skip to main content
10.1145/3445815.3445839acmotherconferencesArticle/Chapter ViewAbstractPublication PagescsaiConference Proceedingsconference-collections
research-article

Bridge Target Detection in Remote Sensing Image Based on Improved YOLOv4 Algorithm

Published: 17 March 2021 Publication History

Abstract

The automatic detection of bridge targets in remote sensing images is of great significance. By analyzing the YOLOv4 network structure and algorithm core ideas, according to the characteristics of remote sensing image bridge target detection, this paper adds 104×104 feature layer scale and combines the idea of attention mechanism to improve the algorithm network structure. At the same time, adjust the anchor point frame according to the characteristics of the bridge target scale to improve the performance of the YOLOv4 algorithm in the remote sensing image bridge target detection, and verify it through the design control experiment. The experimental results show that on the tailored DOTA bridge datasets, the bridge target precision and recall rate of the M-YOLO algorithm have been improved, and the average precision rate has increased by 5.6%, which proves the effectiveness of the improved algorithm.

References

[1]
WANG D Y. Research on Bridge Target Detection Technology in Large Format Images[D].Wuhan: Huazhong University of Science and Technology.2015.
[2]
ZHANG X, GUO F L, LIANG Y J. Survey of Small Target Detection Algorithms Based on Deep Learning[J]. Software Guide, 2020, 19 (5):276-280.
[3]
YUAN M Y, JIANG T, WANG X. Aircraft Target Detection in Remote Sensing Image Based on Improved YOLOv3 Algorithm༻J༽.Journal of Geomatics Science and Technology, 2019, 36( 6) : 614-619.
[4]
CHANG Y L, YANG J, LI P X, ZHAO L L, YU J. Automatic Bridge Recognition Method in High Resolut-ion PolSAR Images Based on CFAR Detector[J]. Geo-matics and Information Science of Wuhan University. 2017, 42(6):762-767.
[5]
Alexey Bochkovskiy, Chien-Yao Wang and Hong-Yuan Mark Liao. YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv: 2004.10934, 2020.4.
[6]
JIANG D B. A Thorough Explanation of the Core Basic Knowledge of Yolov3 & Yolov4 of the Yolo Series. [EB /OL]. [2020-5-28]. https://zhuanlan.zhihu.com/p/14374 7206.
[7]
Sangdoo Yun, Dongyoon Han, Seong Joon Oh, Sangh-yuk Chun, Junsuk Choe, and Youngjoon Yoo. CutMix: Regularization strategy to train strong classifiers with localizable features. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), pages 6023–6032, 2019.3.
[8]
Chien-Yao Wang, Hong-Yuan Mark Liao, Yueh-Hua Wu, Ping-Yang Chen, Jun-Wei Hsieh, and I-Hau Yeh. CSPNet:A new backbone that can enhance learning capability of cnn. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPR Workshop),2020. 2, 7.
[9]
Diganta Misra. Mish: A self regularized nonmonotonic neural activation function. arXiv preprint arXiv: 1908. 08681, 2019. 4.
[10]
Golnaz Ghiasi, Tsung-Yi Lin, and Quoc V Le. Drop-Block:A regularization method for convolutional networks. In Advances in Neural Information Process-ing Systems (NIPS), pages 10727–10737, 2018. 3.
[11]
Shu Liu, Lu Qi, Haifang Qin, Jianping Shi, and Jiaya Jia. Path aggregation network for instance segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 8759–8768, 2018.1, 2, 7.
[12]
Joseph Redmon and Ali Farhadi. YOLOv3: An incre-mental improvement. arXiv preprint arXiv:1804.02767, 2018. 2,4, 7, 11.
[13]
Zhaohui Zheng, Ping Wang, Wei Liu, Jinze Li, Rong-guang Ye, and Dongwei Ren. Distance-IoU Loss: Faster and better learning for bounding box regression. In Proceedings of the AAAI Conference on Artificial Intell-igence (AAAI),2020. 3, 4.
[14]
Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 779–788, 2016.2.
[15]
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 37(9):1904–1916, 2015. 2, 4, 7.
[16]
Joseph Redmon and Ali Farhadi. YOLO9000: better, faster, stronger. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 7263–7271, 2017. 2.

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
CSAI '20: Proceedings of the 2020 4th International Conference on Computer Science and Artificial Intelligence
December 2020
294 pages
ISBN:9781450388436
DOI:10.1145/3445815
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 17 March 2021

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. YOLOv4
  2. attention mechanism
  3. bridge target detection
  4. feature scale optimization
  5. remote sensing image

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

CSAI 2020

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 85
    Total Downloads
  • Downloads (Last 12 months)3
  • Downloads (Last 6 weeks)0
Reflects downloads up to 17 Feb 2025

Other Metrics

Citations

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media