Pedestrian motion direction estimation using simulated automotive MIMO radar

Micro-Doppler (MD)-based target classification capabilities of automotive radars can provide high reliability and short latency to future active safety automotive features. A large number of pedestrians surrounding a vehicle in practical urban scenarios mandate prioritization of their treatment level. Distinguishing between relevant pedestrians that are crossing the street or are within the vehicle path and those that are on the sidewalks and are moving along the vehicle route can significantly minimize the number of vehicle-to-pedestrian accidents. This work proposes a novel technique for estimating a pedestrian direction of motion that treats pedestrians as complex distributed targets and utilizes their MD radar signatures. The MD signatures are shown to be indicative of pedestrian direction of motion, and a supervised regression is used to estimate the mapping between the directions of motion and the corresponding MD signatures. In order to achieve higher regression performance, a state-of-the-art sparse dictionary learning-based feature extraction algorithm was adopted from the field of computer vision by drawing a parallel between the Doppler effect and the video temporal gradient. The performance of the proposed approach is evaluated in practical automotive scenario simulations, where a walking pedestrian is observed by a multiple-input/multiple-output automotive radar with a two-dimensional rectangular array. The simulated data was generated using the statistical Boulic-Thalman human locomotion model. Accurate direction of motion estimation was achieved by using support vector regression and multilayer perceptron-based regression algorithms. The results show that the direction estimation error is less than 10° in 95% of the tested cases for pedestrian at a range of 100 m from the radar.