A Statistical Method for Parking Spaces Occupancy Detection via Automotive Radars

TL;DR

This paper presents a statistical approach using automotive radars and a two-step classification algorithm to detect parking occupancy, addressing data sparsity issues and achieving promising accuracy in real-world tests.

Contribution

It introduces a novel two-step classification method combining Mean-Shift clustering and SVM for parking detection using encoded radar data, overcoming raw data access limitations.

Findings

Average Type I error rate: 15.23% off-street, 32.62% on-street

Type II error rates are below 20% in both cases

Bayesian updating improves occupancy mapping recursively

Abstract

Real-time parking occupancy information is valuable for guiding drivers' searching for parking spaces. Recently many parking detection systems using range-based on-vehicle sensors are invented, but they disregard the practical difficulty of obtaining access to raw sensory data which are required for any feature-based algorithm. In this paper, we focus on a system using 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 the data transmitted through ADAS unit has been encoded to sparse points is overcome by a statistical method instead of feature extractions. We propose a two-step classification algorithm combining Mean-Shift clustering and Support Vector Machine to analyze SRR-GPS data, 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 $20 \%$. Bayesian updating can recursively improve the mapping results. This paper can provide a comprehensive method to elevate automotive sensors for the parking detection function.