Color Barycenter Hexagon Model Based Road Sign Detection

topics in the field of driving safety and intelligent vehicle. In this paper, a new method using Color Barycenter Hexagon (CBH) model for road sign detection is proposed. In CBH model, full color images are calculated the color barycenter and get the barycenter region, then select the thresholds to separate the region of interest (ROI) aiming to detect the road sign. Because of the practically image have many noise, and at the existing color space can not separate the ROI ideally, the proposed CBH model can thresholding the principal color of ROI and have high robust. With simple thresholding and operations, road sign on various scene images can be detected.

[1]  Massimo Bertozzi,et al.  GOLD: a parallel real-time stereo vision system for generic obstacle and lane detection , 1998, IEEE Trans. Image Process..

[2]  Jason M. Kinser,et al.  Optimizing image segmentation using color model mixtures , 2005, 34th Applied Imagery and Pattern Recognition Workshop (AIPR'05).

[3]  Arnold W. M. Smeulders,et al.  PicToSeek: combining color and shape invariant features for image retrieval , 2000, IEEE Trans. Image Process..

[4]  Theo Gevers,et al.  Selection and Fusion of Color Models for Image Feature Detection , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Shang-Jeng Tsai,et al.  HSI color model based lane-marking detection , 2006, 2006 IEEE Intelligent Transportation Systems Conference.

[6]  Yun Q. Shi,et al.  Identifying Computer Graphics using HSV Color Model and Statistical Moments of Characteristic Functions , 2007, 2007 IEEE International Conference on Multimedia and Expo.

[7]  Eam Khwang Teoh,et al.  Laser and camera for road edge and mid-line detection , 2001, Proceedings of the Second International Workshop on Robot Motion and Control. RoMoCo'01 (IEEE Cat. No.01EX535).

[8]  Theo Gevers,et al.  Selection and fusion of color models for feature detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).