R-YOLOv5: a lightweight rotation detector for remote sensing
Authors:
- 2 December 2022
- conference paper
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12288, 90-498
Abstract
Recently, detection algorithms for objects with arbitrary orientation have been greatly developed, but traditional object detection algorithms use horizontal boxes to label objects in images, which will lead to the problems such as loss of accuracy and excessive background information. In this paper, a rotation detection algorithm based on YOLOv5 is proposed, which can effectively detects the targets in the remote sensing image. It uses the CSL method to mark the oblique targets, converts the angle of the rotation boxes into a classification problem, and avoids the boundary problem. We also optimize the loss function to speed up the network convergence and adopt the NMS algorithm based on the rotation boxes, which effectively removes the redundant prediction frame. The experimental results demostrate that compared with the original YOLOv5 algorithm, the improved YOLOv5 algorithm can better locate rotation objects in remote sensing images and effectively prevent occlusion problems in dense target scenes. With a guaranteed inference speed of 24.1fps, Our method has a detection accuracy of 72.65% on dataset DOTA 1.0.Keywords
This publication has 6 references indexed in Scilit:
- IEEE Transactions on Geoscience and Remote Sensing2023
- IEEE Transactions on Pattern Analysis and Machine Intelligence2023
- Arbitrary-Oriented Object Detection in Remote Sensing Images Based on Polar CoordinatesIEEE Access, 2020
- Feature-Attentioned Object Detection in Remote Sensing Imagery2019
- RRPN: Radar Region Proposal Network for Object Detection in Autonomous Vehicles2019
- Automatic Ship Detection in Remote Sensing Images from Google Earth of Complex Scenes Based on Multiscale Rotation Dense Feature Pyramid NetworksRemote Sensing, 2018