remote sensing (LARS) images taken from crane-mounted and unmanned radio controlled helicopter-mounted platforms. Images were taken for comparison between true color (R–G–B) and color-infrared (NIR) digital cameras acquired at different heights above ground. All LARS images were processed to estimate vegetation-indices for distinguishing stages of crop growth and estimating weed density. LARS images from the two platforms (low-dynamic and high-dynamic) were evaluated. It was found that crane-mounted RGBC and NIRC platforms resulted in better quality images at lower altitudes (<10 m). This makes the crane-mounted platform an attractive option in terms of specific low altitude applications at an inexpensive cost. Helicopter-mounted RGBH and NIRH images were found suitable at altitudes >10 m. Comparison of NDVIC and NDVIH images showed that NDVI values at 28 DAG (days after germination) exhibited a strong relationship with altitudes used to capture images (R
2 of 0.75 for NDVIC and 0.79 for NDVIH). However, high altitudes (>10 m) decreased NDVI values for both systems. Higher R
2 values (≥0.7) were also obtained between indices estimated from crane-and helicopter-mounted images with those obtained using an on-ground spectrometer, which showed an adequate suitability of the proposed LARS platform systems for crop growth and weed infestation detection. Further, chlorophyll content was well correlated with the indices from these images with high R
2 values (>0.75) for 7, 14, 21 and 28 DAG.
Image processing has been proved to be effective tool for analysis in various fields and applications. Agriculture sector where the parameters like canopy, yield, quality of product were the important measures from the farmers' point of view. Many times expert advice may not be affordable, majority times the availability of expert and their services may consume time. Image processing along with availability of communication network can change the situation of getting the expert advice well within time and at affordable cost since image processing was the effective tool for analysis of parameters. This paper intends to focus on the survey of application of image processing in agriculture field such as imaging techniques, weed detection and fruit grading. The analysis of the parameters has proved to be accurate and less time consuming as compared to traditional methods. Application of image processing can improve decision making for vegetation measurement, irrigation, fruit sorting, etc.
Automated weed detection and classification allow a high spatial density of measurements and can therefore be used for site-specific application of herbicides at variable rate. A system for the detection and classification of different crops and weed species is presented. Near-range images were taken with a bi-spectral camera (IR+VIS) mounted on a vehicle driving at a speed of about 8 km/h. The techniques used analyse the images including pre-processing steps to reduce noise and to obtain comparable results. A segmentation of green plants and background is achieved by binarisation. The shapes of all plants were extracted and shape parameters, contour and skeleton features were calculated. The features were used to classify different weed and crop species. Their discriminant abilities were tested using data mining and classification algorithms, including discriminant analysis. Different feature sets were compared to each other and the most promising were selected for classification. The classification of an image series taken in a field with Hordeum vulgare in 2006 resulted in a correct classification of 98%. Additionally an image database with weed and crop samples was created, which can be used as prototypes to set up and test different evaluation approaches. This database helps to develop new approaches and makes them comparable to each other.
This paper presents a computer vision system that successfully discriminates between weed patches and crop rows under uncontrolled lighting in real-time. The system consists of two independent subsystems, a fast image processing delivering results in real-time (Fast Image Processing, FIP), and a slower and more accurate processing (Robust Crop Row Detection, RCRD) that is used to correct the first subsystem’s mistakes. This combination produces a system that achieves very good results under a wide variety of conditions. Tested on several maize videos taken of different fields and during different years, the system successfully detects an average of 95% of weeds and 80% of crops under different illumination, soil humidity and weed/crop growth conditions. Moreover, the system has been shown to produce acceptable results even under very difficult conditions, such as in the presence of dramatic sowing errors or abrupt camera movements. The computer vision system has been developed for integration into a treatment system because the ideal setup for any weed sprayer system would include a tool that could provide information on the weeds and crops present at each point in real-time, while the tractor mounting the spraying bar is moving.Research highlights▶ Real-time image processing for weed/crop discrimination. ▶ Vegetation segmentation robust to changes in illumination. ▶ Tested successfully on a wide variety of real outdoor conditions.
In the future, mobile robots will most probably navigate through the fields autonomously to perform different kind of agricultural operations. As most crops are cultivated in rows, an important step towards this long-term goal is the development of a row-recognition system, which will allow a robot to accurately follow a row of plants. In this paper we describe a new method for robust recognition of plant rows based on the Hough transform. Our method adapts to the size of plants, is able to fuse information coming from two rows or more and is very robust against the presence of many weeds. The accuracy of the position estimation relative to the row proved to be good with a standard deviation between 0.6 and 1.2 cm depending on the plant size. The system has been tested on both an inter-row cultivator and a mobile robot. Extensive field tests have showed that the system is sufficiently accurate and fast to control the cultivator and the mobile robot in a closed-loop fashion with a standard deviation of the position of 2.7 and 2.3 cm, respectively. The vision system is also able to detect exceptional situations by itself, for example the occurrence of the end of a row.
Plant Stem Detection and Position Estimation Using Machine Vision
- Haug Sebastian
- Peter Biber
- Andreas Michaels
- Jorn Ostermann
Removal of weeds using Image Processing: A Technical Review
- Riya Desai
- Kruti Desai
- Desai Shaishavi
- Zinal Solanki
- Densi Patel
Wedding of Robots with Agriculture, International Conference on Computing
- G Aravinth Kumar
- M Ramya
- C Ram Kumar
Automatic Weed Removal System using Machine Vision
- M Pusphavalli
- R Chandraleka
Commercial progress in spot spraying weeds
- W L Felton