Paper
21 June 2024 An improved YOLOv5s target detection algorithm
Longlong Tian, Yanzhi Guan, Jinchuan Peng, Xiang Chen
Author Affiliations +
Proceedings Volume 13167, International Conference on Remote Sensing, Mapping, and Image Processing (RSMIP 2024); 1316733 (2024) https://doi.org/10.1117/12.3029827
Event: International Conference on Remote Sensing, Mapping and Image Processing (RSMIP 2024), 2024, Xiamen, China
Abstract
The existing YOLOv5s object detection model has issues of missing small targets and lower detection accuracy in complex scenes. Therefore, YOLOv5s needs to be optimized based on these problems. Firstly, the coordinate attention mechanism and the structure based on receptive field Block are introduced to improve the accuracy of the model. Secondly, the coordinate attention mechanism and the omni-dimensional dynamic convolutional structure are introduced to improve the situation of missing small targets. Selected part of the data in PASCAL VOC2007 for experiments, and the final results show that the model in this paper improves the recall by 1.7%, the average precision mAP50 by 2%, and the average precision mAP50-95 by 3% compared to the yolov5s model. The model in this paper improves the detection accuracy to a certain extent and improves the leakage detection of important targets and is tested in industrial scenarios with good results.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Longlong Tian, Yanzhi Guan, Jinchuan Peng, and Xiang Chen "An improved YOLOv5s target detection algorithm", Proc. SPIE 13167, International Conference on Remote Sensing, Mapping, and Image Processing (RSMIP 2024), 1316733 (21 June 2024); https://doi.org/10.1117/12.3029827
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Target detection

Small targets

Detection and tracking algorithms

Object detection

Feature extraction

Performance modeling

Education and training

RELATED CONTENT


Back to Top