Open Access iconOpen Access

ARTICLE

crossmark

RT-YOLO: A Residual Feature Fusion Triple Attention Network for Aerial Image Target Detection

Pan Zhang, Hongwei Deng*, Zhong Chen

College of Computer Science and Technology, Hengyang Normal University, Hengyang, 421002, China

* Corresponding Author: Hongwei Deng. Email: email

Computers, Materials & Continua 2023, 75(1), 1411-1430. https://doi.org/10.32604/cmc.2023.034876

Abstract

In recent years, target detection of aerial images of unmanned aerial vehicle (UAV) has become one of the hottest topics. However, target detection of UAV aerial images often presents false detection and missed detection. We proposed a modified you only look once (YOLO) model to improve the problems arising in object detection in UAV aerial images: (1) A new residual structure is designed to improve the ability to extract features by enhancing the fusion of the inner features of the single layer. At the same time, triplet attention module is added to strengthen the connection between space and channel and better retain important feature information. (2) The feature information is enriched by improving the multi-scale feature pyramid structure and strengthening the feature fusion at different scales. (3) A new loss function is created and the diagonal penalty term of the anchor frame is introduced to improve the speed of training and the accuracy of reasoning. The proposed model is called residual feature fusion triple attention YOLO (RT-YOLO). Experiments showed that the mean average precision (mAP) of RT-YOLO is increased from 57.2% to 60.8% on the vehicle detection in aerial image (VEDAI) dataset, and the mAP is also increased by 1.7% on the remote sensing object detection (RSOD) dataset. The results show that the RT-YOLO outperforms other mainstream models in UAV aerial image object detection.

Keywords


Cite This Article

APA Style
Zhang, P., Deng, H., Chen, Z. (2023). RT-YOLO: A residual feature fusion triple attention network for aerial image target detection. Computers, Materials & Continua, 75(1), 1411-1430. https://doi.org/10.32604/cmc.2023.034876
Vancouver Style
Zhang P, Deng H, Chen Z. RT-YOLO: A residual feature fusion triple attention network for aerial image target detection. Comput Mater Contin. 2023;75(1):1411-1430 https://doi.org/10.32604/cmc.2023.034876
IEEE Style
P. Zhang, H. Deng, and Z. Chen "RT-YOLO: A Residual Feature Fusion Triple Attention Network for Aerial Image Target Detection," Comput. Mater. Contin., vol. 75, no. 1, pp. 1411-1430. 2023. https://doi.org/10.32604/cmc.2023.034876



cc This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 937

    View

  • 503

    Download

  • 2

    Like

Share Link