Figure - uploaded by João Valente
Content may be subject to copyright.
Separability and model performance per color definition (notated as 'dimension_band' such as DSM_0) in sets of 5, 3, and 1; note how flower exhibits lower classification results overall.

Separability and model performance per color definition (notated as 'dimension_band' such as DSM_0) in sets of 5, 3, and 1; note how flower exhibits lower classification results overall.

Source publication
Article
Full-text available
There is a growing demand in both food quality and quantity, but as of now, one-third of all food produced for human consumption is lost due to pests and other pathogens accounting for roughly 40% of pre-harvest loss in potatoes. Pathogens in potato plants, like the Erwinia bacteria and the PVYNTN virus for example, exhibit symptoms of varying seve...

Contexts in source publication

Context 1
... images were then transformed to the most separable color, segmented, and classified using the model associated with said color ( Figure 6). The separability per color definition was quantified, as was their performance as naïve Bayesian classifiers (Table 2). It shows that particular dimensions in isolation do not allow for adequate class distinction, as the associated spectral characteristic need not be significant in all classes, but can add to an overall distinction if combined with other (more expressive or more general) dimensions (e.g., LUV 1 as seen in Table 2). ...
Context 2
... separability per color definition was quantified, as was their performance as naïve Bayesian classifiers (Table 2). It shows that particular dimensions in isolation do not allow for adequate class distinction, as the associated spectral characteristic need not be significant in all classes, but can add to an overall distinction if combined with other (more expressive or more general) dimensions (e.g., LUV 1 as seen in Table 2). Overlap between distribution sets are also considerably lower in higher dimensions (limited to sets of 5 as per their expected correlation). ...
Context 3
... 3. Random forest model parameters and performance (evaluated with F1 and Matthews Correlation Coefficient (MCC) that range from 0 to 1, Gini is used to quantify information gain); The optimized model exhibits slightly higher values but with considerably more trees, which also implies some feature redundancy. Table 2; note that the spectral threshold appears valid as there is now less within-class variance in all classes without removing discrete boundaries. ...
Context 4
... results presented show that the approach proposed was able to classify potato plant pathogens through morphologic features. Manual segmentation was carefully performed (e.g., shifting local contrasts to better approximate class boundaries), but 'clean' supervised samples that are completely separable in appropriate color definitions could not be guaranteed (Table 2). Although this is arguably reflecting real use cases that could employ flawed sampling schemes, the decision to use a naïve classifier in combination with faulty sampling could result in ambiguous class definitions that hinder classification. ...
Context 5
... results presented show that the approach proposed was able to classify potato plant pathogens through morphologic features. Manual segmentation was carefully performed (e.g., shifting local contrasts to better approximate class boundaries), but 'clean' supervised samples that are completely separable in appropriate color definitions could not be guaranteed (Table 2). Although this is arguably reflecting real use cases that could employ flawed sampling schemes, the decision to use a naïve classifier in combination with faulty sampling could result in ambiguous class definitions that hinder classification. ...
Context 6
... images were then transformed to the most separable color, segmented, and classified using the model associated with said color ( Figure 6). The separability per color definition was quantified, as was their performance as naïve Bayesian classifiers (Table 2). It shows that particular dimensions in isolation do not allow for adequate class distinction, as the associated spectral characteristic need not be significant in all classes, but can add to an overall distinction if combined with other (more expressive or more general) dimensions (e.g., LUV 1 as seen in Table 2). ...
Context 7
... separability per color definition was quantified, as was their performance as naïve Bayesian classifiers (Table 2). It shows that particular dimensions in isolation do not allow for adequate class distinction, as the associated spectral characteristic need not be significant in all classes, but can add to an overall distinction if combined with other (more expressive or more general) dimensions (e.g., LUV 1 as seen in Table 2). Overlap between distribution sets are also considerably lower in higher dimensions (limited to sets of 5 as per their expected correlation). ...
Context 8
... 3. Random forest model parameters and performance (evaluated with F1 and Matthews Correlation Coefficient (MCC) that range from 0 to 1, Gini is used to quantify information gain); The optimized model exhibits slightly higher values but with considerably more trees, which also implies some feature redundancy. Table 2; note that the spectral threshold appears valid as there is now less within-class variance in all classes without removing discrete boundaries. ...
Context 9
... results presented show that the approach proposed was able to classify potato plant pathogens through morphologic features. Manual segmentation was carefully performed (e.g., shifting local contrasts to better approximate class boundaries), but 'clean' supervised samples that are completely separable in appropriate color definitions could not be guaranteed (Table 2). Although this is arguably reflecting real use cases that could employ flawed sampling schemes, the decision to use a naïve classifier in combination with faulty sampling could result in ambiguous class definitions that hinder classification. ...
Context 10
... results presented show that the approach proposed was able to classify potato plant pathogens through morphologic features. Manual segmentation was carefully performed (e.g., shifting local contrasts to better approximate class boundaries), but 'clean' supervised samples that are completely separable in appropriate color definitions could not be guaranteed (Table 2). Although this is arguably reflecting real use cases that could employ flawed sampling schemes, the decision to use a naïve classifier in combination with faulty sampling could result in ambiguous class definitions that hinder classification. ...

Similar publications

Article
Full-text available
The development of UAV sensors has made it possible to obtain a diverse array of spectral images in a single flight. In this study, high-resolution UAV-derived images of urban areas were employed to create land cover maps, including car-road, sidewalk, and street vegetation. A total of nine orthoimages were produced, and the variables effective in...

Citations

... Several recent studies on crop diseases detection from UAV imagery are based on deep learning models to overcome the limitations of traditional techniques, especially Convolutional Neural Network (CNN) algorithms. Most of these studies targeted subsistence crops such as wheat Pan et al. [56], Su et al. [72], Zhang et al. [87], maize Wiesner-Hanks et al. [80], Stewart et al. [71], potato Théau et al. [77], Siebring et al. [66], and tomato Abdulridha et al. [3], Abdulridha et al. [2]. ...
Article
Full-text available
The agricultural crop productivity can be affected and reduced due to many factors such as weeds, pests, and diseases. Traditional methods that are based on terrestrial engines, devices, and farmers' naked eyes are facing many limitations in terms of accuracy and the required time to cover large fields. Currently, precision agriculture that is based on the use of deep learning algorithms and Unmanned Aerial Vehicles (UAVs) provides an effective solution to achieve agriculture applications, including plant disease identification and treatment. In the last few years, plant disease monitoring using UAV platforms is one of the most important agriculture applications that have gained increasing interest by researchers. Accurate detection and treatment of plant diseases at early stages is crucial to improving agricultural production. To this end, in this review, we analyze the recent advances in the use of computer vision techniques that are based on deep learning algorithms and UAV technologies to identify and treat crop diseases.
... In potato, studies have been conducted on quantifying disease severity using the RGB images by detecting pixels of diseased leaves with that of healthy leaves and soil. It was shown that the diseased leaves could be clearly distinguished from the transformed color spaces (Sugiura et al., 2016) or spectral indices (Gibson-Poole et al., 2017;Siebring et al., 2019) from the RGB color space. Also due to the contrast between plant and soil background captured by the RGB image, promising applications have been seen in detecting potato emergence (Gibson-Poole et al., 2018;Li et al., 2019) and calculating ground vegetation coverage (Gibson-Poole et al., 2018). ...
Article
Full-text available
Potato is one of the most significant food crops globally due to its essential role in the human diet. The growing demand for potato, coupled with severe environmental losses caused by extensive farming activities, implies the need for better crop protection and management practices. Precision agriculture is being well recognized as the solution as it deals with the management of spatial and temporal variability to improve agricultural returns and reduce environmental impact. As the initial step in precision agriculture, the traditional methods of crop and field characterization require a large input in labor, time, and cost. Recent developments in remote sensing technologies have facilitated the process of monitoring crops and quantifying field variations. Successful applications have been witnessed in the area of precision potato farming. Thus, this review reports the current knowledge on the applications of remote sensing technologies in precision potato trait characterization. We reviewed the commonly used imaging sensors and remote sensing platforms with the comparisons of their strengths and limitations and summarized the main applications of the remote sensing technologies in potato. As a result, this review could update potato agronomists and farmers with the latest approaches and research outcomes, as well as provide a selective list for those who have the intentions to apply remote sensing technologies to characterize potato traits for precision agriculture.
... The detection of such delicate changes in the ground cover from VHR images provided by UAVs is suitable. As small-scale changes cannot be detected at low resolutions (see Figure 3), it is important to address the possibility of obtaining high spatial and temporal resolution UAV data that are suitable for generating detailed land cover maps [89]. ...
... Nevertheless, they are carefully analyzed in order to make the most of the depth of field provided by the UAV. One of the possible solutions while collecting UAV images in complex terrains is to increase the overlap between images and to increase the number of the GCPs in order to enhance the orthorectification and overall quality of the orthomosaic [89,91]. The study site Babin zub, located on the top of the mountain, was demanding not only for UAV image acquisition but also for the performances of the photogrammetry software. ...
Article
Full-text available
Habitat degradation, mostly caused by human impact, is one of the key drivers of biodiversity loss. This is a global problem, causing a decline in the number of pollinators, such as hoverflies. In the process of digitalizing ecological studies in Serbia, remote-sensing-based land cover classification has become a key component for both current and future research. Object-based land cover classification, using machine learning algorithms of very high resolution (VHR) imagery acquired by an unmanned aerial vehicle (UAV) was carried out in three different study sites on Mt. Stara Planina, Eastern Serbia. UAV land cover classified maps with seven land cover classes (trees, shrubs, meadows, road, water, agricultural land, and forest patches) were studied. Moreover, three different classification algorithms—support vector machine (SVM), random forest (RF), and k-NN (k-nearest neighbors)—were compared. This study shows that the random forest classifier performs better with respect to the other classifiers in all three study sites, with overall accuracy values ranging from 0.87 to 0.96. The overall results are robust to changes in labeling ground truth subsets. The obtained UAV land cover classified maps were compared with the Map of the Natural Vegetation of Europe (EPNV) and used to quantify habitat degradation and assess hoverfly species richness. It was concluded that the percentage of habitat degradation is primarily caused by anthropogenic pressure, thus affecting the richness of hoverfly species in the study sites. In order to enable research reproducibility, the datasets used in this study are made available in a public repository.
... Rapid advances in unmanned aerial vehicle (UAV) technology have been applied to many areas of agricultural research, including estimation of plant height with the RMSE of 0.02-0.07 m using digital surface model (DSM) [14], estimation of canopy cover with a determination coefficient R 2 = 0.99 using a decision-tree-based segmentation model [15,16], estimation of canopy temperature using a miniature longwave infrared camera [17], evaluating the water status of soybean plants via thermal images [18], estimation of leaf chlorophyll content using a hyperspectral line scanner and random forest models [19], estimation of nitrogen content using multispectral data [20], estimation of biomass with an R² = 0.71 using DSM [21], and estimation of soybean and potato yield using RGB, multispectral, hyperspectral, and thermal data [22,23], identification of pests and diseases of potato using object-based image analysis method and random forest model [24], and cotton seedling detection and counting with an R² = 0.98 using a deep-learning-based approach [25]. Furthermore, previous studies on crop characteristics have used UAV images to fit sigmoid functions to simulate crop growth. ...
Article
Full-text available
Convenient, efficient, and high-throughput estimation of wheat heading dates is of great significance in plant sciences and agricultural research. However, documenting heading dates is time-consuming, labor-intensive, and subjective on a large-scale field. To overcome these challenges, model- and image-based approaches are used to estimate heading dates. Phenology models usually require complicated parameters calibrations, making it difficult to model other varieties and different locations, while in situ field-image recognition usually requires the deployment of a large amount of observational equipment, which is expensive. Therefore, in this study, we proposed a growth curve-based method for estimating wheat heading dates. The method first generates a height-based continuous growth curve based on five time-series unmanned aerial vehicle (UAV) images captured over the entire wheat growth cycle (>200 d). Then estimate the heading date by generated growth curve. As a result, the proposed method had a mean absolute error of 2.81 d and a root mean square error of 3.49 d for 72 wheat plots composed of different varieties and densities sown on different dates. Thus, the proposed method is straightforward, efficient, and affordable and meets the high-throughput estimation requirements of large-scale fields and underdeveloped areas.
... Unmanned aerial vehicles (UAVs) with RGB cameras are used with crops such as sorghum, corn, tomato, and rice. Information on the agricultural environment, crop surveillance, crop phenotypic traits, crop symptoms, and disaster damage research can be conducted or gathered [29,[31][32][33][34][35]. However, UAVs are currently less used for long-term continual observation. ...
Article
Full-text available
Rice is one of the three major crops in the world and is the major crop in Asia. Climate change and water resource shortages may result in decreases in rice yields and possible food shortage crises. In this study, water-saving farming management was tested, and IOT field water level monitoring was used to regulate water inflow automatically. Plant height (PH) is an important phenotype to be used to determine difference in rice growth periods and yields using water-saving irrigation. An unmanned aerial vehicle (UAV) with an RGB camera captured sequential images of rice fields to estimate rice PH compared with PH measured on site for estimating rice growth stages. The test results, with two crop harvests in 2019, revealed that with adequate image calibration, the correlation coefficient between UAV-PH and field-PH was higher than 0.98, indicating that UAV images can accurately determine rice PH in the field and rice growth phase. The study demonstrated that water-saving farming is effective, decreasing water usage for the first and second crops of 2019 by 53.5% and 21.7%, respectively, without influencing the growth period and final yield. Coupled with an automated irrigation system, rice farming can be adaptive to water shortage situations.
... These observations were verified by tests carried out in the laboratory. The developed models were able to correctly recognize approximately 70% of cases [16]. ...
Article
Full-text available
This paper describes the research aimed at developing an effective quality assessment method for potato tubers using neural image analysis techniques. Nowadays, the methods used to identify damage and diseases are time-consuming, require specialized knowledge, and often rely on subjective judgment. This study showed the use of the developed neural model as a tool supporting the evaluation of potato tubers during the sorting process in the storage room.
... After ensuring the quality of images, the focus is on extracting characterization attributes, such as color, shape, texture, and statistics for the target or symptoms produced in the plant (BAH et al., 2018;ZHANG et al., 2018;SIEBRING et al., 2019). However, the agricultural environment is challenging due to the complexity of its elements patterns and dynamics. ...
Article
Full-text available
Unmanned Aerial Vehicles (UAVs) have potentially significant application in agriculture and, with the emergence of the digital farming era and Agriculture 4.0, this platform has become increasingly important. UAV imagery may improve or even replace routine data surveys, as well as optimize phytosanitary product application. High-spatial resolution imagery makes UAVs attractive for several applications where traditional satellite sensing is still unsuitable. With the significant recent development of data science techniques, UAVs have a prominent position in assisting farmers for more efficient decision-making and automating agricultural processes. Thus, this work addresses the main agricultural applications of UAVs into five major topics: topographic survey, physiological assessments, biophysical assessments, monitoring of biological targets, and spraying of phytosanitary products and application of bio inputs.
Article
The early detection of diseases in plants through artificial intelligence techniques has been a very important technological advance for agriculture since, through machine learning and optimization algorithms, it has been possible to increase the yield of various crops in several countries around the world. Different researchers have focused their efforts on developing models that allow supporting the task of detecting diseases in plants as a solution to the traditional techniques used by farmers. In this systematic literature review, an analysis of the most relevant articles is presented, in which image processing techniques and machine learning were used to detect diseases by means of images of the leaves of different crops. In turn, an analysis of the interpretability and precision of these methods is carried out, considering each phase of the image processing, segmentation, feature extraction and learning processes of each model. In this way, there is evidence of a void in the field of interpretability since the authors have focused mainly on obtaining good results in their models, beyond providing the user with a clear explanation of the characteristics of the model.