Machine Vision to Lane Departure Detection Systems

碩士 === 國立成功大學 === 航空太空工程學系碩博士班 === 97 === A lane-departure detection system without intrinsic and extrinsic camera parameters calibration is proposed in this paper. This system, which provides driving safety by lane detection and lane departure warning, is focused on urban road with complicated lane...

Full description

Bibliographic Details
Main Authors: Yu-Chi Leng, 冷玉琦
Other Authors: Chieh-Li Chen
Format: Others
Language:zh-TW
Published: 2009
Online Access:http://ndltd.ncl.edu.tw/handle/54398594556234935793
Description
Summary:碩士 === 國立成功大學 === 航空太空工程學系碩博士班 === 97 === A lane-departure detection system without intrinsic and extrinsic camera parameters calibration is proposed in this paper. This system, which provides driving safety by lane detection and lane departure warning, is focused on urban road with complicated lane marks instead of simpler highway cases. Due to the complexity of urban traffic, false lane detection is mainly caused by warning lines and signs which shape and color are similar to lane boundaries. In this dissertation, two lane features, i.e. specific width and lane mark continuity, are proposed to reduce image information disturbances and to obtain reliable detected results. Lane departure warning decisions are then applied to provide driving safety. Experimental results of urban road sceneries have demonstrate effectiveness of the proposed method.