2016/07/22 by Qi Luo, Romesh Saigal, Luo, Qi +5
Engineering · #FOS: Computer and information sciences #Indoor and Outdoor Localization Technologies #Power Line Communications and Noise #Robotics (cs.RO) #Smart Parking Systems Research
paper · pdf · doi:10.48550/arxiv.1607.06708
openalex publication_date 2016/07/22 · openalex created_date 2021/07/05 · openalex updated_date 2026/07/28
Real-time parking occupancy information is valuable for guiding drivers'\nsearching for parking spaces. Recently many parking detection systems using\nrange-based on-vehicle sensors are invented, but they disregard the practical\ndifficulty of obtaining access to raw sensory data which are required for any\nfeature-based algorithm. In this paper, we focus on a system using short-range\nradars (SRR) embedded in Advanced Driver Assistance System (ADAS) to collect\noccupancy information, and broadcast it through a connected vehicle network.\nThe challenge that the data transmitted through ADAS unit has been encoded to\nsparse points is overcome by a statistical method instead of feature\nextractions. We propose a two-step classification algorithm combining\nMean-Shift clustering and Support Vector Machine to analyze SRR-GPS data, and\nevaluate it through field experiments. The results show that the average Type I\nerror rate for off-street parking is 15.23 % and for on-street parking is\n32.62 %. In both cased the Type II error rates are less than 20 %.\nBayesian updating can recursively improve the mapping results. This paper can\nprovide a comprehensive method to elevate automotive sensors for the parking\ndetection function.\n