Skip to Main content Skip to Navigation
Conference papers

Towards an Automatic Parking System using Bio-Inspired 1-D Optical Flow Sensors

Stefano Mafrica 1, 2 Alain Servel 1 Franck Ruffier 2
2 BIOROB - Biorobotique
ISM - Institut des Sciences du Mouvement Etienne Jules Marey
Abstract : Although several (semi-) automatic parking systems have been presented throughout the years [1]–[12], car manufacturers are still looking for low-cost sensors providing redundant information about the obstacles around the vehicle, as well as efficient methods of processing this information, in the hope of achieving a very high level of robustness. We therefore investigated how Local Motion Sensors (LMSs) [13], [14], comprising only of a few pixels giving 1-D optical flow (OF) measurements could be used to improve automatic parking maneuvers. For this purpose, we developed a low computational-cost method of detecting and tracking a parking spot in real time using 1-D OF measurements around the vehicle as well as the vehicle's longitudinal velocity and steering angle. The algorithm used was composed of 5 processing steps, which will be described here in detail. In this initial report, we will first present some results obtained in a highly simplified 2-D parking simulation performed using Matlab/Simulink software, before giving some preliminary experimental results obtained with the first step in the algorithm in the case of a vehicle equipped with two 6-pixel LMSs. The results of the closed-loop simulation show that up to a certain noise level, the simulated vehicle detected and tracked the parking-spot assessment in real time. The preliminary experimental results show that the average refresh frequency obtained with the LMSs was about 2-3 times higher than that obtained with standard ultrasonic sensors and cameras, and that these LMSs therefore constitute a promising alternative basis for designing new automatic parking systems.
Complete list of metadata

Cited literature [21 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01235593
Contributor : Stefano Mafrica <>
Submitted on : Thursday, December 3, 2015 - 12:23:57 PM
Last modification on : Tuesday, March 30, 2021 - 3:16:20 AM
Long-term archiving on: : Saturday, April 29, 2017 - 1:02:18 AM

File

PaperICVES2015_submitted.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01235593, version 1

Collections

Citation

Stefano Mafrica, Alain Servel, Franck Ruffier. Towards an Automatic Parking System using Bio-Inspired 1-D Optical Flow Sensors. IEEE International Conference on Vehicular Electronics and Safety (ICVES) 2015, Nov 2015, Yokohama, Japan. ⟨hal-01235593⟩

Share

Metrics

Record views

289

Files downloads

869