Multi-scenario pear tree inflorescence detection based on improved YOLOv7 object detection algorithm

被引:0
|
作者
Zhang, Zhen [1 ,2 ,3 ]
Lei, Xiaohui [2 ,3 ]
Huang, Kai [2 ,3 ]
Sun, Yuanhao [2 ,3 ]
Zeng, Jin [2 ,3 ]
Xyu, Tao [2 ,3 ]
Yuan, Quanchun [2 ,3 ]
Qi, Yannan [2 ,3 ]
Herbst, Andreas [4 ]
Lyu, Xiaolan [2 ,3 ]
机构
[1] Jiangsu Univ, Sch Agr Engn, Zhenjiang, Peoples R China
[2] Jiangsu Acad Agr Sci, Inst Agr Facil & Equipment, Nanjing, Peoples R China
[3] Minist Agr & Rural Affairs, Key Lab Modern Hort Equipment, Nanjing, Peoples R China
[4] JKI, Inst Chem Applicat Technol, Braunschweig, Germany
来源
基金
中国国家自然科学基金;
关键词
pear tree inflorescence; long-distance detection; YOLOv7; EMA; SPPCSPCS; Soft-NMS;
D O I
10.3389/fpls.2023.1330141
中图分类号
Q94 [植物学];
学科分类号
071001 ;
摘要
Efficient and precise thinning during the orchard blossom period is a crucial factor in enhancing both fruit yield and quality. The accurate recognition of inflorescence is the cornerstone of intelligent blossom equipment. To advance the process of intelligent blossom thinning, this paper addresses the issue of suboptimal performance of current inflorescence recognition algorithms in detecting dense inflorescence at a long distance. It introduces an inflorescence recognition algorithm, YOLOv7-E, based on the YOLOv7 neural network model. YOLOv7 incorporates an efficient multi-scale attention mechanism (EMA) to enable cross-channel feature interaction through parallel processing strategies, thereby maximizing the retention of pixel-level features and positional information on the feature maps. Additionally, the SPPCSPC module is optimized to preserve target area features as much as possible under different receptive fields, and the Soft-NMS algorithm is employed to reduce the likelihood of missing detections in overlapping regions. The model is trained on a diverse dataset collected from real-world field settings. Upon validation, the improved YOLOv7-E object detection algorithm achieves an average precision and recall of 91.4% and 89.8%, respectively, in inflorescence detection under various time periods, distances, and weather conditions. The detection time for a single image is 80.9 ms, and the model size is 37.6 Mb. In comparison to the original YOLOv7 algorithm, it boasts a 4.9% increase in detection accuracy and a 5.3% improvement in recall rate, with a mere 1.8% increase in model parameters. The YOLOv7-E object detection algorithm presented in this study enables precise inflorescence detection and localization across an entire tree at varying distances, offering robust technical support for differentiated and precise blossom thinning operations by thinning machinery in the future.
引用
下载
收藏
页数:15
相关论文
共 50 条
  • [1] Improved Underwater Object Detection Algorithm of YOLOv7
    Liang, Xiuman
    Li, Ran
    Yu, Haifeng
    Liu, Zhendong
    Computer Engineering and Applications, 2024, 60 (06) : 89 - 99
  • [2] Improved YOLOv7 Object Detection Algorithm for Fisheye Images
    Wu, Zhaodong
    Xu, Cheng
    Liu, Hongzhe
    Fu, Ying
    Jian, Muwei
    Computer Engineering and Applications, 2024, 60 (14) : 250 - 256
  • [3] Improved YOLOv7 Automatic Driving Object Detection Algorithm
    Hu, Miao
    Jiang, Lin
    Tao, Youfeng
    Zhang, Zhijian
    Computer Engineering and Applications, 60 (11): : 165 - 172
  • [4] A Small Object Detection Algorithm for Traffic Signs Based on Improved YOLOv7
    Li, Songjiang
    Wang, Shilong
    Wang, Peng
    SENSORS, 2023, 23 (16)
  • [5] Helmet Detection Algorithm Based on Improved YOLOv7
    Yajie Yaermaimaiti Yilihamu
    Lingfei Liu
    Ruohao Xi
    undefined Wang
    Automatic Control and Computer Sciences, 2024, 58 (6) : 642 - 655
  • [6] A Flame Detection Algorithm Based on Improved YOLOv7
    Yan, Guibao
    Guo, Jialin
    Zhu, Dongyi
    Zhang, Shuming
    Xing, Rui
    Xiao, Zhangshu
    Wang, Qichao
    APPLIED SCIENCES-BASEL, 2023, 13 (16):
  • [7] Improved Complex Road Scene Object Detection Algorithm of YOLOv7
    Du, Juan
    Cui, Shaohua
    Jin, Meijuan
    Ru, Chen
    Computer Engineering and Applications, 2024, 60 (01) : 96 - 103
  • [8] SCNet-YOLO: a symmetric convolution network for multi-scenario ship detection based on YOLOv7
    Weina Zhou
    Yuqi Yang
    Ming Zhao
    Wenhua Hu
    The Journal of Supercomputing, 81 (4)
  • [9] Improved YOLOv7 for Small Object Detection Algorithm Based on Attention and Dynamic Convolution
    Li, Kai
    Wang, Yanni
    Hu, Zhongmian
    APPLIED SCIENCES-BASEL, 2023, 13 (16):
  • [10] Night target detection algorithm based on improved YOLOv7
    Bowen, Zheng
    Huacai, Lu
    Shengbo, Zhu
    Xinqiang, Chen
    Hongwei, Xing
    SCIENTIFIC REPORTS, 2024, 14 (01):