面向复杂田间收获作业的轻量化三七目标检测方法  

Lightweight object detection method for Panax Notoginseng in complex field harvesting

作　　者：王法安 何忠平 张兆国[1,2] 解开婷 房汉玉 WANG Fa'an;HE Zhongping;ZHANG Zhaoguo;XIE Kaiting;FANG Hanyu(Faculty of Modern Agricultural Engineering,Kunming University of Science and Technology,Kunming 650500,China;Research Center on Mechanization Engineering of Chinese Medicinal Materials in Yunnan Universities,Kunming 650500,China;Faculty of Mechanical and Electrical Engineering,Kunming University of Science and Technology,Kunming 650500,China;Tangyuan County Agricultural Technology Extension Service Center,Jiamusi 154000,China)

机构地区：[1]昆明理工大学现代农业工程学院,昆明650500 [2]云南省高校中药材机械化工程研究中心,昆明650500 [3]昆明理工大学机电工程学院,昆明650500 [4]黑龙江佳木斯汤原县农业技术推广中心,佳木斯154000

出　　处：《农业工程学报》2024年第8期133-143,共11页Transactions of the Chinese Society of Agricultural Engineering

基　　金：国家重点研发计划项目(2022YFD2002004);云南省基础研究专项-青年基金项目(202401AU070196)。

摘　　要：针对目前三七检测算法在复杂田间收获工况下检测精度低、模型复杂度大、移动端部署难等问题,该研究提出一种基于YOLOv5s的轻量化三七目标检测方法。首先,采用GSConv卷积方法替换原始颈部网络的传统卷积,引入Slim-neck轻量级颈部网络,降低了模型复杂度,同时提升了模型精度;其次,使用ShuffleNetv2轻量型特征提取网络对主干网络进行轻量化改进,提升了模型实时检测性能,并采用角度惩罚度量的损失(SIoU)优化边界框损失函数,提升了轻量化后的模型精度和泛化能力。试验结果表明,改进后的PN-YOLOv5s模型参数量、计算量、模型大小分别为原YOLOv5s模型的46.65%、34.18%和48.75%,检测速度提升了1.2倍,F_(1)值较原始模型提升了0.22个百分点,平均精度均值达到了94.20%,较原始模型低0.6个百分点,与SSD、Faster R-CNN、YOLOv4-tiny、YOLOv7-tiny和YOLOv8s模型相比能够更好地平衡检测精度与速度,检测效果更好。台架试验测试结果表明,4种输送分离作业工况下三七目标检测的准确率达90%以上,F_(1)值达86%以上,平均精度均值达87%以上,最低检测速度为105帧/s,实际收获工况下模型的检测性能良好,可为后续三七收获作业质量实时监测与精准分级输送提供技术支撑。Intelligent harvesting is often required for object detection under complex field conditions,especially in the process of the real-time monitoring of harvesting quality and accurate grading conveyor.Taking Panax Notoginseng as the research plant,this study aims to propose lightweight object detection using YOLOv5s.The complex field conditions included the large variations in the light intensity,the difficulty in separating the roots from the soil,easy entanglement of roots,variable lifting speed,vibration amplitude,and frequency.The optimal model was also obtained with the high accuracy,and low complexity of a large model suitable for the deployment of mobile terminals.Firstly,a sample dataset was collected from the Panax Notoginseng in the complex field.The influence parameters of transportation and separation were also determined for the complex root-soil system;Secondly,real-time detection was realized under complex field conditions.Slim-neck lightweight neck network was introduced into the lightweight convolution of GSConv.The original SPPF feature fusion module was retained,while the ShuffleNetv2 lightweight feature extraction network was used to improve the original backbone network,which greatly reduced the model complexity with the model accuracy;Finally,the loss function with angular penalty metric(SCYLLA-IoU,SIoU)was used to optimize the bounding box loss function,in order to enhance the detection accuracy and generalization performance of the lightweight improved model.Ablation experiments were carried out to verify three improvement strategies,namely the Slim-neck neck feature extraction network,ShuffleNetv2 backbone feature extraction network,and SIoU bounding box loss function.The experimental results showed that the improved lightweight model(PNYOLOv5s)had 3.27×106 M parameters,5.4 G computational complexity,6.85 MB weight size,and a detection speed of 108 frames per second.The number of parameters and weight size were approximately half of the original YOLOv5s,while the computational complexity w

关 键 词：神经网络 目标检测 轻量化 复杂收获作业工况 三七 YOLOv5s 

分 类 号：S220.1[农业科学—农业机械化工程]