Two-Stream Deep Fusion Network Based on VAE and CNN for Synthetic Aperture Radar Target Recognition

Abstract

Usually radar target recognition methods only use a single type of high-resolution radar signal, e.g., high-resolution range profile (HRRP) or synthetic aperture radar (SAR) images. In fact, in the SAR imaging procedure, we can simultaneously obtain both the HRRP data and the corresponding SAR image, as the information contained within them is not exactly the same. Although the information contained in the HRRP data and the SAR image are not exactly the same, both are important for radar target recognition. Therefore, in this paper, we propose a novel end-to-end two stream fusion network to make full use of the different characteristics obtained from modeling HRRP data and SAR images, respectively, for SAR target recognition. The proposed fusion network contains two separated streams in the feature extraction stage, one of which takes advantage of a variational auto-encoder (VAE) network to acquire the latent probabilistic distribution characteristic from the HRRP data, and the other uses a lightweight convolutional neural network, LightNet, to extract the 2D visual structure characteristics based on SAR images. Following the feature extraction stage, a fusion module is utilized to integrate the latent probabilistic distribution characteristic and the structure characteristic for the reflecting target information more comprehensively and sufficiently. The main contribution of the proposed method consists of two parts: (1) different characteristics from the HRRP data and the SAR image can be used effectively for SAR target recognition, and (2) an attention weight vector is used in the fusion module to adaptively integrate the different characteristics from the two sub-networks. The experimental results of our method on the HRRP data and SAR images of the MSTAR and civilian vehicle datasets obtained improvements of at least 0.96 and 2.16%, respectively, on recognition rates, compared with current SAR target recognition methods.

An operation site security detection method based on point cloud data and improved YOLO algorithm under the architecture of the power internet of things

“…Ref. [17] proposes a new end‐to‐end dual flow fusion network, which includes two separate flows in the feature extraction stage and utilizes fusion modules to comprehensively integrate potential probability distribution features and structural features reflecting target information, in order to achieve accurate target classification. Ref.…”

Deep fusion network based on two-stream CNN for radar target recognition

“…In practical applications, prior information is variable and even unknown [5] . Moreover, these features primarily constitute lower-level representations, such as texture features and local physical structural features, and cannot represent higher-level abstract information [6] . With the rise of deep learning, an increasing number of radar target recognition methods based on deep learning have emerged and achieved excellent performance.…”

FACET-based SAR imaging and target detection based on YOLOv7

“…Synthetic aperture radar (SAR) target imaging of satellites or airborne early warning aircraft plays a vital role in the commercial, civil, and military fields. Due to the unique advantage of all-weather and all-day for imaging, it has been widely employed in target reconnaissance, automatic driving, ecological monitoring, natural disaster treatment, and so forth [1]. In recent years, SAR imaging methods and SAR image target recognition have been hot topics in this field.…”