Supervised Contrastive Learning for Vehicle Classification Based on the IR-UWB Radar

Impulse radio ultrawideband (IR-UWB) radar has high range resolution, strong anti-jamming ability, and low power consumption and has been widely used in target detection and recognition. Currently, existing studies always extract artificial features of echo signals, such as time–frequency images, Doppler features, or time-domain features, and then distinguish these features through well-designed deep networks. However, these manual features are difficult to achieve task-invariant and disentangled representations. The target echo received by UWB radar also has amplitude, time-shift, and target-aspect sensitivity problems. To address the above problems, we propose a novel supervised contrastive learning (SupCon) framework to recognize different vehicles. Under label constraints, deep invariant representations are obtained through contrastive learning of echo signals, improving classification accuracy. First, a 1-D deep residual network (ResNet) is designed as the backbone, and the self-attention (SA) layer is added to extract long-range features of echo signals. Second, well-designed data augmentation methods can improve the performance of contrastive learning. Due to the integration of multiple data transformations, the model can learn invariant features by maximizing the mutual information between different signal transformations. Finally, we modify the SupCon loss function. It alleviates the conflict problem of simultaneously shrinking and expanding the distance between the positive samples in the feature space and improves the recognition performance of the model. Ablation experiments on the measured dataset show that the designed components of the method are effective. Comparative experiments on ultrawideband radar public datasets [Air Force Research Laboratory’s (AFRL) high-resolution range profile (HRRP), moving and stationary target acquisition and recognition (MSTAR)] also demonstrate the excellent classification performance of the proposed algorithm.

I. Introduction

The impulse radio ultrawideband (IR-UWB) radar uses impulse waves of short duration and wide bandwidth. It has many advantages over other sensor systems, including high resolution, anti-interference, good penetration power, and insensitivity to light and climate [1], [2]. Due to these promising characteristics, studies based on the IR-UWB radar have been carried out with topics on people motion identification [3], [4], gesture recognition [5], target recognition in the jungle [6], [7], and medical assistance [8]. However, most of the existing IR-UWB target recognition studies focus on human postures or gestures, and there are few studies on target recognition with large size, many scattering points, and complex distribution. This article uses IR-UWB radar to identify different vehicles to help applications such as traffic safety. Compared to other sensors, it is less susceptible to weather, light, or dust conditions [9]. Moreover, the extremely narrow pulsewidth gives it a high-range resolution and small near-range blind zone.