Computer Science ›› 2014, Vol. 41 ›› Issue (6): 269-274.doi: 10.11896/j.issn.1002-137X.2014.06.053

Previous Articles     Next Articles

Vehicle Matching Based on Quaternion Visual Attention Model

XU Hang,ZANG Di,CHENG Cheng and ZHANG Ya-ying   

  • Online:2018-11-14 Published:2018-11-14

Abstract: Searching and matching the vehicle which caused traffic accidents is a challenging problem of great importance in Intelligent Transport System (ITS).Compared with the traditional methods,visual attention model provides a new perspective by merging several fundamental features.This paper presented a new method to extract color information from an image aiming at vehicle matching problem.By combining with intensity and orientations under the framework of quaternions,a quaternion visual attention model was proposed.Experiments use the quaternion saliency as the new feature to match the vehicle which caused traffic accidents and the results demonstrate that the proposed approach is able to narrow the searching range effectively with good accuracy and robustness.

Key words: Vehicle which caused traffic accidents,Matching,Visual attention model,Saliency,Quaternion,Color feature

[1] Zeng N,Crisman J D.Vehicle matching using color [C]∥IEEE ITS Conf.1997:206-211
[2] Lowe D G.Distinctive Image Features from Scale-Invariant Keypoints[J].International Journal Computer Vision,2004,60(2):91-110
[3] Hu X L,Tang Y C,Zhang Z H.Video Object Matching Based on SIFT Algorithm[C]∥IEEE International Conference Neural Networks & Signal Processing.2008:412-415
[4] 纪华,吴元昊,孙宏海,等.结合全局信息的SIFT特征匹配算法[J].光学精密工程,2009(2):439-444
[5] Alhwarin F,Wang C,Ristic-Durrant D,et al.Improved SIFT-Features Matching for Object Recognition [C]∥BSC International Academic Conference.2008:170-190
[6] Hsu C Y,et al.Cross-camera vehicle tracking via affine invariant object matching for video forensics applications [C]∥IEEE Int.Conf.on Multimedia and Expo (ICME).2013
[7] Shan Y,Sahwney H S,Kumar R.Unsupervised learning of discriminative edge measures for vehicle matching between non-overlapping cameras [C]∥IEEE Conf.on Computer Vision and Pattern Recognition.2005,1:894-901
[8] Yan Bo,Wang Sheng-jin,Chen You-bin,et al.Deformable 3-D model based vehicle matching with weighted Hausdorff and EDA in traffic surveillance [C]∥International Conference on Image Analysis and Signal Processing.2010:22-27
[9] Jela∨V,Castaeda J O N,Frías-Velázquez A,et al.Real-Time Vehicle Matching for Multi-Camera Tunnel Surveillance [C]∥Proceedings of the SPIE 2011.San Francisco,2011
[10] Wang Hao-you,Shih H-C.A Robust Vehicle Model Construc-tion and Identification System using Local Feature Alignment [C]∥2013IEEE 17th International Symposium on Consumer Electronics (ISCE).2013
[11] Itti L.Models of Bottom-Up and Top-Down Visual Attention [D].California Institute of Technology Pasadena,2000
[12] 李旃.基于视觉注意机制的运动目标识别算法研究 [D].长沙:国防科技大学,2010
[13] 宋雁斓.视觉注意模型及其在图像分类中的应用 [D].上海:上海交通大学,2008
[14] Itti L,Koch C,Niebur E.A Model for Saliency-Based VisualAttention for Rapid Scene Analysis [J].IEEE Trans.Pattern Analysis and Machine Intelligence,1998,20(11):1254-1259
[15] Pei S-C,Cheng Ching-min.A novel block truncation coding ofcolor images by using quaternion-moment preserving principle [C]∥IEEE International Symposium Circuits and Systems.1996,2:684-687
[16] Bas P,Bihan N L,Chassery J.Color watermarking using quaternion Fourier transform [C]∥Acoustics,Speech,and Signal Processing.2003:521-524
[17] Sangwine S J.Color image edge detector based on quaternionconvolution[J].Electron Letters,1998,34(10):969-971
[18] Shi L,Funt B.Quaternion color texture segmentation [J].Computer Vision and Image Understand,2007,107:88-96
[19] Guo C L,Ma Q,Zhang L M.Spatio-temporal saliency detection using phase spectrum of quaternion Fourier transform[C]∥IEEE Conf.on Computer Vision and Pattern Recognition.2008:1-8
[20] Daugman J G.Uncertainty relation for resolution in space,spatial frequency,and orientation optimized by two-dimensional visual cortical filters [J].Journal of the Optical Society of America A,1985,2:1160-1169
[21] Otsu N.A threshold selection method from gray-level histo-grams [J].IEEE Trans.Biomed.Eng.,1979,BME-9:63-66

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!