基于机器视觉的蚕豆荚高精度检测方法研究

doi:10.13733/j.jcam.issn.2095-5553.2025.01.024

摘要/Abstract

摘要： 蚕豆荚检测是蚕豆自动化采摘的前提与基础，因此，实现蚕豆荚的快速、准确识别与定位十分关键。基于此，提出一种基于深度学习的蚕豆荚检测方法YOLO-B。为增大整体网络的感受野，获取目标丰富的上下文信息从而提高检测精度，提出SPPX模块。由于蚕豆荚特征较为相似，为消除冗余特征，提出GhostPAN特征融合模块。经过对比试验分析，相比于其他YOLOv7、YOLOv5与YOLOv4，YOLO-B参数量（29092M）和计算量（95.466G）最低，mAP（92.58%）最高，分别提升1.33%、2.75%与3.74%。在蚕豆荚特征差异较小、生长姿态差异较大的场景下，均能实现准确检测。

关键词: 蚕豆荚, 目标检测, 深度学习, YOLO

Abstract: The detection of broad bean pods is the basis of automatic picking of broad bean, it plays an important role to realize rapid and accurate identification and positioning of broad bean pods. In this paper, a deep learningbased accurate detection method of broad bean pods （i.e., YOLO-B） was proposed. A SPPX module was proposed to improve the detection accuracy, which could enlarge the receptive field of the whole network and obtain the rich context information of the target. Since the characteristics of broad bean pods were similar, a feature fusion module （i.e., GhostPAN） was proposed to eliminate redundant features. Compared to other YOLOv7, YOLOv5 and YOLOv4 algorithms, the number of parameter YOLO-B （29.092M） and computational power （95.466G） were the lowest, while mAP （92.58%） was the highest, increasing by 1.33%, 2.75% and 3.74%, respectively. The accurate detection can be achieved in the scenarios with small differences in pod characteristics and large differences in growth posture.

Key words: broad bean pods, object detection, deep learning, YOLO

中图分类号:

TP391

夏子林, 张新洲, 王文波, 夏先飞, 陈兰, 顾寄南. 基于机器视觉的蚕豆荚高精度检测方法研究[J]. 中国农机化学报, 2025, 46(1): 157-163.

Xia Zilin, Zhang Xinzhou, Wang Wenbo, Xia Xianfei, Chen Lan, Gu Jinan. Research on high precision detection method of broad bean pods based on machine vision[J]. Journal of Chinese Agricultural Mechanization, 2025, 46(1): 157-163.

参考文献

［1］　李旭. 蚕豆综合加工利用研究进展［J］. 现代食品, 2018（7）: 170-171.
Li Xu. Research progress of comprehensive processing and utilization of broad beans ［J］. Modern Food, 2018 （7）: 170-171.
［2］　张阳婷,黄德启,王东伟,等.基于深度学习的目标检测算法研究与应用综述［J］.计算机工程与应用, 2023, 59（18）: 1-13.
Zhang Yangting, Huang Deqi, Wang Dongwei, et al. A review on research and application of deep learningbased target detection algorithms ［J］. Computer Engineering and Applications，2023, 59（18）: 1-13.
［3］　张志杰,顾寄南,李静，等.基于深度学习的电子元器件快速检测算法研究［J］. 电子测量技术, 2022, 45（10）: 93-101.
Zhang Zhijie, Gu Jinan, Li Jing, et al. Research on fast electronic component detection algorithm based on deep learning ［J］. Electronic Measurement Technology, 2022, 45（10）: 93-101.
［4］　张可,顾寄南,夏子林，等.基于深度学习的色环电阻检测与判读方法研究［J］.电子测量技术,2022, 45（11）: 126-133.
Zhang Ke, Gu Jinan, Xia Zilin, et al. Research on color ring resistor detection and interpretation method based on deep learning ［J］. Electronic Measurement Technology, 2022, 45（11）: 126-133.
［5］　Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation ［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition， 2014: 580-587.
［6］　Girshick R. Fast R-CNN ［C］. Proceedings of the IEEE International Conference on Computer Vision， 2015: 1440-1448.
［7］　Ren S, He K, Girshick R, et al. Faster R-CNN: Towards realtime object detection with region proposal networks ［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39（6）:1137-1149.
［8］　He K, Gkioxari G, Dollár P, et al. Mask R-CNN ［C］.Proceedings of the IEEE International Conference on Computer Vision， 2017: 2961-2969.
［9］　程书帅,王霄,李伟,等. 基于改进YOLOv4的轻量级目标检测算法研究［J］.微电子学与计算机, 2023, 40（6）: 1-8.
Cheng Shushuai, Wang Xiao, Li Wei, et al. Research on lightweight target detection algorithm based on improved YOLOv4 ［J］. Microelectronics & Computer, 2023, 40（6）: 1-8.
［10］　王琳毅,白静,李文静,等.YOLO系列目标检测算法研究进展［J］.计算机工程与应用, 2023, 59（14）: 15-29.
Wang Linyi, Bai Jing, Li Wenjing, et al. Research progress of YOLO series target detection algorithms ［J］. Computer Engineering and Applications, 2023, 59（14）: 15-29.
［11］　Liu W, Anguelov D, Erhan D, et al. Ssd: Single shot multibox detector ［C］. Computer VisionECCV 2016: 14th European Conference, Amsterdam, the Netherlands, October 11-14, 2016, Proceedings, Part Ⅰ 14. Springer International Publishing, 2016: 21-37.
［12］　Lin T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection ［C］. Proceedings of the IEEE International Conference on Computer Vision， 2017: 2980-2988.
［13］　翔云,陈其军,宋栩杰,等.基于深度学习的菜用大豆荚型表型识别方法［J］.核农学报, 2022, 36（12）: 2391-2399.
Xiang Yun, Chen Qijun, Song Xujie, et al. Deep learningbased identification method for vegetable soybean pod morphology traits ［J］. Journal of Nuclear Agricultural Sciences, 2022, 36（12）: 2391-2399.
［14］　杨肖,袁锐波,李兆旭,等.改进YOLOv4的蚕豆苗检测算法及TensorRT加速［J］.重庆理工大学学报（自然科学）, 2023, 37（3）: 312-320.
Yang Xiao, Yuan Ruibo, Li Zhaoxu, et al. The improved YOLOv4 algorithm for broad bean sprout detection and TensorRT acceleration ［J］. Journal of Chongqing University of Technology （Natural Science）, 2023, 37（3）: 312-320.
［15］　郭希岳,李劲松,郑立华,等.利用Re-YOLOv5和检测区域搜索算法获取大豆植株表型参数［J］.农业工程学报, 2022, 38（15）: 186-194.
Guo Xiyue, Li Jinsong, Zheng Lihua, et al. Acquiring soybean phenotypic parameters using Re-YOLOv5 and area search algorithm ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38（15）: 186-194.
［16］　Ma J, Dai Y, Tan Y P. Atrous convolutions spatial pyramid network for crowd counting and density estimation ［J］. Neurocomputing, 2019, 350: 91-101.
［17］　Liu S, Qi L, Qin H, et al. Path aggregation network for instance segmentation ［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 8759-8768.
［18］　Han K, Wang Y, Tian Q, et al. Ghostnet: More features from cheap operations ［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 1580-1589.
［19］　Tang Y, Han K, Guo J, et al. GhostNetV2: Enhance cheap operation with longrange attention ［J］. arXiv preprint arXiv:221112905, 2022.
［20］　Ding X, Zhang X, Ma N, et al. Repvgg: Making vggstyle convnets great again ［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 13733-13742.

[1]	高芳征, 温鑫, 黄家才, 陈光明, 金少宇, 赵雪迪. 基于AD-YOLOX-Nano的茶叶嫩芽识别算法[J]. 中国农机化学报, 2025, 46(1): 178-184.
[2]	王鑫淼, 张正, 董晓威, 王林烽, 李瑞祥. 基于改进YOLOv8算法的谷子田杂草检测[J]. 中国农机化学报, 2025, 46(1): 185-189.
[3]	李春雨, 郭肖琴, 杨晶晶, 李忠华. 基于深度学习的水果图像识别[J]. 中国农机化学报, 2025, 46(1): 198-203.
[4]	牛潘婷, 张宝林, 潘丽杰, 郭建鹏(. 基于改进GoogLeNet的玉米叶片病害识别及其可解释性研究[J]. 中国农机化学报, 2025, 46(1): 204-212.
[5]	彭勇, 乔印虎, 张春燕, 姚杰, 包殿令. 改进YOLOv5模型的草莓检测方法研究[J]. 中国农机化学报, 2025, 46(1): 213-219.
[6]	卢明, 余心杰, 郭俊先. 基于改进YOLOv8算法的水稻田间人工施肥行为识别[J]. 中国农机化学报, 2025, 46(1): 220-226.
[7]	韩鹏飞, 宋其江, 贾梦实. 基于改进轻量化 EfficientNet-V2模型的小麦种子分类[J]. 中国农机化学报, 2024, 45(9): 111-117.
[8]	李志臣, 凌秀军, 李鸿秋. 基于声音深度学习的发动机失火故障诊断[J]. 中国农机化学报, 2024, 45(9): 134-140.
[9]	熊明明 , 李晓娟 , . 基于图像与深度信息融合的西梅果实识别定位方法[J]. 中国农机化学报, 2024, 45(9): 172-177.
[10]	桑一男 , 徐增莱 , 汪琼 , 葛海涛 , 王殿广 . 一种轮式采花机器人设计——以黄蜀葵为例[J]. 中国农机化学报, 2024, 45(9): 202-208.
[11]	张传栋, 亓璐, 丁华立. 基于改进 YOLOv8n模型的多品种葡萄簇检测方法[J]. 中国农机化学报, 2024, 45(9): 220-226.
[12]	李邦国, 王辉, 宋杨, 任志伟, 刘跃华, 徐乐程. 基于无人驾驶小麦收割机立体视觉感知系统[J]. 中国农机化学报, 2024, 45(9): 244-249.
[13]	宋立航, 张屹, 时寅豪. 基于改进 YOLOv5s的自然环境下油桃成熟度检测方法[J]. 中国农机化学报, 2024, 45(9): 250-257.
[14]	宋小鹿 , 冯娟 , 梁翔宇 , 周玺兴 . 基于 YOLOv4的水下海参检测与计数算法[J]. 中国农机化学报, 2024, 45(9): 258-264.
[15]	杨巧梅, 崔婷婷, 袁永榜, 罗桦 . 轻量化 YOLO模型在农作物微小病虫害检测中的应用研究[J]. 中国农机化学报, 2024, 45(9): 265-270.