Traffic Sign Recognition Utilizing an Eigen Space Method Based on the KL Transform

Abstract:

This study explains that a method utilizing the eigen spaces obtained by the KL transform for automatic recognition by camera of the speed on a speed limit sign has the following advantages: it is robust in response to changes in intensity patterns caused by the direction the sign is facing and by the amount of light striking the sign, and it is able to reduce the recognition processing time by reducing the number of feature vector dimensions during analysis. The method for recognition of traffic signs previously proposed by the authors of this study was a method for recognition based on extracting geometric shapes from the sign and recognizing them based on their aspect ratios. As such, this method was not able to identify the numbers on a speed limit sign, all of which have identical aspect ratios. It will be shown that the method in this study is able to recognize nearly all speed limits indicated on traffic signs within several 100s of ms after image acquisition. This method was applied to still images and its effectiveness was verified from the perspective of the following requirements for providing accurate information concerning the vehicle surroundings to the driver: high processing speed, high recognition accuracy, detection of all detectable objects without omission, and robustness in response to changes in the surrounding environment.

• Periodical: Advanced Materials Research (Volumes 452-453)
• Pages: 876-882
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.452-453.876
• Online since: January 2012
• Authors: Shigeharu Miyata, Takahiro Ishikawa, Hitomi Nakamura, Shin Takehara
• Keywords: Computer Vision, Eigen Space Method, Feature Extraction, Image Processing, KL Transform, Pattern Recognition, Traffic Sign

References

[1] H. Yamaguchi; A. Kojima; T. Miyamoto; H. Takahashi; K. Fukunaga. A Robust Road Sign Recognition by Superposing Extracted Regions from Successive Frame (in Japanese), IEICE Trans. D-II, 2007. J90-D-II. no. 2, PP494-502.

DOI: 10.1109/icmech.2007.4279978

[2] G. Mo; Y. Aoki. A Recognition Method for Traffic Sign in Color Image (in Japanese), IEICE Trans. D-II, 2004. J87-D-II. no. 12, PP2124-2135.

[3] S. Hsu; C. Huang. Road Sign Detection and Recognition Using Matching Pursuit Method, Image and Vision Computing, 2001. 19. no. 3, PP119-129.

DOI: 10.1016/s0262-8856(00)00050-0

[4] K. Uchimura; S. Wakiyama; M. Fujino. Extraction of Circular Traffic Sign Using Limited Color Indication (in Japanese), IEICE Trans. D-II. 2000. J83-D-II. no. 2, PP855-858.

[5] D.M. Gavrila. Multi-Feature Hierarchical Template Matching Using Distance Transforms, Proc. of IEEE International Conference on Pattern Recognition, 1998. Sept., PP439-444.

DOI: 10.1109/icpr.1998.711175

[6] G. Piccioli; E. De Michieli; P. Parodi; M. Campani. Robust Method for Road Sign Detection and Recognition, Image and Vision Computing, 1996. 14. no. 3, PP209-223.

DOI: 10.1016/0262-8856(95)01057-2

[7] S. Kimura; H. Tano; T. Sakamoto; H. Shiroma; Y. Ohashi. Traversal Region and Obstacle Detection Using Tilted-Plane-Based Stereo Vision (in Japanese), Robotics Society of Japan[J], 2005. 23. no. 2, PP59-66.

DOI: 10.7210/jrsj.23.205

[8] S. Uchida; M. Iwamura; S. Omachi; K. Kise. Category Data Embedding for Camera-Based Character Recognition (in Japanese), IEICE Trans. D-II, 2006. J89-D-II. no. 2, PP344-352.

DOI: 10.1109/icpr.2006.891

[9] D. Doermann; J. Liang; H. Li. Progress in Camera-Based Document Image Analysis, Proc. of IC-DAR'03, 2003, PP606-616.

[10] Y. Inoue; N. Ishikawa; M. Nakajima. Automatic Recognition of Road Signs (in Japanese), Techical report of IEICE, 2003. ITS2003-98, PP57-62.

[11] D. Matsuura; H. Yamauchi; H. Takahashi. Extracting Circular Road Sign Using Specific Color Distinction and Region Limitation (in Japanese), IEICE Trans. D-II, 2002. J85-D-II. no. 6, PP1075-1083.

DOI: 10.1002/scj.10396

[12] K. Uchimura; H. Kimura; S. Wakiyama. Extraction and Recognition of Circular Road Signs Using Road Scene Color Image(in Japanese), IEICE Trans. A, 1998. J81-A. no. 4, PP546-553.

[13] N. Yabuki; Y. Matsuda; D. Kataoka; Y. Sumi; Y. Fukui; S. Miki. A Study on an Automatic Stop of Computation in Active Net (in Japanese), Technical report of IEICE, 2000. 99. 575, PP69-76.

[14] T. T. Zin; H. Hama. A Robust Road Sign Recognition Using Segmentation with Morphology and Relative Color, Institute of Image Information and Television Engineers[J], 2005. 59. no. 9, PP1333-1342.

DOI: 10.3169/itej.59.1333

[15] Z. Zhang; Y. Ahao. Multiple Description Image Coding Based on Fractal, Innovative Computing, Information and Control[J], 2007. 3. no. 6 (B), PP1615-1623.

[16] X. zhang. The Improvement of a Feature-Based Image Mosaics Algorithm, Innovative Computing, Information and Control[J], 2008. 4. no. 10, PP2759-2764.

[17] C. C. Chen; D. S. Kao. DCT-Based Zero Replacement Reversible Image Watermarking Approach, Innovative Computing, Information and Control[J], 2008. 4. no. 11, PP3027-3036.

[18] H. Yamauchi; H. Takahashi. A Road Sign Recognition Technique by Tracing Outline Vectors, Institute of Image Information and Television Engineers[J], 2003. 57. no. 7, PP847-853.

DOI: 10.3169/itej.57.847

[19] K. Fukui; O. Yamaguchi. Identification Technology with Face Image Recognition, TOSHIBA Review, 2001. 56. no. 7, PP14-17.

[20] S. Miyata; A. Yanou; H. Nakamura; S. Takehara. Road Sign Feature Extraction and Recognition sing Dynamic Image Processing, Innovative Computing, Information and Control[J], 2009. 5. no. 11(B), PP4105-4113.

DOI: 10.1109/icicic.2008.277

[21] V. Rehrmann; L. Priese. Fast and Robust Segmentation of Natural Color Scenes, Proc. of the 3rd Asian Conference on Computer Vision, 1998. 1(Hongkong), PP598-606.

DOI: 10.1007/3-540-63930-6_172

[22] M. Miyahara; Y. Yoshida. Mathematical Transform of (R, G, B) Color Space to Munsel (H, V, C) Color Data, SPIE visual Communication and Image Processing, visual Communication, 1998. 1001, PP650-657.

[23] Y.J. Zhang; Y.R. Yao; Y. He. Color Image Segmentation Based on HSI model, High Tech. Let., 1998. 4. no. 1, PP28-31.