access icon free Detection of partially occluded pedestrians by an enhanced cascade detector

Pedestrian detection occupies a vital status in the field of computer vision because of its important applications such as intelligent surveillance system, intelligent transport system, robotics and automotive safety. To improve the algorithm performance for pedestrian detection, and especially to cope with the partial occlusion problem, a novel pedestrian detection framework is presented based on the improved adaptive boosting (Adaboost) algorithm and enhanced cascade detector output. There are three major contributions. First, aiming to solve the drawbacks of the conventional Adaboost method, a modified Adaboost algorithm is proposed for more accurate detecting pedestrian. Second, a simple yet effective way is proposed, called local area marking map (LAMM), to decide whether the partial occlusion occurs in a detection window. At last, in order to handle the partial occlusion problem, an enhanced cascade scheme is derived from the LAMM information. Additionally, the histograms of oriented gradients features are combined with the proposed framework. The authors validate the significant improvements of the proposed method by extensive experiments testing on Institut National de Recherche en Informatique et en Automatique (INRIA), Daimler, by performance evaluation of tracking and by surveillance 2001 (PETS'2001) datasets with comparisons to several state-of-the-art methods.

Inspec keywords: learning (artificial intelligence); pedestrians; object detection; traffic engineering computing; computer vision

Other keywords: computer vision; automotive safety; histograms of oriented gradients; local area marking map; Adaboost method; intelligent transport system; cascade detector enhancement; adaptive boosting algorithm; LAMM; Adaboost algorithm; robotics; intelligent surveillance system; partially occluded pedestrian detection

Subjects: Optical, image and video signal processing; Traffic engineering computing; Computer vision and image processing techniques; Knowledge engineering techniques

References

    1. 1)
      • 32. ‘PETS'2001 datasets’, http://www.cvg.rdg.ac.uk/slides/pets.html, accessed March 2012.
    2. 2)
    3. 3)
      • 4. Leibe, B., Seemann, E., Schiele, B.: ‘Pedestrian detection in crowded scenes’. Proc. Computer Vision and Pattern Recognition, San Diego, USA, June2005, pp. 878885.
    4. 4)
      • 25. Viola, P., Jones, M., Snow, D.: ‘Detecting pedestrians using patterns of motion and appearance’. Proc. Ninth IEEE Int. Conf. Computer Vision, Nice, France, October2003, pp. 734741.
    5. 5)
      • 10. Lienhart, R., Maydt, J.: ‘An extended set of Haar-like features for rapid object detection’. Proc. Int. Conf. Image Processing, New York, USA, September 2002, pp. 900903.
    6. 6)
    7. 7)
      • 6. Junior, J.C.S.J., Musse, S.R., Jung, C.R.: ‘Crowd analysis using computer vision techniques’, IEEE Signal Process. Mag., 2010, 27, (5), pp. 6677.
    8. 8)
      • 12. Felzenszwalb, P.F.: ‘Learning models for object recognition’. Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, Kauai, USA, December 2001, pp. 5662.
    9. 9)
      • 20. Enzweiler, M., Eigenstetter, A., Schiele, B., Gavrila, D.M.: ‘Multi-cue pedestrian classification with partial occlusion handling’. Proc. Computer Vision and Pattern Recognition, San Francisco, USA, June2010, pp. 990997.
    10. 10)
      • 9. Haga, T., Sumi, K., Yagi, Y.: ‘Human detection in outdoor scene using spatio-temporal motion analysis’. Proc. Int. Conf. Pattern Recognition, Cambridge, UK, August 2004, pp. 331334.
    11. 11)
      • 21. Walk, S., Schindler, K., Schiele, B.: ‘Disparity statistics for pedestrian detection: combining appearance, motion and stereo’. Proc. ECCV, Crete, Greece, September 2010, pp. 182195.
    12. 12)
    13. 13)
      • 5. Viola, P., Jones, M.J., Snow, D.: ‘Detecting pedestrians using patterns of motion and appearance’. IEEE Int. Conf. Computer Vision, Nice, France, October 2003, pp. 734741.
    14. 14)
    15. 15)
      • 29. Servedio, R.A.: ‘Smooth boosting and learning with malicious noise’, J. Mach. Learn. Res., 2003, 4, pp. 633648.
    16. 16)
      • 18. Wu, B., Nevatia, R.: ‘Tracking of multiple, partially occluded humans based on static body part detection’. Proc. Computer Vision and Pattern Recognition, New York, USA, June 2006, pp. 951958.
    17. 17)
      • 34. Li, W., Ni, H.: ‘An improved Adaboost training algorithm’, J. Jlilin Univ. (Sci. Edn), 2011, 49, (3), pp. 498504.
    18. 18)
      • 32. PETS'2001 datasets’, http://www.cvg.rdg.ac.uk/slides/pets.html, accessedMarch2012.
    19. 19)
      • 24. Cheng, H., Zheng, N., Qin, J.: ‘Pedestrian detection using sparse Gabor filter and support vector machine’. Proc. IEEE Intelligence Vehicle Symp., Las Vegas, USA, June2005, pp. 583587.
    20. 20)
      • 30. Domingo, C., Watanabe, O.: ‘Madaboost: a modified version of Adaboost’. Proc. Thirteenth Annual Conf. Computational Learning Theory, San Francisco, USA, 2000, pp. 180189.
    21. 21)
      • 27. Angelova, A., Abu-Mostafam, Y., Perona, P.: ‘Pruning training sets for learning of object categories’. Proc. ComputerVisionandPatternRecognition, San Diego, USA, June2005, pp. 494501.
    22. 22)
    23. 23)
    24. 24)
    25. 25)
      • 14. Beleznai, C., Bischof, H.: ‘Fast human detection in crowded scenes by contour integration and local shape estimation’. Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, Miami, USA, June 2009, pp. 22462253.
    26. 26)
      • 26. Lai, S., Liu, Y., Zhang, M., Theobald, B.-J.: ‘REBoost: probabilistic resampling for boosted pedestrian detection’, Opt. Eng., 2011, 50, (12), p. 127203.
    27. 27)
      • 16. Dalal, N., Triggs, B.: ‘Histograms of oriented gradients for human detection’. Proc. Computer Vision and Pattern Recognition, San Diego, USA, June2005, pp. 886893.
    28. 28)
      • 1. Xu, Y.W., Cao, X.B., Qiao, H.: ‘An efficient tree classifier ensemblebasedapproach for pedestrian detection’, IEEE Trans. Syst., Man, Cybern. B, Cybern., 2010, 41, (1), pp. 107117.
    29. 29)
    30. 30)
      • 22. Freund, Y., Schapire, R.E.: ‘A decision-theoretic generalization of on-line learning and an application to boosting’. Proc. Second European Conf. Computational Learning Theory, Barcelona, Spain, March 1995, pp. 2337.
    31. 31)
      • 19. Micilotta, A., Ong, E., Bowden, R.: ‘Detection and tracking of humans by probabilistic body part assembly’. British Machine Vision Conf., Oxford, UK, September 2005, pp. 429438.
    32. 32)
    33. 33)
    34. 34)
      • 33. Laptev, I.: ‘Improvements of object detection using boosted histograms’. Proc. BMVC, Edinburgh, England, 2006.
    35. 35)
      • 17. Wang, X., Han, T., Yan, S.: ‘A HOG-LBP human detector with partial occlusion handling’. Proc. ICCV, Kyoto, Japan, 2009, pp. 3239.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its.2012.0173
Loading

Related content

content/journals/10.1049/iet-its.2012.0173
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading