Weed Detection in Potato Fields Based on Improved YOLOv4: Optimal Speed and Accuracy of Weed Detection in Potato Fields

The key to precise weeding in the field lies in the efficient detection of weeds. There are no studies on weed detection in potato fields. In view of the difficulties brought by the cross-growth of potatoes and weeds to the detection of weeds, the existing detection methods cannot meet the requirements of detection speed and detection accuracy at the same time. This study proposes an improved YOLOv4 model for weed detection in potato fields. The proposed algorithm replaces the backbone network CSPDarknet53 in the YOLOv4 network structure with the lightweight MobileNetV3 network and introduces Depthwise separable convolutions instead of partial traditional convolutions in the Path Aggregation Network (PANet), which reduces the computational cost of the model and speeds up its detection. In order to improve the detection accuracy, the convolutional block attention module (CBAM) is fused into the PANet structure, and the CBAM will process the input feature map with a channel attention mechanism (CAM) and spatial attention mechanism (SAM), respectively, which can enhance the extraction of useful feature information. The K-means++ clustering algorithm is used instead of the K-means clustering algorithm to update the anchor box information of the model so that the anchor boxes are more suitable for the datasets in this study. Various image processing methods such as CLAHE, MSR, SSR, and gamma are used to increase the robustness of the model, which eliminates the problem of overfitting. CIoU is used as the loss function, and the cosine annealing decay method is used to adjust the learning rate to make the model converge faster. Based on the above-improved methods, we propose the MC-YOLOv4 model. The mAP value of the MC-YOLOv4 model in weed detection in the potato field was 98.52%, which was 3.2%, 4.48%, 2.32%, 0.06%, and 19.86% higher than YOLOv4, YOLOv4-tiny, Faster R-CNN, YOLOv5 l, and SSD(MobilenetV2), respectively, and the average detection time of a single image was 12.49ms. The results show that the optimized method proposed in this paper outperforms other commonly used target detection models in terms of model footprint, detection time consumption, and detection accuracy. This paper can provide a feasible real-time weed identification method for the system of precise weeding in potato fields with limited hardware resources. This model also provides a reference for the efficient detection of weeds in other crop fields and provides theoretical and technical support for the automatic control of weeds.

[1]  Wenkai Cao,et al.  Weed Detection in Peanut Fields Based on Machine Vision , 2022, Agriculture.

[2]  Yankun Peng,et al.  SE-YOLOv5x: An Optimized Model Based on Transfer Learning and Visual Attention Mechanism for Identifying and Localizing Weeds and Vegetables , 2022, Agronomy.

[3]  Qifan Wang,et al.  A deep learning approach incorporating YOLO v5 and attention mechanisms for field real-time detection of the invasive weed Solanum rostratum Dunal seedlings , 2022, Comput. Electron. Agric..

[4]  Baoxing Gu,et al.  Review of agricultural IoT technology , 2022, Artificial Intelligence in Agriculture.

[5]  Ioannis Malounas,et al.  Testing the Suitability of Automated Machine Learning for Weeds Identification , 2021, AI.

[6]  Gerassimos Peteinatos,et al.  Weed Identification in Maize, Sunflower, and Potatoes with the Aid of Convolutional Neural Networks , 2020, Remote. Sens..

[7]  Soo Young Shin,et al.  An Improved Deep Convolutional Neural Network-Based Autonomous Road Inspection Scheme Using Unmanned Aerial Vehicles , 2020, Electronics.

[8]  Cristiano Saltori,et al.  Deep Learning for Classification and Localization of COVID-19 Markers in Point-of-Care Lung Ultrasound , 2020, IEEE Transactions on Medical Imaging.

[9]  Bruce Grieve,et al.  High Speed Crop and Weed Identification in Lettuce Fields for Precision Weeding , 2020, Sensors.

[10]  Yiannis Ampatzidis,et al.  Development and evaluation of a low-cost and smart technology for precision weed management utilizing artificial intelligence , 2019, Comput. Electron. Agric..

[11]  Jan Tommy Gravdahl,et al.  Robotic in-row weed control in vegetables , 2018, Comput. Electron. Agric..

[12]  P. Singh,et al.  Assessment of yield and economic losses in agriculture due to weeds in India , 2018 .

[13]  Abdolabbas Jafari,et al.  Evaluation of support vector machine and artificial neural networks in weed detection using shape features , 2018, Comput. Electron. Agric..

[14]  Hemerson Pistori,et al.  Weed detection in soybean crops using ConvNets , 2017, Comput. Electron. Agric..

[15]  Yang Xu,et al.  Weed identification based on K-means feature learning combined with convolutional neural network , 2017, Comput. Electron. Agric..

[16]  Yuning Jiang,et al.  UnitBox: An Advanced Object Detection Network , 2016, ACM Multimedia.

[17]  Jia Lei,et al.  Deep Learning: Yesterday, Today, and Tomorrow , 2013 .

[18]  Henrik Skov Midtiby,et al.  Performance evaluation of a crop/weed discriminating microsprayer , 2011 .

[19]  N. D. Tillett,et al.  Mechanical within-row weed control for transplanted crops using computer vision , 2008 .

[20]  H. T. Søgaard,et al.  Application Accuracy of a Machine Vision-controlled Robotic Micro-dosing System , 2007 .

[21]  Leonardo Solaque,et al.  Weed recognition by SVM texture feature classification in outdoor vegetable crops images , 2017 .

[22]  David C. Slaughter,et al.  Review: Automatic GPS-based intra-row weed knife control system for transplanted row crops , 2012 .