No file available
To read the file of this research,
you can request a copy directly from the authors.
Real-Time Detection of Strawberry Ripeness Using Augmented Reality and Deep Learning
Preprints and early-stage research may not have been peer reviewed yet.
Recent advances in artificial intelligence and computer vision have led to significant progress in the use of agricultural technologies for yield prediction, pest detection, and real-time monitoring of plant conditions. However, collecting large-scale, high-quality image datasets in the agriculture sector remains challenging, particularly for specialized datasets such as plant disease images. This study analyzed the effects of the image size (320–640+) and the number of labels on the performance of a YOLO-based object detection model using diverse agricultural datasets for strawberries, tomatoes, chilies, and peppers. Model performance was evaluated using the intersection over union and average precision (AP), where the AP curve was smoothed using the Savitzky–Golay filter and EEM. The results revealed that increasing the number of labels improved the model performance to a certain degree, after which the performance gradually diminished. Furthermore, while increasing the image size from 320 to 640 substantially enhanced the model performance, additional increases beyond 640 yielded only marginal improvements. However, the training time and graphics processing unit usage scaled linearly with increasing image sizes, as larger size images require greater computational resources. These findings underscore the importance of an optimal strategy for selecting the image size and label quantity under resource constraints in real-world model development.
In order to accurately detect the maturity of chili peppers under different lighting and natural environmental scenarios, in this study, we propose a lightweight maturity detection model, YOLOv8-CBSE, based on YOLOv8n. By replacing the C2f module in the original model with the designed C2CF module, the model integrates the advantages of convolutional neural networks and Transformer architecture, improving the model’s ability to extract local features and global information. Additionally, SRFD and DRFD modules are introduced to replace the original convolutional layers, effectively capturing features at different scales and enhancing the diversity and adaptability of the model through the feature fusion mechanism. To further improve detection accuracy, the EIoU loss function is used instead of the CIoU loss function to provide more comprehensive loss information. The results showed that the average precision (AP) of YOLOv8-CBSE for mature and immature chili peppers was 90.75% and 85.41%, respectively, with F1 scores and a mean average precision (mAP) of 81.69% and 88.08%, respectively. Compared with the original YOLOv8n, the F1 score and mAP of the improved model increased by 0.46% and 1.16%, respectively. The detection effect for chili pepper maturity under different scenarios was improved, which proves the robustness and adaptability of YOLOv8-CBSE. YOLOv8-CBSE also maintains a lightweight design with a model size of only 5.82 MB, enhancing its suitability for real-time applications on resource-constrained devices. This study provides an efficient and accurate method for detecting chili peppers in natural environments, which is of great significance for promoting intelligent and precise agricultural management.
The recognition and localization of strawberries are crucial for automated harvesting and yield prediction. This article proposes a novel RTF-YOLO (RepVgg-Triplet-FocalLoss-YOLO) network model for real-time strawberry detection. First, an efficient convolution module based on structural reparameterization is proposed. This module was integrated into the backbone and neck networks to improve the detection speed. Then, the triplet attention mechanism was embedded into the last two detection heads to enhance the network’s feature extraction for strawberries and improve the detection accuracy. Lastly, the focal loss function was utilized to enhance the model’s recognition capability for challenging strawberry targets, which thereby improves the model’s recall rate. The experimental results demonstrated that the RTF-YOLO model achieved a detection speed of 145 FPS (frames per second), a precision of 91.92%, a recall rate of 81.43%, and an mAP (mean average precision) of 90.24% on the test dataset. Relative to the baseline of YOLOv5s, it showed improvements of 19%, 2.3%, 4.2%, and 3.6%, respectively. The RTF-YOLO model performed better than other mainstream models and addressed the problems of false positives and false negatives in strawberry detection caused by variations in illumination and occlusion. Furthermore, it significantly enhanced the speed of detection. The proposed model can offer technical assistance for strawberry yield estimation and automated harvesting.
Post-harvest grain processes play a crucial role in food supply chains. Recent research focuses on how digital technologies can minimize grain losses, enhance food safety, and reduce their environmental impacts. The relationship between technologies and efficiency and sustainability needs more clarity, particularly concerning critical control points in post-harvest activities. The purpose of this article is to establish a connection between digital technologies used in food supply chains and critical control points within post-harvest systems. The research method is a bibliometric analysis. A literature survey identified thirteen digital technologies. The most published technologies are simulation, automation, and artificial intelligence. The least is augmented reality. Previous research identified nine critical control points in post-harvest engineering solutions, responsible for most losses in efficiency and environmental impacts. A framework using a sample of recent case studies was constructed to relate digital technologies and critical control points. The primary contribution of the study is a categorized list of the most influential technologies corresponding to each control point. The significance and novelty lie in providing managers and practitioners in engineering solutions for post-harvest systems with a practical guide for decision-making in the selection of technologies for future projects. Ultimately, this aids in reducing losses and environmental impact.
Image analysis-based artificial intelligence (AI) models leveraging convolutional neural networks (CNN) take a significant role in evaluating the ripeness of strawberry, contributing to the maximization of productivity. However, the convolution, which constitutes the majority of the CNN models, imposes significant computational burdens. Additionally, the dense operations in the fully connected (FC) layer necessitate a vast number of parameters and entail extensive external memory access. Therefore, reducing the computational burden of convolution operations and alleviating memory overhead is essential in embedded environment. In this paper, we propose a strawberry ripeness classification system utilizing a convolution-based feature extractor (CoFEx) for accelerating convolution operations and an edge AI processor, Intellino, for replacing FC layer operations. We accelerated feature map extraction utilizing the CoFEx constructed with systolic array (SA) and alleviated the computational burden and memory overhead associated with the FC layer operations by replacing them with the k-nearest neighbors (k-NN) algorithm. The CoFEx and the Intellino both were designed with Verilog HDL and implemented on a field-programmable gate array (FPGA). The proposed system achieved a high precision of 93.4%, recall of 93.3%, and F1 score of 0.933. Therefore, we demonstrated a feasibility of the strawberry ripeness classification system operating in an embedded environment.
ResearchGate has not been able to resolve any references for this publication.