Synthetic aperture radar (SAR) image target detection method

US12131438B2 · kind B2 · utility

Assignees

• Anhui University · CN
• Anhui Zhongke Xinglian Information Technology Co., Ltd. · CN

Inventors

• Jie Chen · Hefei, CN
• Huiyao Wan · Hefei, CN
• Zhixiang Huang · Hefei, CN
• Xiaoping Liu · Tokyo, JP
• Bocai Wu · Hefei, CN
• Runfan Xia · Hefei, CN
• Zheng Zhou · Lo Wu, CN
• Jianming Lv · Hefei, CN
• Yun Feng · Dongguan, CN
• Wentian Du · Hefei, CN
• Jingqian Yu · Hefei, CN

Key dates

• Filing date: Feb 10, 2022
• Grant date: Oct 29, 2024
• Expiry date: Jan 22, 2043

Classification

• Technology area (CPC G): Physics
• CPC primary: G06V2201/07
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

The present disclosure provides a synthetic aperture radar (SAR) image target detection method. The present disclosure takes the anchor-free target detection algorithm YOLOX as the basic framework, reconstructs the backbone feature extraction network from the lightweight perspective, and replaces the depthwise separable convolution in MobilenetV2 with one ordinary convolution and one depthwise separable convolution. The number of channels in the feature map is reduced by half through the ordinary convolution, features input from the ordinary convolution are further extracted by the depthwise separable convolution, and the convolutional results from the two convolutions are spliced. The present disclosure highlights the unique strong scattering characteristic of the SAR target through the attention enhancement pyramid attention network (CSEMPAN) by integrating channels and spatial attention mechanisms. In view of the multiple scales and strong sparseness of the SAR target, the present disclosure uses an ESPHead.