Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Detecting partially occluded vehicles with geometric and likelihood reasoning

© The Institution of Engineering and Technology
Received 18/12/2013, Accepted 30/05/2014, Revised 29/04/2014, Published 25/06/2014

In real-world scenes, vehicles are frequently overlapped by other objects and various backgrounds. In this study, an effective method to detect such vehicles, especially those partially occluded by nearby vehicles or other objects is presented. The authors have developed a statistical approach to generate occlusion hypothesis and a new hypothesis verification method. To verify occlusion hypothesis, the verification method utilises geometric and likelihood information. In this way, both vehicle–background and vehicle–vehicle occlusions can be detected. No additional occlusion-specific training is required. In addition, a median filter is applied to eliminate the noise in the patch scoring, and a union-find algorithm is used to find the connected positive region in the binary map. A synthesised occlusion dataset is created to test the performance, and the experimental results on popular benchmarks indicate that the proposed method is effective and robust in recognising partially occluded vehicles.

Inspec keywords: traffic engineering computing; geometry; median filters; vehicles; visual databases; image denoising; statistical analysis; object detection

Other keywords: statistical approach; occlusion hypothesis; median fllter; geometric reasoning; occlusion dataset synthesis; real-world scenes; hypothesis veriflcation method; likelihood reasoning; vehicle-background occlusions; vehicle-vehicle occlusions; union-flnd algorithm; partially occluded vehicle detection; binary map; positive region; patch scoring; noise elimination

Subjects: Combinatorial mathematics; Other topics in statistics; Optical, image and video signal processing; Traffic engineering computing; Combinatorial mathematics; Computer vision and image processing techniques; Filtering methods in signal processing; Other topics in statistics; Spatial and pictorial databases

References

    1. 1)
      • 20. Ohn-Bar, E., Sivaraman, S., Trivedi, M.: ‘Partially occluded vehicle recognition and tracking in 3d’. 2013 IEEE Intelligent Vehicles Symp. (IV), June 2013, pp. 1350–1355.
    2. 2)
      • 5. Barinova, O., Lempitsky, V., Kohli, P.: ‘On detection of multiple object instances using hough transforms’. IEEE Conf. Computer Vision and Pattern Recognition, 2010, pp. 2233–2240.
    3. 3)
    4. 4)
    5. 5)
      • 16. Tang, S., Andriluka, M., Schiele, B.: ‘Detection and tracking of occluded people’. British Machine Vision Conf., 2012, pp. 1–11.
    6. 6)
      • 21. Wang, X., Han, T.X., Yan, S.: ‘An HOG-LBP human detector with partial occlusion handling’. IEEE 12th Int. Conf. Computer Vision, 2009, pp. 32–39.
    7. 7)
      • 19. Feris, R., Petterson, J., Siddiquie, B., Brown, L., Pankanti, S.: ‘Large-scale vehicle detection in challenging urban surveillance environments’. 2011 IEEE Workshop Applications of Computer Vision (WACV), January 2011, pp. 527–533.
    8. 8)
    9. 9)
      • 15. Felzenszwalb, P.F., Girshick, R.B., McAllester, D.: ‘Cascade object detection with deformable part models’. IEEE Conf. Computer Vision and Pattern Recognition, 2010, pp. 2241–2248.
    10. 10)
      • 9. Gall, J., Lempitsky, V.: ‘Class-specific Hough forests for object detection’. IEEE Conf. Computer Vision and Pattern Recognition, 2009, pp. 1022–1029.
    11. 11)
      • 12. Weber, M., Welling, M., Perona, P.: ‘Towards automatic discovery of object categories’. IEEE Conf. Computer Vision and Pattern Recognition, 2000, vol. 2, pp. 101–108.
    12. 12)
    13. 13)
      • 7. Okada, R.: ‘Discriminative generalized Hough transform for object dectection’. IEEE 12th Int. Conf. Computer Vision, 2009, pp. 2000–2005.
    14. 14)
      • 11. Fergus, R., Perona, P., Zisserman, A.: ‘Object class recognition by unsupervised scaleinvariant learning’. 2003 IEEE Computer Society Conf. Computer Vision and Pattern Recognition, 2003, vol. 2, pp. II-264.
    15. 15)
    16. 16)
    17. 17)
    18. 18)
      • 22. Kenneth, L.: ‘A method for the solution of certain non-linear problems in least squares’, Q. Appl. Math., 1944, 2, (2), pp. 164–168.
    19. 19)
      • 6. Razavi, N., Gall, J., Kohli, P., Van Gool, L.: ‘Latent Hough transform for object detection’. European Conf. Computer Vision, Springer, 2012, pp. 312–325.
    20. 20)
      • 26. Wu, B., Nevatia, R.: ‘Cluster boosted tree classifier for multi-view, multi-pose object detection’. IEEE 11th Int. Conf.Computer Vision, 2007, pp. 1–8.
    21. 21)
      • 17. Leibe, B., Leonardis, A., Schiele, B.: ‘Combined object categorization and segmentation with an implicit shape model’. Workshop on Statistical Learning in Computer Vision, ECCV, 2004, vol. 2, no. 5, p. 7.
    22. 22)
      • 18. Dalal, N., Triggs, B.: ‘Histograms of oriented gradients for human detection’. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, 2005, vol. 1, pp. 886–893.
    23. 23)
    24. 24)
      • 8. Maji, S., Malik, J.: ‘Object detection using a max-margin Hough transform’. IEEE Conf. Computer Vision and Pattern Recognition, 2009, pp. 1038–1045.
    25. 25)
    26. 26)
      • 25. Mutch, J., Lowe, D.G.: ‘Multiclass object recognition with sparse, localized features’. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, 2006, vol. 1, pp. 11–18.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2013.0334
Loading

Related content

content/journals/10.1049/iet-cvi.2013.0334
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address