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
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;
Conference_Titel :
Control Engineering and Communication Technology (ICCECT), 2012 International Conference on
Conference_Location :
Liaoning
Print_ISBN :
978-1-4673-4499-9
DOI :
10.1109/ICCECT.2012.194