Recognition and Localization Method for Pepper Clusters in Complex Environments Based on Improved YOLO v5

HUANG Hua, ZHANG Hao, HU Xiaolin, NIE Xingyi

Abstract

Pepper trees yield is a substantial quantity of fruits, characterized by crisscrossed branches and dense foliage, resulting insignificant challenges for automated peppercorn picking. Therefore, a fast identification and localization method of pepper clusters in complex environment based on improved YOLO v5 was proposed. By adding efficient channel attention (ECA) after the CSPLayer of the backbone extraction network CSPDarknet and the upsampling layer of Neck to simplify the computation of the CSPLayer layer and improve the feature extraction capability. In the downsampling layer, coordinate attention (CA) was added to reduce the loss of information in the downsampling process, strengthen the spatial information of features, and cooperate with the heat map (Grad-CAM) and the depth map of the point cloud to complete the spatial localization of pepper clusters. The test results showed that the improved network over the original YOLO v5 reduced the residual computation to 1 time, which ensured the model was lightweight and the efficiency was improved. Under the same frame number interval, the accuracy of the improved network was 96.27%, comparing with three similar feature extraction networks YOLO v5, YOLO v5-tiny, and Faster R-CNN, the precision of the improved network was improved by 5.37 percentage points, 3.35 percentage points, and 15.37 percentage points, respectively, and the ability of separating and recognizing the pepper clusters of the successive plants was greatly improved. The experimental results showed that the average checking accuracy of the system in the natural environment was 81.60%, and the leakage rate was 18.39%, which can satisfy the pepper cluster recognition, and build the foundation for mobile deployment.

 

Keywords: pepper cluster identification; agricultural robots; deep learning; target detection; YOLO v5

 

Download Full Text:

PDF


References


WANG Dandan, SONG Huaibo, HE Dongjian. Research advance on vision system of apple picking robotfjj. Transactions of theCSAE, 2017, 33( 10) : 59 -69. ( in Chinese)

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, 2018, 117(1) : 51 —61.

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(3) : 159 - 167.

MAURYA P, SINGH N P. Mushroom classification using feature-based machine learning approach [ G ] // Proceedings of 3rd International Conference on Computer Vision and Image Processing,2020: 197 -206.

WANG Y, DU J, ZHANG II, et al. Mushroom toxicity recognition based on multi-grained cascade forest [ J ]. Scientific Programming, 2020, 8(3) : 8849011.

XIONG Juntao, LIU Zhen, TANG Linyue, et al. Visual detection technology of green citrus under natural environment [ J].Transactions of the Chinese Society for Agricultural Machinery, 2018, 49(4) : 45 -52. (in Chinese)

FU L, FENG Y, WU J, et al. Fast and acc urate detection of kiwifruit in orchard using improved YOLOv3-tiny model [ J]. Precision Agriculture, 2021 , 22(3) ;754 -776.

W ANG 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. (in Chinese)

LIU Chengliang, GONG Liang, YUAN Jin, et al. Current status and development trends of agricultural robots [J]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(7) ; 1 -22,55. (in Chinese)

GAO Xinyang, WEI Sheng, W EN Zhiqing, et al. Citrus detection method based on improved YOLO v5 lightweight network [J ]. Computer Engineering and Applications, 2023 , 59(11): 212 -221. (in Chinese)

ZHU X, LYU S, WANG X, et al. ТРИ — Y0L0v5; improved YOLO v5 based on transformer prediction head for object detection on crone-captured scenarios [С ] // Proceedings of the IEEE/CVF International Conferenc e on Computer Vision. IEEE, 2021 : 2778 -2788.

YANG Ping,GUO Zhicheng. Vision recognition and location solution of Zanthoxylum bungeanum picking robot [ J] . Journal of Hebei Agricultural University, 2020, 43(3) : 121 - 129. (in Chinese)

YU Xiaodong, YANG Mengji, ZHANG Haiqing, et al. Research and application of crop diseases detection method based on transfer learning [J ].Transactions of the Chinese Society for Agricultural Machinery,2020,51 ( 10) *.252 -258. (in Chinese)

WANG Qilong, WU Banggu, ZHU Pengfei,et al. ECA — Net: efficient channel attention for deep convolutional neural networks [ C] //EEE 2020 IEEE/CVF Conferenceon Computer Vision and Pattern, 2020: 1 1531 - 1 1539.

ZHAI Zhaoyu, CAO Yifei, XU Huanliang, et al. Review of key techniques for crop disease and pest detection [ J ]. Transactions of the Chinese Society for Agricultural Machinery, 2021 , 52(7) : 1 - 18. (in Chinese)

ZHAO Di, YE Shengbo, ZHOU Bin. Ground penetrating radar anomaly detection based on convolution Grad — CAM [ J ]. Electronic Measurement Technology, 2020, 43( 10) ; 1 13 - 1 18. (in Chinese)

XU Jinghui,SHAO Mingye, WANG Yichen, et al. Recognition of corn leaf spot and rust based on transfer learning with convolutional neural network [J ]. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51 (2) : 230 - 236, 253. (in Chinese)

LONG Mansheng, OUYANG Chunjuan, LIU Huan, et al. Image recognition of Camellia oleifera diseases based on convolutional neural network & transfer learning [J] . Transactions of the CSAE, 2018. 34( 18) : 194 -201. (in Chinese)

WANG H, ZHU Y, GREEN B,et al. Axial-deep lab: stand-alone axial-attention for panoptic segmentation [С ] // European Conference on Computer Vision, 2020: 108 - 126.


Refbacks

  • There are currently no refbacks.