CDE-DETR: A Real-Time End-To-End High-Resolution Remote Sensing Object Detection Method Based on RT-DETR
Anrui Wang, Yang Xu, He Wang, Zebin Wu, Zhihui Wei
Abstract
High-resolution remote sensing object detection is a research field with significant application value and challenges. However, existing methods cannot directly predict or produce a large number of redundant bounding boxes. They perform poorly in the face of issues such as multi-scale, dense small objects, and complex backgrounds in high-resolution remote sensing images. Therefore, a real-time end-to-end high-resolution remote sensing object detection method based on RT-DETR (CDE-DETR) is proposed. Through introducing cascaded group attention, we propose CGA-IFI for intra-scale feature interaction. The DRB-CFFM is designed with a dilated reparam block to facilitate cross-scale feature interaction. Furthermore, we enhance the bounding box regression loss function with EIoU. Experimental results demonstrate that the accuracy mAP value of our method is 2.9% higher than the baseline, FPS is increased by 33.8%. The number of parameters is reduced by 9.9%, and FLOPs is reduced by 16.0%. Compared with other methods, the proposed method has obvious accuracy and lightweight advantages.