SEFEPNet: Scale Expansion and Feature Enhancement Pyramid Network for SAR Aircraft Detection With Small Sample Dataset

• Published in: IEEE journal of selected topics in applied earth observations and remote sensing Vol. 15; pp. 3365 - 3375
• Main Authors: Zhang, Peng, Xu, Hao, Tian, Tian, Gao, Peng, Li, Linfeng, Zhao, Tianming, Zhang, Nan, Tian, Jinwen
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Aircraft; Aircraft detection; Atmospheric modeling; Complexity; Computer networks; Data models; Datasets; Detection; Domains; Feature enhancement pyramid (FEP); Feature extraction; Homology; Image enhancement; Interference; Methods; Object detection; Object recognition; Radar detection; Radar imaging; SAR (radar); Synthetic aperture radar; synthetic aperture radar (SAR) aircraft detection; Target detection; Transfer learning
• ISSN: 1939-1404; 2151-1535
• DOI: 10.1109/JSTARS.2022.3169339

Aircraft detection in synthetic aperture radar (SAR) images is still a challenging research task because of the insufficient public data, the difficulty of multiscale target detection, and the complexity of background interference. In this article, we construct a public SAR aircraft detection dataset (SADD) with complex background and interference objects to facilitate the research in SAR aircraft detection. Then, we propose the scale expansion and feature enhancement pyramid network as the SADD baseline. It uses a four-scale fusion method to combine the shallow position information with the deep semantic information, effectively adapting to the multiscale target detection in SAR images, significantly improving the detection effect of small targets. The feature enhancement pyramid structure is connected behind the backbone network to weaken the background texture and highlight the target to achieve feature enhancement, improving the ability to extract target features in complex backgrounds. Finally, to further improve the detection performance of the small-scale SAR aircraft dataset, we propose a domain adaptive transfer learning method. Experiments on SADD show that this method can significantly improve the recall rate and F1 score. At the same time, we find that the transfer effect of using homologous but different types of targets as the source domain is better than those of heterologous but same types of targets in SAR aircraft detection, which is instructive for future research.