Search

This study proposes a Synthetic Aperture Radar (SAR) aircraft detection and recognition method combined with scattering perception to address the problem of target discreteness and false alarms caused by strong background interference in SAR images. The global information is enhanced through a context-guided feature pyramid module, which suppresses strong disturbances in complex images and improves the accuracy of detection and recognition. Additionally, scatter key points are used to locate targets, and a scatter-aware detection module is designed to realize the fine correction of the regression boxes to improve target localization accuracy. This study generates and presents a high-resolution SAR-AIRcraft-1.0 dataset to verify the effectiveness of the proposed method and promote the research on SAR aircraft detection and recognition. The images in this dataset are obtained from the satellite Gaofen-3, which contains 4,368 images and 16,463 aircraft instances, covering seven aircraft categories, namely A220, A320/321, A330, ARJ21, Boeing737, Boeing787, and other. We apply the proposed method and common deep learning algorithms to the constructed dataset. The experimental results demonstrate the excellent effectiveness of our method combined with scattering perception. Furthermore, we establish benchmarks for the performance indicators of the dataset in different tasks such as SAR aircraft detection, recognition, and integrated detection and recognition.

The sample scarcity issue is still challenged for SAR images interpretation. The number of geospatial targets related images is constrained of the SAR images interpretation ability of data acquisition, sample labeling, and the lack of target coverage. Our SAR-ATR method is demonstrated based on scattering information and meta-learning. First, the discrete distribution of the spatial structure of different types of aircraft is quite different in SAR images. An associated scattering classifier is designed to guide the network to learn more discriminative intra-class and inter-class feature descriptions. Our proposed classifier facilitates the modeling of discrete degree of the aircraft target quantitatively and balance the weights of sample pairs dynamically through the differentiated analysis of different target discrete distributions. In addition, an adaptive feature refinement module is designed to optimize the network cohesion for the key parts of the aircraft and reduce the interference of background noise. The proposed method integrates the target scattering distribution properties to the network learning process. On 5-way 1-shot emerging categorized recognition task involved only few samples, our experimental results demonstrate that the recognition accuracy of this method is 59.90%, which is 3.85% higher than the benchmark. After reducing the amount of training data by half, the proposed method is still competitive on the new category of few-shot recognition tasks.

Over the recent years, high-resolution Synthetic-Aperture Radar (SAR) images have been widely applied for intelligent interpretation of urban mapping, change detection, etc. Different from optical images, the acquisition approach and object geometry of SAR images have limited the interpretation performances of the existing deep-learning methods. This paper proposes a novel building footprint generation method for high-resolution SAR images. This method is based on supervised contrastive learning regularization, which aims to increase the similarities between intra-class pixels and diversities of interclass pixels. This increase will make the deep learning models focus on distinguishing building and nonbuilding pixels in latent space, and improve the classification accuracy. Based on public SpaceNet6 data, the proposed method can improve the segmentation performance by 1% compared to the other state-of-the-art methods. This improvement validates the effectiveness of the proposed method on real data. This method can be used for building segmentation in urban areas with complex scene background. Moreover, the proposed method can be extended for other types of land-cover segmentation using SAR images.