Green pepper fruits counting based on improved DeepSort and optimized Yolov5s

作者：Pengcheng Du, Shang Chen, Xu Li, Wenwu Hu, Nan Lan, Xiangming Lei, Yang Xiang · 发表于：Frontiers in Plant Science · 年份：2024 · DOI：10.3389/fpls.2024.1417682 · 被引用次数：11 · 研究领域：Smart Agriculture and AI、Advanced Data and IoT Technologies、Advanced Neural Network Applications

Introduction: Green pepper yield estimation is crucial for establishing harvest and storage strategies. Method: This paper proposes an automatic counting method for green pepper fruits based on object detection and multi-object tracking algorithm. Green pepper fruits have colors similar to leaves and are often occluded by each other, posing challenges for detection. Based on the YOLOv5s, the CS_YOLOv5s model is specifically designed for green pepper fruit detection. In the CS_YOLOv5s model, a Slim-Nick combined with GSConv structure is utilized in the Neck to reduce model parameters while enhancing detection speed. Additionally, the CBAM attention mechanism is integrated into the Neck to enhance the feature perception of green peppers at various locations and enhance the feature extraction capabilities of the model. Result: According to the test results, the CS_YOLOv5s model of mAP, Precision and Recall, and Detection time of a single image are 98.96%, 95%, 97.3%, and 6.3 ms respectively. Compared to the YOLOv5s model, the Detection time of a single image is reduced by 34.4%, while Recall and mAP values are improved. Additionally, for green pepper fruit tracking, this paper combines appearance matching algorithms and track optimization algorithms from SportsTrack to optimize the DeepSort algorithm. Considering three different scenarios of tracking, the MOTA and MOTP are stable, but the ID switch is reduced by 29.41%. Based on the CS_YOLOv5s model, the counting performance bef...