For target detection tasks in complicated backgrounds, a deep learning-based radar target detection method is suggested to address the problems of a high false alarm rate and the difficulties of achieving high-performance detection by conventional methods. Considering the issues of large parameter count and memory occupation of the deep learning-based target detection models, a lightweight target detection method based on improved YOLOv4-tiny is proposed. The technique applies depthwise separable convolution (DSC) and bottleneck architecture (BA) to the YOLOv4-tiny network. Moreover, it introduces the convolutional block attention module (CBAM) in the improved feature fusion network. It allows the network to be lightweight while ensuring detection accuracy. We choose a certain number of pulses from the pulse-compressed radar data for clutter suppression and Doppler processing to obtain range–Doppler (R–D) images. Experiments are run on the R–D two-dimensional echo images, and the results demonstrate that the proposed method can quickly and accurately detect dim radar targets against complicated backgrounds. Compared with other algorithms, our approach is more balanced regarding detection accuracy, model size, and detection speed.

No abstract