A Lightweight Detection Model for SAR Aircraft in a Complex Environment

Abstract

Recently, deep learning has been widely used in synthetic aperture radar (SAR) aircraft detection. However, the complex environment of the airport—consider the boarding bridges, for instance—greatly interferes with aircraft detection. Besides, the detection speed is also an important indicator in practical applications. To alleviate these problems, we propose a lightweight detection model (LDM), mainly including a reuse block (RB) and an information correction block (ICB) based on the Yolov3 framework. The RB module helps the neural network extract rich aircraft features by aggregating multi-layer information. While the RB module brings more effective information, there is also redundant and useless information aggregated by the reuse block, which is harmful to detection precision. Therefore, to accurately extract more aircraft features, we propose an ICB module combining scattering mechanism characteristics by extracting the gray features and enhancing spatial information, which helps suppress interference in a complex environment and redundant information. Finally, we conducted a series of experiments on the SAR aircraft detection dataset (SAR-ADD). The average precision was 0.6954, which is superior to the precision values achieved by other methods. In addition, the average detection time of LDM was only 6.38 ms, making it much faster than other methods.

Synthetic aperture radar image aircraft detection based on target spatial imaging characteristics

“…Aircraft in SAR images usually consists of a series of scattering center points 19 Figure 3(a). shows a simulated SAR image of aircraft, Fig.…”

“…Aircraft in SAR images usually consists of a series of scattering center points. 19 grayscale values of this image. It can be seen that the aircraft in SAR image is discrete, and the intensity of the scattering center points varies with the radar incident angle, target azimuth angle, and other imaging conditions.…”

YOLO v7-CS: A YOLO v7-Based Model for Lightweight Bayberry Target Detection Count

“…Liu et al proposed a lightweight detection algorithm for the surface defects of fine crystals, which solved the problems of low detection efficiency, strong specificity, large fine-grained classification error, and unstable detection results in aerospace applications [32]. Li et al proposed a lightweight detection model for SAR aircraft in complex environments and proposed an ICB module combining the characteristics of scattering mechanisms, which can effectively extract gray features and enhance spatial information, inhibit interference and redundancy information in complex environments, and reduce the detection time [33]. Models that can simultaneously satisfy multiple and lightweight are more use in deployment in real-time detection devices.…”