Lightweight method for maturity
detection of Hemerocallis citrina Baroni based on improved
YOLOv5

Abstract

Abstract: To address the low efficiency and high subjectivity of manual harvesting of Hemerocallis citrina Baroni, a deep learning-based SSH-YOLOv5 Hemerocallis citrina Baroni maturity detection algorithm was proposed，in this method, the lightweight network ShuffleNet V2 was combined with original YOLOv5 backbone to compress model size and improve the detection speed. Squeeze-and-Excitation network was integrated into the model to improve target detection precision, and ordinary convolution was replaced with depth-separable convolution module to further reduce the model computation. The experimental results showed that the number of parameters and floating point operations of the improved SSH-YOLOv5 model were reduced by 61.6% and 68.3% respectively, and the number of network layers was reduced by 18%, while the detection presicion of SSH-YOLOv5 was improved from 88.8% to 91.2% of the original algorithm. The real-time detection speed reached 66.4FPS, which is 18.1% higher than the original YOLOv5 algorithm and meets the real-time detection requirements. According to the results showed that the proposed algorithm is more accurate and faster, which can better meet the demand of Hemerocallis citrina Baroni detection.

Key words: deep learning, YOLOv5 algorithm, lightweight, attention mechanism, Hemerocallis citrina Baroni

摘要： 黄花菜具有较短的采摘周期和相对严格的采摘要求，针对传统人工采摘效率低、主观性高的问题，提出一种基于深度学习的SSH-YOLOv5黄花成熟度检测算法。以YOLOv5模型为基础，结合轻量级网络ShuffleNet V2基本残差单元压缩网络模型大小，提升模型目标检测速度；引入SE Net通道注意力机制模块，增强模型对有用特征信息的敏感度，提高目标检测精度；将普通卷积替换为深度可分离卷积模块，进一步减少模型计算量。试验结果表明，改进后的SSH-YOLOv5模型参数量和浮点运算量分别减少61.6%和68.3%，网络层数减少18%，同时SSH-YOLOv5的检测精度由原算法的88.8%提高到91.2%，实时检测速度达到66.4FPS，相比原算法提高18.1%，达到实时检测要求。改进后的算法不仅实现模型的轻量化，同时也使黄花成熟度检测更加准确和快速，可以较好地满足黄花检测需求。

关键词: 深度学习, YOLOv5算法, 轻量化, 注意力机制, 黄花

CLC Number:

TP399

Wu Ligang, Lv Yuanyuan, Zhou Qian, Chen Le, Zhang Liang, Shi Jianhua.

Lightweight method for maturity detection of Hemerocallis citrina Baroni based on improved YOLOv5 [J]. Journal of Chinese Agricultural Mechanization.

吴利刚, 吕媛媛, 周倩, 陈乐, 张梁, 史建华. 基于改进YOLOv5的轻量级黄花成熟检测方法[J]. 中国农机化学报.

References

[1] 马聪, 陈学东. 黄花菜采摘机器人视觉系统研究[J]. 宁夏农林科技, 2021, 62(12): 60-64.

Ma Cong, Chen Xuedong. Vision system of daylily picking robot [J]. Ningxia Journal of Agriculture and Forestry Science and Technology, 2021, 62(12): 60-64.

[2] 郑太雄, 江明哲, 冯明驰. 基于视觉的采摘机器人目标识别与定位方法研究综述[J]. 仪器仪表学报, 2021, 42(9): 28-51.

Zheng Taixiong, Jiang Mingzhe, Feng Mingchi. Vision based target recognition and location for picking robot: a review [J]. Chinese Journal of Scientific Instrument, 2021, 42(9): 28-51.

[3] 岑海燕, 朱月明, 孙大伟, 等. 深度学习在植物表型研究中的应用现状与展望[J]. 农业工程学报, 2020, 36(9): 1-16.

Cen Haiyan, Zhu Yueming, Sun Dawei, et al. Current status and future perspective of the application of deep learning in plant phenotype research [J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(9): 1-16.

[4] 赵立新, 邢润哲, 白银光, 等. 深度学习在目标检测的研究综述[J]. 科学技术与工程, 2021, 21(30): 12787-12795.

Zhao Lixin, Xing Runzhe, Bai Yinguang, et al. Review on survey of deep learning in target detection [J]. Science Technology and Engineering, 2021, 21(30): 12787-12795.

[5] Girshick R, Donahue J, Darrell T, et al. Region based convolutional networks for accurate object detection and segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(1): 142-158.

[6] 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 and Machine Intelligence, 2015, 39(6):1137-1149.

[7] Liu W, Anguelov D, Erhan D, et al. SSD: Single shot multi box detector [C]. European Conference on Computer Vision, 2016: 21-37.

[8] Redmon J, Divvala S, Girshick R, et al. You only look once: unified, real-time object detection[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016: 779-788.

[9] Redmon J, Farhadi A. YOLO9000: Better, faster, stronger[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017: 7263-7271.

[10] Redmon J, Farhadi A. YOLOv3: An incremental improvement [C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

[11] 董文轩, 梁宏涛, 刘国柱, 等. 深度卷积应用于目标检测算法综述[J]. 计算机科学与探索, 2022, 16(5): 1025-1042.

Dong Wenxuan, Liang Hongtao, Liu Guozhu, et al. Review of deep convolution applied to target detection algorithms [J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(5):1025-1042.

[12] 朱红春, 李旭, 孟炀, 等. 基于Faster R-CNN网络的茶叶嫩芽检测[J]. 农业机械学报, 2022, 53(5): 217-224.

Zhu Hongchun, Li Xu, Meng Yang, et al. Tea bud detection based on Faster R-CNN network [J]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(5): 217-224.

[13] 岳有军, 孙碧玉, 王红君, 等. 基于级联卷积神经网络的番茄果实目标检测[J]. 科学技术与工程, 2021, 21(6): 2387-2391.

Yue Youjun, Sun Biyu, Wang Hongjun, et al. Object detection of tomato fruit based on cascade RCNN [J]. Science Technology and Engineering, 2021, 21(6): 2387-2391.

[14] 汤旸, 杨光友, 王焱清. 面向采摘机器人的改进YOLOv3-tiny轻量化柑橘识别方法[J]. 科学技术与工程, 2022, 22(31): 13824-13832.

Tang Yang, Yang Guangyou, Wang Yanqing. Improved YOLOv3-tiny lightweight citrus recognition method for picking robot [J]. Science Technology and Engineering, 2022, 22(31): 13824-13832.

[15] 王卓, 王健, 王枭雄, 等. 基于改进YOLO v4的自然环境苹果轻量级检测方法[J]. 农业机械学报, 2022, 53(8): 294-302.

Wang Zhuo, Wang Jian, Wang Xiaoxiong, et al. Lightweight real-time apple detection method based on improved YOLO v4 [J]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(8): 294-302.

[16] Zhang L, Wu L, Liu Y. Hemerocallis citrina Baroni maturity detection method integrating lightweight neural network and dual Attention mechanism[J]. Electronics, 2022, 11(17): 2743.

[17] 邓颖, 吴华瑞, 朱华吉. 基于实例分割的柑橘花朵识别及花量统计[J]. 农业工程学报, 2020, 36(7): 200-207.

Deng Ying, Wu Huarui, Zhu Huaji. Recognition and counting of citrus flowers based on instance segmentation [J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(7): 200-207.

[18] 宋爽, 张悦, 张琳娜, 等. 基于深度学习的轻量化目标检测算法[J]. 系统工程与电子技术, 2022, 44(9): 2716-2725.

Song Shuang, Zhang Yue, Zhang Linna, et al. Lightweight target detection algorithm based on deep learning [J]. Systems Engineering and Electronics, 2022, 44(9): 2716-2725.

[19] 李东升, 胡文泽, 兰玉彬, 等. 深度学习在杂草识别领域的研究现状与展望[J]. 中国农机化学报, 2022, 43(9): 137-144.

Li Dongsheng, Hu Wenze, Lan Yubin, et al. Research status and prospect of deep learning in weed recognition [J], Journal of Chinese Agricultural Mechanization, 2022, 44(9): 137-144

[20] Ma N, Zhang X, Zheng H, et al. Shuffle Net v2: practical guidelines for efficient CNN architecture design[C]. European Conference on Computer Vision, 2018: 116-131.

[21] Zhang X, Zhou X, Lin M, et al. Shuffle Net: An extremely efficient convolutional neural network for mobile devices [C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR).2018: 6848-6856.

[22] Andrew G Howard， Zhu M, Chen B, et al. Mobilenets: efficient convolutional neural networks for mobile vision applications [J]. Computer Vision and Pattern Recognition: 2017.

[23] Sandler M, Howard A, Zhu M, et al. Mobilenetv2: Inverted residuals and linear bottlenecks [C]. IEEE Conference on Computer Vision and Pattern Recognition, 2018: 4510-4520.

[24] Hu J, Shen L, Sun G, et al. Squeeze-and-excitation networks [J]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, 7132-7141.

Lightweight method for maturity detection of Hemerocallis citrina Baroni based on improved YOLOv5

基于改进YOLOv5的轻量级黄花成熟检测方法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Wu Xiao, Yang Ying, Liu Gang, Zhang Qian, Ning Yuanlin. Pig individual recognition method based on transfer learning and improved ResNet34 for real environment [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(9): 214-221.
[2]	Sun Songli, Wen Hongyuan, Liu Binling, Zhong Jinyang, Mao Zhengxing. Design of intelligent sorting system of Pleurotus eryngii based on ROS and deep learning [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(8): 95-102.
[3]	Xiang Hao, Gao Qiaoming, , , Wei Zengjian, Xu Peng, Zeng Junhao, Zhao Pengfei. Design of an ipsilateral output planetary reducer for a mountain modular electric chassis [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(8): 133-140.
[4]	Yu Sheng, Xie Li. Research on plant disease identification based on transfer learning and convolutional vision transformer [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(8): 191-197.
[5]	Li Zongnan, Jiang Yi, Wang Si, Li Yuanhong, Huang Ping, Wei Peng. Object detection of invasive Erigeron L. plants base on YOLOv5 [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(7): 200-206.
[6]	Wang Chuntao, , , , Liang Weijian, Guo Qingwen, Zhong Hao, Gan Yu, Xiao Deqin, , . Review on computervisionbased detection of agricultural pests [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(7): 207-213.
[7]	Chen Weimei, Liu Xinwei, Wang Tiewei, Xu Wenkai, Li Juan. Recognition of pine wilt disease based on twolevel fusion deep learning [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(7): 214-219.
[8]	Li Ming, , Ding Zhihuan, , Zhao Jingxuan, Chen Siming, Li Wenyong, Yang Xinting. Detection method for cucumber downy mildew #br# #br# sporangia in a solar greenhouse based on improved YOLOv5s#br# [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(5): 63-70.
[9]	Yang Chenglei, , Lan Yubin, , Wang Qingyu, , Bie Xiaoting, , Shan Changfeng, , Wang Guobin, . Application of neural network in greenhouse microclimate prediction [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(5): 89-99.
[10]	Fu Hao, , Zhao Xueguan, Zhai Changyuan, , Zheng Kang, Zheng Shenyu, Wang Xiu. Research progress on weed recognition method based on deep learning technology [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(5): 198-207.
[11]	Duan Yufei, , Dong Geng, Sun Jiwei, Wang Yanqing, . Sorting model of camellia fruit shells and tea seeds based on SE-ResNet network [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(4): 89-95.
[12]	Li Yuhang, Zhuang Jihui, Chen Zhenbin. Datadriven NOX emission prediction model for diesel engines in agricultural vehicles [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(4): 128-136.
[13]	Chen Peng, , Ma Zihan, Zhang Jun, Xia Yi, Wang Bing, Liang Dong. Semantic segmentation network based on attention mechanism for wheat FHB [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(4): 145-152.
[14]	Li Guangming, Gong Haobin, Yuan Kai. Research on lightweight pepper cluster detection based on YOLOv5s [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(4): 153-158.
[15]	Wang Yubo, , Ma Tinghuai, Chen Guangming. Weeds detection in farmland based on a modified YOLOv5 algorithm [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(4): 167-173.