基于YOLOv5的平贝母检测装置试验研究  

Experimental study of Fritillary Bulb Detection Device Based on YOLOV5

作　　者：宋江[1] 赵伟 SONG Jiang;ZHAO Wei(College of Engineering,Heilongjiang Bayi Agricultural University,Daqing 163319,China)

机构地区：[1]黑龙江八一农垦大学工程学院,黑龙江大庆163319

出　　处：《农机使用与维修》2024年第8期1-7,共7页Agricultural Machinery Using & Maintenance

基　　金：“三纵”基础培育计划项目(ZRCPY202011);“三纵”基础培育计划项目(ZDZRCPY201802)。

摘　　要：目前,平贝母表土剥离机在工作过程中存在刮土调节慢,导致平贝母损伤高的问题,要想实现表土剥离机智能调节刮土,第一步在于实现其智能识别。该文以YOLOv5系列为基础模型,在骨干段加入SENet注意力机制替换其C3进行结合,并将改进后的模型部署到Jetson Nano开发板中,搭建平贝母检测系统,通过正交试验验证该文改进模型移植的可行性,试验结果表明,平贝母检测的准确度最高可达86.61%。研究结果可为下一步平贝母表土剥离机实现智能刮土提供理论参考。At present,there is a problem that the flat fritillary topsoil stripping machine has slow scraping adjustment in the working process,resulting in high damage of the flat fritillary,and the first step is to realize its intelligent identification in order to realize the intelligent adjustment of the topsoil stripping machine.In this paper,the YOLOv5 series is used as the basic model,the SENet attention mechanism is added to the backbone segment to replace its C3 for combination,and the improved model is deployed to the Jetson Nano development board to build a flat fritillary detection system,and the feasibility of the improved model transplantation is verified by orthogonal experiments.The test results showed that the accuracy of the detection of flat fritillary could reach up to 86.61%.The research results can provide a theoretical reference for the next step of the flat fritillary topsoil stripping machine to achieve intelligent scraping.

关 键 词：平贝母 YOLOv5 Jetson Nano 

分 类 号：S225[农业科学—农业机械化工程] TP391.41[农业科学—农业工程]