DocumentCode
2989176
Title
Vision-Based Curvature Model for Artificial Intelligence in Vehicles
Author
Chong Wang ; Weiwei Miao ; Junfeng Zhao
Author_Institution
Jiangsu Electr. Power Inf. & Telecommun. Co., Jiangsu, China
fYear
2012
fDate
7-9 Dec. 2012
Firstpage
245
Lastpage
248
Abstract
Most vehicles use GPS for vehicle autonomous driving. Visual information is essential in artificial intelligence in vehicles and should be an important supplement to the GPS-based system. But road lanes are often curved, making vision-based detection of smooth and continuous curves a challenging task. Furthermore, commonly used computer vision algorithms such as edge detectors or Hough transform for line or curvature detection are not robust in changing lighting conditions. This paper presents a vision algorithm designed specifically for detecting and modeling road curvature for human-like active steering control and heading adjustment for artificial intelligence in vehicles. The proposed algorithm has been tested in different road conditions and shown very good results.
Keywords
Gabor filters; Global Positioning System; artificial intelligence; automated highways; computer vision; edge detection; lighting; road vehicles; steering systems; wavelet transforms; GPS-based system; Gabor wavelet filters; artificial intelligence; computer vision algorithm; continuous curves; heading adjustment; human-like active steering control; lighting conditions; line detection; road conditions; road curvature detection; road curvature modeling; road lanes; smooth curves; vehicle autonomous driving; vision-based curvature model; vision-based detection; visual information; Computational modeling; Feature extraction; Gabor filters; Image edge detection; Kernel; Roads; Vehicles; Gabor wavelet filters; artificial intelligence; lane detection; q-Bernstein polynomials;
fLanguage
English
Publisher
ieee
Conference_Titel
Control Engineering and Communication Technology (ICCECT), 2012 International Conference on
Conference_Location
Liaoning
Print_ISBN
978-1-4673-4499-9
Type
conf
DOI
10.1109/ICCECT.2012.194
Filename
6414110
Link To Document