The detection of vehicle targets in wide-area Synthetic Aperture Radar (SAR) images is crucial for real-time reconnaissance tasks and the widespread application of remote sensing technology in military and civilian fields. However, existing detection methods often face difficulties in handling large-scale images and achieving high accuracy. In this study, we address the challenges of detecting vehicle targets in wide-area SAR images and propose a novel method that combines coarse-grained judgment with fine-grained detection to overcome these challenges. Our proposed vehicle detection model is based on YOLOv5, featuring a CAM attention module, CAM-FPN network, and decoupled detection head, and it is strengthened with background-assisted supervision and coarse-grained judgment. These various techniques not only improve the accuracy of the detection algorithms, but also enhance SAR image processing speed. We evaluate the performance of our model using the Wide-area SAR Vehicle Detection (WSVD) dataset. The results demonstrate that the proposed method achieves a high level of accuracy in identifying vehicle targets in wide-area SAR images. Our method effectively addresses the challenges of detecting vehicle targets in wide-area SAR images, and has the potential to significantly enhance real-time reconnaissance tasks and promote the widespread application of remote sensing technology in various fields.
Full Text Finder