Citrus Detection Method Based on Improved YOLOv5 Lightweight Network

doi:10.3778/j.issn.1002-8331.2212-0023

Abstract

Abstract: Aiming at the problems of the existing citrus detection algorithms, such as low accuracy, large amount of model parameters, poor real-time detection, and unsuitability for mobile picking equipment, a citrus detection method based on the improved lightweight model YOLO-DoC is proposed. This paper introduces the ShuffleNetV2 network of the Bottleneck structure as the YOLOv5 backbone network model to construct a lightweight network. At the same time, the non-parametric SimAM attention mechanism is added to improve the recognition accuracy of targets in complex environments. In order to improve the positioning accuracy of the bounding box of the target fruit by the detection network, the bounding box of the target is obtained by introducing the method of Alpha-IoU bounding box regression loss function. Experiments show that the P（precision） value and mAP（mean average precision） value of the YOLO-DoC model are 98.8% and 99.1%, respectively, and the number of parameters is reduced to 1/7 that of the YOLOv5 network, and the size of the model is 2.8?MB. Compared with the original network model, the improved model has the advantages of fast recognition speed, high positioning accuracy and less memory usage. It can improve the picking efficiency under the premise of meeting the requirements of precise picking work.

Key words: neural network, attention mechanism, YOLOv5, citrus detection, loss function, ShuffleNetV2, Alpha-IoU

摘要： 针对现有的柑橘检测算法准确率低、模型参数量大、检测实时性差、不适用移动采摘设备等问题，提出一种基于改进轻量模型YOLO-DoC的柑橘检测方法。引入Bottleneck结构的ShuffleNetV2网络作为YOLOv5骨干网络模型，构造轻量化网络。同时加入无参型SimAM注意力机制提高复杂环境下对目标的识别精度。为了提高检测网络对于目标果实的边界框定位精度，通过引入Alpha-IoU边界框回归损失函数的方法来获取目标的边界框。实验显示，YOLO-DoC模型的P（precision）值和mAP（mean average precision）值分别为98.8%和99.1%，参数量缩减为YOLOv5网络的1/7，模型的大小为2.8?MB。改进后的模型相比于原网络模型具有识别速度快、定位准度高以及占用内存少的优势，在满足精准采摘工作要求的前提下可以提高采摘效率。

关键词: 神经网络, 注意力机制, YOLOv5, 柑橘检测, 损失函数, ShuffleNetV2, Alpha-IoU

GAO Xinyang, WEI Sheng, WEN Zhiqing, YU Tianbiao. Citrus Detection Method Based on Improved YOLOv5 Lightweight Network[J]. Computer Engineering and Applications, 2023, 59(11): 212-221.

高新阳, 魏晟, 温志庆, 于天彪. 改进YOLOv5轻量级网络的柑橘检测方法[J]. 计算机工程与应用, 2023, 59(11): 212-221.

References

[1] 柴光荣，王晨洋，等.丘陵山地果园运输机械的发展现状与展望[J].农业技术与装备，2019（3）：30-31.
CHAI Guangrong，WANG Chenyang，et al.Development status and prospects of orchard transportation machinery in hilly and mountainous areas[J].Agricultural Technology and Equipment，2019（3）：30-31.
[2] 叶敏，邹湘军，罗陆锋，等.荔枝采摘机器人双目视觉的动态定位误差分析[J]. 农业工程学报，2016，32（5）：50-56.
YE Min，ZOU Xiangjun，LUO Lufeng，et al.Error analysis of dynamic localization tests based on binocular stereo vision on litchi harvesting manipulator[J].Transactions of the Chinese Society of Agricultural Engineering，2016，32（5）：50-56.
[3] 杨长辉，刘艳平，王毅，等.自然环境下柑橘采摘机器人识别定位系统研究[J].农业机械学报，2019，50（12）：14-22.
YANG Changhui，LIU Yanping，WANG Yi，et al.Research and experiment on recognition and location system for citrus picking robot in natural environment[J].Transactions of the Chinese Society for Agricultural Machinery，2019，50（12）：14-22.
[4] XIONG J，LIN R，LIU Z，et al.The recognition of litchi clusters and the calculation of picking point in a nocturnal natural environment[J].Biosystems Engineering，2018，166：44-57.
[5] ZHUANG J J，LUO S M，HOU C J，et al.Detection of orchard citrus fruits using a monocular machine vision-based method for automatic fruit picking applications[J].Computers and Electronics in Agriculture，2018，152：64-73.
[6] 冯娟，刘刚，司永胜，等.苹果采摘机器人激光视觉系统的构建[J].农业工程学报，2013，29（25）：32-37.
FENG Juan，LIU Gang，SI Yongsheng，et al.Construction of laser vision system for apple harvesting robot[J].Transactions of the Chinese Society of Agricultural Engineering，2013，29（25）：32-37.
[7] BAC C W，HEMMING J，VAN HENTEN E J.Stem locali-zation of sweet-pepper plants using the support wire as a visual cue[J].Computers and Electronics in Agriculture，2014，105：111-120.
[8] HUANG Z，WANE S，PARSONS S.Towards automated strawberry harvesting：identifying the picking point[C]//Annual Conference Towards Autonomous Robotic Systems，2017.
[9] SENGUPTA S，LEE W S.Identification and determination of the number of immature green citrus fruit in a canopy under different ambient light conditions[J].Biosystems Engineering，2014，117（1）：51-61.
[10] HE Z L，XIONG J T，LIN R，et al.A method of green litchi recognition in natural environment based on improved LDA classifier[J].Computers & Electronics in Agriculture，2017，140：159-167.
[11] 黄彤镔，黄河清，李震，等.基于YOLOv5改进模型的柑橘果实识别方法[J].华中农业大学学报，2022，41（4）：170-177.
HUANG Tongbin，HUANG Heqing，LI Zhen，et al.Citrus fruit recognition method based on improved model of YOLOv5[J].Journal of Huazhong Agricultural University，2022，41（4）：170-177.
[12] WOO S，PARK J，LEE J Y，et al.CBAM：convolutional block attention module[C]//Proceedings of the 2018 European Conference on Computer Vision：Lecture Notes in Computer Science.Cham：Springer，2018：3-19.
[13] 吕石磊，卢思华，李震，等.基于改进YOLOv3-LITE轻量级神经网络的柑橘识别方法[J].农业工程学报，2019，35（17）：205-214.
LV Shilei，LU Sihua，LI Zhen，et al.Orange recognition method using improved YOLOv3-LITE lightweight neural network[J].Transactions of the Chinese Society of Agricultural Engineering，2019，35（17）：205-214.
[14] SANDLER M，HOWARD A，ZHU M，et al.MobileNetv2：inverted residuals and linear bottlenecks[C]//IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City：IEEE，2018：4510-4520.
[15] 冯硕，李旗.奇异果采摘机器人机械臂控制系统研究——基于计算机视觉和卷积神经网络[J].农机化研究，2022，44（10）：25-29.
FENG Shuo，LI Qi.Research on the control system of the manipulator of kiwi fruit picking robot-based on computer vision and convolutional neural network[J].Journal of Agricultural Mechanization Research，2022，44（10）：25-29.
[16] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[J].arXiv：1512.03385，2015.
[17] 陈锋军，张新伟，朱学岩，等.基于改进EfficientDet的油橄榄果实成熟度检测[J].农业工程学报，2022，38（13）：158-166.
CHEN Fengjun，ZHANG Xinwei，ZHU Xueyan，et al.Detection of the olive fruit maturity based on improved EfficientDet[J].Transactions of the Chinese Society of Agricultural Engineering，2022，38（13）：158-166.
[18] TAN M，PANG R，LE Q V.EfficientDet：scalable and efficient object detection[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition，2020.
[19] 张皓婷，李明，李敏，等.基于Faster R-CNN的番茄果实检测算法应用[J].农业与技术，2022，42（15）：12-16.
ZHANG Haoting，LI Ming，LI Min，et al.Application of tomato fruit detection algorithm based on Faster R-CNN[J].Agriculture and Technology，2022，42（15）：12-16.
[20] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems，2015：91-99.
[21] MA N，ZHANG X，ZHAGN H T，et al.ShuffleNet V2：practical guidelines for efficient CNN architecture design[C]//European Conference on Computer Vision（ECCV）.Cham：Springer，2018.
[22] YANG Lingxiao，ZHANG Ruyang，LI Lida，et al.SimAM：a simple，parameter-free attention module for convolutional neural networks[C]//Proceedings of the 38th International Conference on Machine Learning，2021.
[23] HE J B，ERFANI S，MA X J，et al.Alpha-IoU：a family of power intersection over union losses for bounding box regression[J].arXiv：2110.13675，2021.
[24] 杨永波，李栋.改进YOLOv5的轻量级安全帽佩戴检测算法[J].计算机工程与应用，2022，58（9）：201-207.
YANG Yongbo，LI Dong.Lightweight helmet wearing detection algorithm of improved YOLOv5[J].Computer Engineering and Applications，2022，58（9）：201-207.
[25] LIU C，ZHU H J，GUO W，et al.EFDet：an efficient detection method for cucumber disease under natural complex environments[J].Computers and Electronics in Agriculture，2021，189：1063978.