Skip to main content
SpringerLink
Log in

Car model recognition by utilizing symmetric property to overcome severe pose variation

  • Original Paper
  • Published:
Machine Vision and Applications Aims and scope Submit manuscript

Abstract

This paper presents a mirror morphing scheme to deal with the challenging pose variation problem in car model recognition. Conventionally, researchers adopt pose estimation techniques to overcome the pose problem, whereas it is difficult to obtain very accurate pose estimation. Moreover, slight deviation in pose estimation degrades the recognition performance dramatically. The mirror morphing technique utilizes the symmetric property of cars to normalize car images of any orientation into a typical view. Therefore, the pose error and center bias can be eliminated and satisfactory recognition performance can be obtained. To support mirror morphing, active shape model (ASM) is used to acquire car shape information. An effective pose and center estimation approach is also proposed to provide a good initialization for ASM. In experiments, our proposed car model recognition system can achieve very high recognition rate (>95%) with very low probability of false alarm even when it is dealing with the severe pose problem in the cases of cars with similar shape and color.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Zheng D., Zhao Y., Wang J.: An efficient method of license plate location. Pattern Recogn. Lett. 26(15), 2431–2438 (2005)

    Article  Google Scholar 

  2. Chang S.L., Chen L.S., Chung Y.C., Chen S.W.: Automatic license plate recognition. IEEE Trans. Intell. Transp. Syst. 5(1), 42–53 (2004)

    Article  MathSciNet  Google Scholar 

  3. Anagnostopoulos C.E., Anagnostopoulos I.E., Psoroulas I.D., Loumos V., Kayafas E.: License plate recognition from still images and video sequences: a survey. IEEE Trans. Intell. Transp. Syst. 9(3), 377–391 (2008)

    Article  Google Scholar 

  4. Hoffman, C., Dang, T., Stiller, C.: Vehicle detection fusing 2d visual features, pp. 280–285. IEEE Intelligent Vehicles Symposium (2004)

  5. Betke M., Haritaoglu E., Davis L.S.: Real-time multiple vehicle detection and tracking from a moving vehicle. Mach. Vis. Appl. 12, 69–83 (2000)

    Article  Google Scholar 

  6. Santos, D., Correia, P.L.: Car Recognition Based on Back Lights and Rear View Features, pp. 137–140. Workshop on Image Analysis for Multimedia Interactive Services (2009)

  7. Wen, X., Zhao, H., Wang, N., Yuan, H.: A rear-vehicle detection system for static images based on monocular vision, pp. 1–4. International Conference Control, Automation, Robotics and Vision (2006)

  8. Li, X.Z., Zhang, G.M., Fang, J., Wu, J.A., Cui, Z.M.: Vehicle color recognition using vector matching of template, pp. 189–193. International Symposium Electronic Commerce and Security (2010)

  9. Kim, K.J., Park, S.M., Choi, Y.J.: Deciding the number of color histogram bins for vehicle color recognition, pp. 134–138. IEEE Conference Asia-Pacific Services Computing (2008)

  10. Zhao W., Chellappa R., Rosenfeld A., Phillpse P.J.: Face Recognition: A Literature Survey, pp. 399–458. ACM Computing Surveys, New York (2003)

    Google Scholar 

  11. Chellappa R., Sinha P., Phillips P.J.: Face recognition by computers and humans. IEEE J. Comput. Soc. 43(2), 46–55 (2010)

    Article  Google Scholar 

  12. Voit, M., Nickel, K., Stiefelhagen, R.: A bayesian approach for multi-view head pose estimation, pp. 31–34. International Conference Multi-sensor Fusion and Integration for Intelligent Systems (2006)

  13. Voit, M., Nickel, K., Stiefelhagen, R.: Multi-view head pose estimation using neural networks, pp. 347–352. Canadian Conference on Computer and Robot Vision (2005)

  14. Hou, T., Wang, S., Qin, H.: Vehicle matching and recognition under large variations of pose and illumination, pp. 24–29. International Conference Computer Vision and Pattern Recognition, June (2009)

  15. Lai, A.H.S., Fung, G.S.K., Yung, N.H.C.: Vehicle type classification from visual based dimension estimation, pp. 201–206. IEEE International System Conference (2001)

  16. Ozuysal, M., Lepetit, V., Fua, P.: Pose estimation for category specific multiview object localization, pp. 778–785. IEEE Conference on Computer Vision and Pattern Recognition (2009)

  17. Arie-Nachimson, M., Basri, R.: Constructing implicit 3D shape models for pose estimation, pp. 1341–1348. International Conference on Computer Vision (2009)

  18. Hutter, M., Brewer, N.: Matching 2-D ellipses to 3-D circles with application to vehicle pose identification, pp. 153–158. International Conference on Image and Vision Computing, New Zealand (2009)

  19. Prokaj, J., Medioni, G.: 3D model based vehicle recognition, pp. 1–7. Workshop on Applications of Computer Vision (2009)

  20. Guo Y., Hsu S., Sawhney H.S., Kumar R., Shan Y.: Robust object matching for persistent tracking with heterogeneous features. IEEE Trans. Pattern Anal. Mach. Intell. 29(5), 824–839 (2007)

    Article  Google Scholar 

  21. Kuehnle A.: Symmetry-based recognition of vehicle rears. Pattern Recogn. Lett. 12(4), 249–258 (1991)

    Article  Google Scholar 

  22. Zielke, T., Brauckmann, M., Seelen, W.V.: Intensity and Edge-based Symmetry Detection Applied to Car-following. Lecture Notes in Computer Science, vol. 588, pp. 865–873. Springer, Berlin (1992)

  23. Kim, D.S., Chien, S.I.: Automatic car license plate extraction using modified generalized symmetry transform and image warping, vol. 3, pp. 2022–2027. IEEE International Symposium on Industrial Electronics (2001)

  24. Kadow, U., Schneider, G., Vukotich, A.: Radar-vision based vehicle recognition with evolutionary optimized and boosted features, pp. 13–15. IEEE Intelligent Vehicles Symposium (2007)

  25. Chang, H.Y., Fu, C.M., Huang, C.L.: Real-time vision-based preceding vehicle tracking and recognition, pp. 514–519. IEEE Intelligent Vehicles Symposium (2005)

  26. Wan, S., Kodagoda, S., Sehestedt, S.: Multiple cue based vehicle detection and tracking for road safety, pp. 12–14. International Conference on Intelligent Technologies (2007)

  27. Cootes T.F., Taylor C.J., Cooper D.H., Graham J.: Active shape models—their training and application. Comput. Vis. Image Underst. 61(1), 38–59 (1995)

    Article  Google Scholar 

  28. Cootes T.F., Page G.J., Jackson C.B., Taylor C.J.: Statistical grey-level models for object location and identification. Image Vis. Comput. 14(8), 533–540 (1996)

    Article  Google Scholar 

  29. Liu S.C., Fu C.W., Chang S.: Statistical change detection with moment under time-varying illumination. IEEE Trans. Image Process. 7(9), 1258–1268 (1998)

    Article  Google Scholar 

  30. Zhang D.S., Lu G.: Segmentation of moving objects in image sequence: a review. Circuits Syst. Signal Process. 20(2), 143–183 (2001)

    Article  MATH  Google Scholar 

  31. Chien S.Y., Ma S.Y., Chen L.G.: Efficient moving object segmentation algorithm using background registration technique. IEEE Trans. Circuits Syst. Video Technol. 12(7), 577–586 (2002)

    Article  Google Scholar 

  32. Chen, B.S., Lei, Y.Q., Li, W.W.: A novel background model for real-time vehicle detection, vol. 2, pp. 1276–1279. IEEE International Conference Signal Processing (2004)

  33. Leotta, M.J., Mundy, J.L.: Predicting high resolution image edges with a generic, adaptive, 3-D vehicle model, pp. 1311–1318. International Conference on Computer Vision and Pattern Recognition (2009)

  34. Cootes T.F., Edwards G.J., Taylor C.J.: Active appearance models. IEEE Trans. Pattern Anal. Mach. Intell. 23(6), 681–685 (2001)

    Article  Google Scholar 

  35. Wolberg G.: Image morphing: a survey. Vis. Comput. 14, 360–372 (1998)

    Article  Google Scholar 

  36. Beier T., Neely S.: Feature-based image metamorphosis, pp. 35–42. SIGGRAPH (1992)

  37. Zhao, S., Gao, W., Shan, S., Yin, B.: Enhance the alignment accuracy of active shape models using elastic graph matching, pp. 52–58. International Conference on Biometric Authentication (2004)

  38. Zheng, Z.L., Yang, F.: Enhanced active shape model for facial feature localization. International Conference on Machine Learning and Cybernetics, vol. 5, pp. 2841–2845 (2008)

  39. Gu, H.Z., Kao, Y.W., Lee, S.Y., Yuan, S.M.: HVPN: the combination of horizontal and vertical pose normalization for face recognition, pp. 367–378. International Conference on Multimedia Modeling (2009)

  40. Brunelli R.: Template Matching Techniques in Computer Vision: Theory and Practice. Wiley, New York (2009)

    Book  Google Scholar 

  41. Dataset for car model recognition. http://www.cs.nctu.edu.tw/~hcku/

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Information Engineering, National Chiao Tung University, 1001 Ta Hsueh Rd., Hsinchu, 300, Taiwan

    Hui-Zhen Gu & Suh-Yin Lee

Authors
  1. Hui-Zhen Gu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Suh-Yin Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hui-Zhen Gu.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Gu, HZ., Lee, SY. Car model recognition by utilizing symmetric property to overcome severe pose variation. Machine Vision and Applications 24, 255–274 (2013). https://doi.org/10.1007/s00138-012-0414-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00138-012-0414-8

Keywords

Search

Navigation