Cargando…
R-YOLO: A YOLO-Based Method for Arbitrary-Oriented Target Detection in High-Resolution Remote Sensing Images
In view of the existence of remote sensing images with large variations in spatial resolution, small and dense objects, and the inability to determine the direction of motion, all these components make object detection from remote sensing images very challenging. In this paper, we propose a single-s...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9371002/ https://www.ncbi.nlm.nih.gov/pubmed/35957272 http://dx.doi.org/10.3390/s22155716 |
_version_ | 1784766996644102144 |
---|---|
author | Hou, Yongjie Shi, Gang Zhao, Yingxiang Wang, Fan Jiang, Xian Zhuang, Rujun Mei, Yunfei Ma, Xinjiang |
author_facet | Hou, Yongjie Shi, Gang Zhao, Yingxiang Wang, Fan Jiang, Xian Zhuang, Rujun Mei, Yunfei Ma, Xinjiang |
author_sort | Hou, Yongjie |
collection | PubMed |
description | In view of the existence of remote sensing images with large variations in spatial resolution, small and dense objects, and the inability to determine the direction of motion, all these components make object detection from remote sensing images very challenging. In this paper, we propose a single-stage detection network based on YOLOv5. This method introduces the MS Transformer module at the end of the feature extraction network of the original network to enhance the feature extraction capability of the network model and integrates the Convolutional Block Attention Model (CBAM) to find the attention area in dense scenes. In addition, the YOLOv5 target detection network is improved by incorporating a rotation angle approach from the a priori frame design and the bounding box regression formulation to make it suitable for rotating frame-based detection scenarios. Finally, the weighted combination of the two difficult sample mining methods is used to improve the focal loss function, so as to improve the detection accuracy. The average accuracy of the test results of the improved algorithm on the DOTA data set is 77.01%, which is higher than the previous detection algorithm. Compared with the average detection accuracy of YOLOv5, the average detection accuracy is improved by 8.83%. The experimental results show that the algorithm has higher detection accuracy than other algorithms in remote sensing scenes. |
format | Online Article Text |
id | pubmed-9371002 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-93710022022-08-12 R-YOLO: A YOLO-Based Method for Arbitrary-Oriented Target Detection in High-Resolution Remote Sensing Images Hou, Yongjie Shi, Gang Zhao, Yingxiang Wang, Fan Jiang, Xian Zhuang, Rujun Mei, Yunfei Ma, Xinjiang Sensors (Basel) Article In view of the existence of remote sensing images with large variations in spatial resolution, small and dense objects, and the inability to determine the direction of motion, all these components make object detection from remote sensing images very challenging. In this paper, we propose a single-stage detection network based on YOLOv5. This method introduces the MS Transformer module at the end of the feature extraction network of the original network to enhance the feature extraction capability of the network model and integrates the Convolutional Block Attention Model (CBAM) to find the attention area in dense scenes. In addition, the YOLOv5 target detection network is improved by incorporating a rotation angle approach from the a priori frame design and the bounding box regression formulation to make it suitable for rotating frame-based detection scenarios. Finally, the weighted combination of the two difficult sample mining methods is used to improve the focal loss function, so as to improve the detection accuracy. The average accuracy of the test results of the improved algorithm on the DOTA data set is 77.01%, which is higher than the previous detection algorithm. Compared with the average detection accuracy of YOLOv5, the average detection accuracy is improved by 8.83%. The experimental results show that the algorithm has higher detection accuracy than other algorithms in remote sensing scenes. MDPI 2022-07-30 /pmc/articles/PMC9371002/ /pubmed/35957272 http://dx.doi.org/10.3390/s22155716 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Hou, Yongjie Shi, Gang Zhao, Yingxiang Wang, Fan Jiang, Xian Zhuang, Rujun Mei, Yunfei Ma, Xinjiang R-YOLO: A YOLO-Based Method for Arbitrary-Oriented Target Detection in High-Resolution Remote Sensing Images |
title | R-YOLO: A YOLO-Based Method for Arbitrary-Oriented Target Detection in High-Resolution Remote Sensing Images |
title_full | R-YOLO: A YOLO-Based Method for Arbitrary-Oriented Target Detection in High-Resolution Remote Sensing Images |
title_fullStr | R-YOLO: A YOLO-Based Method for Arbitrary-Oriented Target Detection in High-Resolution Remote Sensing Images |
title_full_unstemmed | R-YOLO: A YOLO-Based Method for Arbitrary-Oriented Target Detection in High-Resolution Remote Sensing Images |
title_short | R-YOLO: A YOLO-Based Method for Arbitrary-Oriented Target Detection in High-Resolution Remote Sensing Images |
title_sort | r-yolo: a yolo-based method for arbitrary-oriented target detection in high-resolution remote sensing images |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9371002/ https://www.ncbi.nlm.nih.gov/pubmed/35957272 http://dx.doi.org/10.3390/s22155716 |
work_keys_str_mv | AT houyongjie ryoloayolobasedmethodforarbitraryorientedtargetdetectioninhighresolutionremotesensingimages AT shigang ryoloayolobasedmethodforarbitraryorientedtargetdetectioninhighresolutionremotesensingimages AT zhaoyingxiang ryoloayolobasedmethodforarbitraryorientedtargetdetectioninhighresolutionremotesensingimages AT wangfan ryoloayolobasedmethodforarbitraryorientedtargetdetectioninhighresolutionremotesensingimages AT jiangxian ryoloayolobasedmethodforarbitraryorientedtargetdetectioninhighresolutionremotesensingimages AT zhuangrujun ryoloayolobasedmethodforarbitraryorientedtargetdetectioninhighresolutionremotesensingimages AT meiyunfei ryoloayolobasedmethodforarbitraryorientedtargetdetectioninhighresolutionremotesensingimages AT maxinjiang ryoloayolobasedmethodforarbitraryorientedtargetdetectioninhighresolutionremotesensingimages |