Parking Slot Markings Recognition for Automatic Parking Assist System

Author

Jung, Ho Gi ; Kim, Dong Suk ; Yoon, Pal Joo ; Kim, Jaihie

Author_Institution

Central R&D Center, MANDO Corp., Yongin

fYear

0

fDate

0-0 0

Firstpage

106

Lastpage

113

Abstract

This paper describes a monocular vision based parking-slot-markings recognition algorithm, which is used to automate the target position selection of automatic parking assist system. Peak-pair detection and clustering in Hough space recognize marking lines. Specially, one-dimensional filter in Hough space is designed to utilize a priori knowledge about the characteristics of marking lines in bird´s eye view edge image. Modified distance between point and line-segment is used to distinguish guideline from recognized marking line-segments. Once the guideline is successfully recognized, T-shape template matching easily recognizes dividing marking line-segments. Experiments show that proposed algorithm successfully recognizes parking slots even when adjacent vehicles occlude parking-slot-markings severely

Keywords

computer vision; image matching; pattern clustering; traffic engineering computing; Hough space; T-shape template matching; automatic parking assist system; clustering; monocular vision based parking slot markings recognition; one-dimensional filter; peak-pair detection; target position selection; Filters; Guidelines; Image edge detection; Image recognition; Machine vision; Manufacturing automation; Sensor systems; Stereo vision; Surface fitting; Vehicles;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Vehicles Symposium, 2006 IEEE

Conference_Location

Tokyo

Print_ISBN

4-901122-86-X

Type

conf

DOI

10.1109/IVS.2006.1689613

Filename

1689613