A Statistical Method for Parking Spaces Occupancy Detection via Automotive Radars

Real-time parking occupancy information is valuable for guiding drivers' searching for parking spaces. Recently many parking detection systems using on-vehicle range-based sensors are invented. However, they disregard the practical difficulty of obtaining access to raw sensory data which are required for feature-based algorithms. In this paper, we focus on transforming short-range radars (SRR) embedded in Advanced Driver Assistance System (ADAS) to collect occupancy information, and broadcast it through a connected vehicle network. The challenge that raw data transmitted through ADAS unit has been encoded to sparse points is overcome by analyzing the cumulative data by statistical techniques instead of direct feature extractions. We propose a two-step classification algorithm combining Mean-Shift clustering and Support Vector Machine, and evaluate it through field experiments. The results show that the average Type I error rate for off-street parking is 15.23% and for on-street parking is 32.62%. In both cased the Type II error rates are less than 20%, and Bayesian updating can recursively improve the mapping results. This paper provides a comprehensive method to leverage on ADAS sensors for the parking detection function.