SVDD: SAR Vehicle Dataset Construction and Detection

作     者：Gao, Dan Wu, Xiaofang Wen, Zhijin Xu, Yue Chen, Zhengchao 

作者机构：Acad Mil Sci Peoples Liberat Army Inst Syst Engn Beijing 100191 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Key Lab Remote Sensing & Digital Earth Beijing 100094 Peoples R China 

出 版 物：《IEEE ACCESS》 (IEEE Access)

年 卷 期：2025年第13卷

页      面：18107-18122页

核心收录：

主　　题：Object detection Feature extraction Detection algorithms Vehicle detection Synthetic aperture radar Accuracy Real-time systems Transformers Computational modeling Complexity theory Deep learning object detection synthetic aperture radar datasets vision transformer 

摘      要：With the advent of high-quality SAR images and the rapid development of computing technology, the object detection algorithms based on convolution neural network have attracted a lot of attention in the field of SAR object detection. At present, the main dataset for SAR target detection in China focus on ships, there is a lack of SAR vehicle detect datasets, and complex ground scenes can affect vehicle detection performance. To solve these problems, we proposed a lightweight SAR vehicle detection algorithm, aiming to improve the vehicle detection accuracy and simplify the model complexity. First, we constructed a multi-band SAR vehicle detection dataset (SVDD) with annotations as the training dataset of the object detection model. Then, we introduced dual conv into the RT-DETR model. Dual conv uses group convolution technology to filter the convolutional network to reduce model parameters, so we can achieve a lightweight and real-time end-to-end detection. Finally, we used the mmdetection framework as a benchmark and test the robust performance under different conditions. Experimental results show that the AP50 of we proposed method reaches 98.5%, achieving excellent detection performance.