One of the main challenges in pedestrian classification is partial occlusion. This study presents a new method for pedestrian classification with partial occlusion handling. The proposed method involves a set of part-based classifiers trained on histogram of oriented gradients features derived from non-occluded pedestrian data set. The score of each part classifier is then employed to weight features used to train a second stage full-body classifier. The full-body classifier based on local weighted linear kernel support vector machine is trained using both non-occluded and artificially generated partial occlusion pedestrian dataset. The new kernel allows to significantly focus on the non-occluded parts and reduce the impact of the occluded ones. Experimental results on real-world dataset, with both partially occluded and non-occluded data, show high performance of the proposed method compared with other state-of-the-art methods.

References

1. 1)
  - 8. Nguyen, D.T., Li, W., Ogunbona, P.O.: ‘Inter-occlusion reasoning for human detection based on variational mean field’, Neurocomputing, 2013, 110, (13), pp. 51–61 (doi: 10.1016/j.neucom.2012.12.009).
2. 2)
  - 7. Conde, C., Moctezuma, D., Diego, I.M.D., Cabello, E.: ‘Hogg: Gabor and hog-based human detection for surveillance in non-controlled environments’, Neurocomputing, 2013, 100, (16), pp. 19–30 (doi: 10.1016/j.neucom.2011.12.037).
3. 3)
  - 21. Dollar, P., Belongie, P.r.S., Perona, P.: ‘The fastest pedestrian detector in the west’. BMVC 2010, Aberystwyth, UK.
4. 4)
  - 12. Lin, Z., Davis, L., Doermann, D., DeMenthon, D.: ‘Hierarchical part-template matching for human detection and segmentation’. IEEE 11th Int. Conf. on Computer Vision (ICCV), 2007, pp. 1–8.
5. 5)
  - 13. Wu, B., Nevatia, R.: ‘Tracking of multiple, partially occluded humans based on static body part detection’. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 2006, vol. 1, pp. 951–958.
6. 6)
  - M. Enzweiler , D.M. Gavrila . Monocular pedestrian detection: survey and experiments. IEEE Trans. Pattern Anal. Mach. Intell. , 12 , 2179 - 2195
7. 7)
  - 14. Shu, G., Dehghan, A., Oreifej, O., Hand, E., Shah, M.: ‘Part-based multiple person tracking with partial occlusion handling’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2012, pp. 1815–1821.
8. 8)
  - 19. Xu, G., Wu, X., Liu, L., Wu, Z.: ‘Real-time pedestrian detection based on edge factor and histogram of oriented gradient’. IEEE Int. Conf. on Information and Automation (ICIA), 2011, pp. 384–389.
9. 9)
  - P. Dollár , C. Wojek , B. Schiele , P. Perona . Pedestrian detection: an evaluation of the state of the art. IEEE Trans. Pattern Anal. Mach. Intell. , 4 , 743 - 761
10. 10)
  - 31. Lin, H.-T., Lin, C.-J., Weng, R.C.: ‘A note on platt's probabilistic outputs for support vector machines’, Mach. Learn., 2007, 68, (3), pp. 267–276 (doi: 10.1007/s10994-007-5018-6).
11. 11)
  - 17. Lian, G., Lai, J., Yuan, Y.: ‘Fast pedestrian detection using a modified wld detector in salient region’. Int. Conf. on System Science and Engineering (ICSSE), 2011, pp. 564–569.
12. 12)
  - 35. Platt, J.: ‘Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods’, Adv. Large Margin Classifiers, 1999, 10, (3), pp. 61–74.
13. 13)
  - 16. Chen, Z., Xu, T., Han, Z.: ‘Occluded face recognition based on the improved svm and block weighted LBP’. IEEE Int. Conf. on Image Analysis and Signal Processing (IASP), 2011, pp. 118–122.
14. 14)
  - 28. Vedaldi, A., Gulshan, V., Varma, M., Zisserman, A.: ‘Multiple kernels for object detection’. IEEE 12th Int. Conf. on Computer Vision, 2009, pp. 606–613.
15. 15)
  - D.M. Gavrila , S. Munder . Multi-cue pedestrian detection and tracking from a moving vehicle. Int. J. Comput. Vis. , 1 , 41 - 59
16. 16)
  - 7. Ran, X., Jianbin, J., Baochang, Z., Qixiang, Y.: ‘Pedestrian detection in images via cascaded L1-norm minimization learning method’, Pattern Recognit., 2012, 45, (7), pp. 2573–2583 (doi: 10.1016/j.patcog.2012.01.004).
17. 17)
  - 30. Jia, H., Martinez, A.M.: ‘Support vector machines in face recognition with occlusions’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2009, pp. 136–141.
18. 18)
  - 9. Ali, I., Dailey, M.N.: ‘Multiple human tracking in high-density crowds’, Image Vis. Comput., 2012, 30, (12), pp. 966–977 (doi: 10.1016/j.imavis.2012.08.013).
19. 19)
  - T. Gandhi , M.M. Trivedi . Pedestrian protection systems: issues, survey, and challenges. IEEE Trans. Intell. Transp. Syst. , 3 , 413 - 430
20. 20)
  - P.F. Felzenszwalb , R.B. Girshick , D. McAllester , D. Ramanan . Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. , 9 , 1627 - 1645
21. 21)
  - 26. Wu, B., Nevatia, R.: ‘Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors’. 10th IEEE Int. Conf. on Computer Vision (ICCV) 2005, 2005, vol. 1, pp. 90–97.
22. 22)
  - 18. Pang, Y., Yuan, Y., Li, X., Pan, J.: ‘Efficient hog human detection’, Signal Process., 2011, 91, (4), pp. 773–781 (doi: 10.1016/j.sigpro.2010.08.010).
23. 23)
  - 27. Ouyang, W., Wang, X.: ‘A discriminative deep model for pedestrian detection with occlusion handling’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2012, pp. 3258–3265.
24. 24)
  - 36. Dalal, N., Triggs, B.: ‘Histograms of oriented gradients for human detection’. IEEEConf. on Computer Vision and Pattern Recognition, IEEE Computer Society, 2005, vol. 1, pp. 886–893.
25. 25)
  - 23. Maji, S., Berg, A.C., Malik, J.: ‘Classification using intersection kernel support vector machines is efficient’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2008, pp. 1–8.
26. 26)
  - 6. AntAnez, E., Marfil, R., Bandera, J.P., Bandera, A.: ‘Part-based object detection into a hierarchy of image segmentations combining color and topology’, Pattern Recognit. Lett., 2013, 34, (7), pp. 744–753 (doi: 10.1016/j.patrec.2013.01.012).
27. 27)
  - K. Hotta . Robust face recognition under partial occlusion based on support vector machine with local Gaussian summation kernel. Image Vis. Comput. , 11 , 1490 - 1498
28. 28)
  - 1. Li, B., Yao, Q., Wang, K.: ‘A review on vision-based pedestrian detection in intelligent transportation systems’. Ninth IEEE Int. Conf. on Networking, Sensing and Control (ICNSC). 2012, pp. 393–398.
29. 29)
  - 20. Xu, Y., Cao, X., Qiao, H.: ‘An efficient tree classifier ensemble-based approach for pedestrian detection’, IEEE Trans. Syst. Man Cybern. B Cybern., 2011, 41, (1), pp. 107–117.
30. 30)
  - 10. Yu, C., Wang, X.: ‘Pedestrian detection based on combinational holistic and partial features’. Int. Conf. on Machine Learning and Cybernetics (ICMLC), 2011, vol. 4, pp. 1938–1942.
31. 31)
  - D. Gerónimo , A.M. López , A.D. Sappa , T. Graf . Survey of pedestrian detection for advanced driver assistance systems. IEEE Trans. Pattern Anal. Mach. Intell. , 7 , 1239 - 1258
32. 32)
  - 34. Shawe-Taylor, J., Cristianini, N.: ‘Kernel methods for pattern analysis’ (Cambridge University Press, 2004).
33. 33)
  - 25. Enzweiler, M., Eigenstetter, A., Schiele, B., Gavrila, D.M.: ‘Multi-cue pedestrian classification with partial occlusion handling’. 2010 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2010, pp. 990–997.
34. 34)
  - 32. Hotta, K.: ‘Local normalized linear summation kernel for fast and robust recognition’, Pattern Recognit., 2010, 43, (3), pp. 906–913 (doi: 10.1016/j.patcog.2009.09.009).
35. 35)
  - 29. Zhu, L., Chen, Y., Yuille, A., Freeman, W.: ‘Latent hierarchical structural learning for object detection’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2010, pp. 1062–1069.
36. 36)
  - 24. Wang, X., Han, T.X., Yan, S.: ‘An HOG-LBPhuman detector with partial occlusion handling’. IEEE 12th Int. Conf. on Computer Vision, 2009, pp. 32–39.

Partially occluded pedestrian classification using histogram of oriented gradients and local weighted linear kernel support vector machine

References

Related content