@article{ZHONG2025, 
author = {Shuai ZHONG and Liping WANG},
title = {MCS-RETR: Improved RT-DETR object detection method for UAV aerial images},
year = {2025},
journal = {Acta Aeronautica et Astronautica Sinica},
volume = {46},
number = {22},
keywords = {object detection, UAV aerial imagery, RT-DETR, multi-scale edge information enhancement, convolutional additive token mixer, small object enhancement pyramid},
url = {https://www.sciopen.com/article/10.7527/S1000-6893.2025.31987},
doi = {10.7527/S1000-6893.2025.31987},
abstract = {To address the challenges in Unmanned Aerial Vehicle (UAV) aerial imagery, such as blurred object edge information, complex background interference, and the low resolution and difficulty in identification of small objects, this paper proposes a novel improved RT-DETR-based object detection method for UAV aerial imagery, named MCS-DETR. Initially, a multi-scale edge information enhancement module is designed within the backbone network. By constructing an edge information enhancement mechanism and integrating it with deep convolutional operations and feature fusion strategies, the module aims to extract feature information at different scales and enhance the model's perception of image edge information. Subsequently, a convolutional additive token mixer is incorporated into the intra-scale feature interaction mechanism to optimize the feature interaction process and improve the model's capability of capturing global contextual key information. Finally, based on the original feature fusion method, a small object enhancement pyramid network is proposed to enhance the model's ability to extract detailed features of small targets. Experimental results indicate that, compared to the RT-DETR model, the MCS-DETR algorithm reduces the parameter size by 20.7%, while increasing accuracy, recall, mAP50, and mAP50∶95 of 2.4%, 3.1%, 2.8%, and 2.0%, respectively on the Visdrone2019-DET-Test dataset. This method effectively migrates missed and erroneous detections in complex scenes for UAV aerial image object detection.}
}