Du Pengcheng, Chen Shang, Li Xu, Hu Wenwu, Lan Nan, Lei Xiangming, Xiang Yang
College of Mechanical and Electrical Engineering, Hunan Agricultural University, Changsha, China.
Front Plant Sci. 2024 Jul 16;15:1417682. doi: 10.3389/fpls.2024.1417682. eCollection 2024.
Green pepper yield estimation is crucial for establishing harvest and storage strategies.
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.
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 before and after DeepSort optimization is compared. For green pepper counting in videos, the optimized DeepSort algorithm achieves ACP (Average Counting Precision), MAE (Mean Absolute Error), and RMSE (Root Mean Squared Error) values of 95.33%, 3.33, and 3.74, respectively. Compared to the original algorithm, ACP increases by 7.2%, while MAE and RMSE decrease by 6.67 and 6.94, respectively. Additionally, Based on the optimized DeepSort, the fruit counting results using YOLOv5s model and CS_YOLOv5s model were compared, and the results show that using the better object detector CS_YOLOv5s has better counting accuracy and robustness.
青椒产量估计对于制定收获和储存策略至关重要。
本文提出了一种基于目标检测和多目标跟踪算法的青椒果实自动计数方法。青椒果实颜色与叶子相似，且常相互遮挡，给检测带来挑战。基于YOLOv5s，专门设计了CS_YOLOv5s模型用于青椒果实检测。在CS_YOLOv5s模型中，颈部采用了Slim-Nick与GSConv相结合的结构，以减少模型参数同时提高检测速度。此外，将CBAM注意力机制集成到颈部，以增强对不同位置青椒的特征感知并提升模型的特征提取能力。
根据测试结果，CS_YOLOv5s模型的平均精度均值（mAP）、精确率（Precision）、召回率（Recall）以及单张图像的检测时间分别为98.96%、95%、97.3%和6.3毫秒。与YOLOv5s模型相比，单张图像的检测时间减少了34.4%，同时召回率和mAP值有所提高。此外，对于青椒果实跟踪，本文结合了SportsTrack中的外观匹配算法和轨迹优化算法对DeepSort算法进行优化。考虑三种不同的跟踪场景，多目标跟踪精度（MOTA）和多目标跟踪误差（MOTP）较为稳定，但身份切换减少了29.4 %。基于CS_YOLOv5s模型，比较了DeepSort优化前后的计数性能。对于视频中的青椒计数，优化后的DeepSort算法的平均计数精度（ACP）、平均绝对误差（MAE）和均方根误差（RMSE）值分别为95.33%、3.33和3.74。与原算法相比，ACP提高了7.2%，而MAE和RMSE分别下降了6.67和6.94。此外，基于优化后的DeepSort，比较了使用YOLOv5s模型和CS_YOLOv5s模型的果实计数结果，结果表明使用更好的目标检测器CS_YOLOv5s具有更好的计数准确性和鲁棒性。
