Advertisement

Neural Computing and Applications

, Volume 31, Issue 4, pp 1189–1200 | Cite as

Adaptive pedestrian detection by predicting classifier

  • Song Tang
  • Mao YeEmail author
  • Pei Xu
  • Xudong Li
Original Article
  • 153 Downloads

Abstract

Generally the performance of a pedestrian detector will decrease rapidly, when it is trained on a fixed training set but applied to specific scenes. The reason is that in the training set only a few samples are useful for the specific scenes while other samples may disturb the accurate detections. Traditional methods solve this problem by transfer learning which suffer the problem of keeping source samples or artificially labeling a few samples in the detection phase. In this paper, we propose a new method to bypass these defects by predicting pedestrian classifier for each sample in the detection phase. A classifier regression model is trained in the source domain in which each sample has a proprietary classifier. In the detection phase, a pedestrian classifier is predicted for each candidate window in an image. Thus, for the samples in the target domain, the pedestrian classifiers are different. Our main contributions are: (1) a new adaptive detector without keeping source samples or labeling a few new target samples; (2) a new dimensionality reduction method for classifier vector which simultaneously ensures the performance of both reconstruction and classification; (3) a two-stage regression neural model which can handle the high-dimensional regression problem effectively. Experiments prove that our method can achieve the state-of-the-art results on two pedestrian datasets.

Keywords

Adaptive pedestrian detection Exemplar classifier Regression model 

Notes

Acknowledgements

This work was supported in part by the National Natural Science Foundation of China (61375038) and Applied Basic Research Programs of Sichuan Science and Technology Department (2016JY0088).

Compliance with ethical standards

Conflict of interest

We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work, there is no professional or other personal interest of any nature or kind in any product, service and/or company that could be construed as influencing the position presented in, or the review of, the manuscript entitled, Adaptive Pedestrian Detection by Predicting Classifier.

References

  1. 1.
    Andriluka M, Roth S, Schiele B (2009) Pictorial structures revisited: people detection and articulated pose estimation. In: Conference on computer vision and pattern recognition (CVPR), pp 1014–1021Google Scholar
  2. 2.
    Caseiro R, Henriques JF, Martins P, Batista J (2015) Beyond the shortest path: unsupervised domain adaptation by sampling subspaces along the spline flow. In: Conference on computer vision and pattern recognition (CVPR), pp 3846–3854Google Scholar
  3. 3.
    Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Conference on computer vision and pattern recognition (CVPR), pp 886–893Google Scholar
  4. 4.
    Dollár P, Appel R, Belongie S, Perona P (2014) Fast feature pyramids for object detection. TIEEE Tran Pattern Anal Mach Intell (PAMI) 36(8):1532–1545CrossRefGoogle Scholar
  5. 5.
    Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis (IJCV) 88(2):303–338CrossRefGoogle Scholar
  6. 6.
    Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D (2010) Object detection with discriminatively trained part-based models. TIEEE Trans Pattern Anal Mach Intell (PAMI) 32(9):1627–1645CrossRefGoogle Scholar
  7. 7.
    Gall J, Lempitsky V (2013) Class-specific hough forests for object detection. In: Conference on computer vision and pattern recognition (CVPR), pp 143–157Google Scholar
  8. 8.
    Girshick R, Donahue J, Darrell T, Malik, J (2014a) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Conference on computer vision and pattern recognition (CVPR), pp 580–587Google Scholar
  9. 9.
    Girshick R, Donahue J, Darrell T, Malik J (2014b) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Conference on computer vision and pattern recognition (CVPR), pp 580–587Google Scholar
  10. 10.
    Gong B, Shi Y, Sha F, Grauman K (2012) Geodesic flow kernel for unsupervised domain adaptation. In: Conference on computer vision and pattern recognition (CVPR), pp 2066–2073Google Scholar
  11. 11.
    Gopalan R, Li R, Chellappa R (2011) Domain adaptation for object recognition: an unsupervised approach. In: International conference on computer vision (ICCV), pp 999–1006Google Scholar
  12. 12.
    Gould S, Fulton R, Koller, D (2009) Decomposing a scene into geometric and semantically consistent regions. In: International Conference on computer vision (ICCV), pp 1–8Google Scholar
  13. 13.
    He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: International conference on computer vision (ICCV)Google Scholar
  14. 14.
    Jiang W, Zavesky E, Chang SF, Loui A (2008) Cross-domain learning methods for high-level visual concept classification. In: International conference on image processing (ICIP), pp 161–164Google Scholar
  15. 15.
    Kate S, Brian K, Mario F, Trevor D (2010) Adapting visual category models to new domains. In: European conference on computer vision (ECCV), pp 213–226Google Scholar
  16. 16.
    Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems (NIPS), pp 1097–1105Google Scholar
  17. 17.
    Li X, Ye M, Fu M, Xu P, Li T (2015) Domain adaption of vehicle detector based on convolutional neural networks. IJCAS 13(4):1020–1031Google Scholar
  18. 18.
    Malisiewicz T, Gupta A, Efros A et al. (2011) Ensemble of exemplar-svms for object detection and beyond. In: International conference on computer vision (ICCV), pp 89–96Google Scholar
  19. 19.
    Nair V, Clark JJ (2004) An unsupervised, online learning framework for moving object detection. In: Conference on computer vision and pattern recognition (CVPR), pp 317–324Google Scholar
  20. 20.
    Oren M, Papageorgiou C, Sinha P, Osuna E, Poggio T (1997) Pedestrian detection using wavelet templates. In: Conference on computer vision and pattern recognition (CVPR), pp 193–99Google Scholar
  21. 21.
    Overett G, Petersson L, Brewer N, Andersso, L, Pettersson N (2008) A new pedestrian dataset for supervised learning. In: IVS, pp 373–378Google Scholar
  22. 22.
    Pang J, Huang Q, Yan S, Jiang S, Qin L (2011) Transferring boosted detectors towards viewpoint and scene adaptiveness. IEEE Trans Image Process (TIP) 20(5):1388–1400MathSciNetCrossRefzbMATHGoogle Scholar
  23. 23.
    Schulter S, Leistner C, Wohlhart P, Roth PM, Bischof H (2014) Accurate object detection with joint classification-regression random forests. In: Conference on computer vision and pattern recognition (CVPR), pp 923–930Google Scholar
  24. 24.
    Sermanet P, Kavukcuoglu K, Chintala S, LeCun Y (2013) Pedestrian detection with unsupervised multi-stage feature learning. In: Conference on computer vision and pattern recognition (CVPR), pp 3626–3633Google Scholar
  25. 25.
    Sun Y, Wang X, Tang X (2013) Deep convolutional network cascade for facial point detection. In: Conference on computer vision and pattern recognition (CVPR), pp 3476–3483Google Scholar
  26. 26.
    Tian Y, Luo P, Wang X, Tang X (2015) Pedestrian detection aided by deep learning semantic tasks. In: Conference on computer vision and pattern recognition (CVPR), pp 5079–5087Google Scholar
  27. 27.
    Wang M, Li W, Wang X (2012) Transferring a generic pedestrian detector towards specific scenes. In: Conference on computer vision and pattern recognition (CVPR), pp 3274–3281Google Scholar
  28. 28.
    Wang M, Wang X (2011) Automatic adaptation of a generic pedestrian detector to a specific traffic scene. In: Conference on computer vision and pattern recognition (CVPR), pp 3401–3408Google Scholar
  29. 29.
    Wang X, Wang M, Li W (2014) Scene-specific pedestrian detection for static video surveillance. TIEEE Trans Pattern Anal Mach Intell (PAMI) 36(2):361–374MathSciNetCrossRefGoogle Scholar
  30. 30.
    Wu Y, Wang L, Cui F, Zhai H, Dong B, Wang JY (2016) Cross-model convolutional neural network for multiple modality data representation. Neural Comput Appl. doi: 10.1007/s00521-016-2824-4 Google Scholar
  31. 31.
    Yang J, Yan R, Hauptmann AG (2007) Cross-domain video concept detection using adaptive svms. In: ACM international conference on multimedia (ACMM), pp 188–197Google Scholar
  32. 32.
    Yin Z, Kong D, Shao G, Ning X, Jin W, Wang JY (2016) A-optimal convolutional neural network. Neural Comput Appl. doi: 10.1007/s00521-016-2783-9 Google Scholar
  33. 33.
    Zeng X, Ouyang W, Wang M, Wang X (2014) Deep learning of scene-specific classifier for pedestrian detection. In: European conference on computer vision (ECCV), pp 472–487Google Scholar
  34. 34.
    Zeng X, Ouyang W, Wang X (2013) Multi-stage contextual deep learning for pedestrian detection. In: International conference on computer vision (ICCV), pp 121–128Google Scholar
  35. 35.
    Zhang H, Cao X, Ho JK, Chow TW (2017) Object-level video advertising: an optimization framework. IEEE Trans Ind Inform 13(2):520–531CrossRefGoogle Scholar
  36. 36.
    Zhang H, Li J, Ji Y, Yue H (2017) Understanding subtitles by character-level sequence-to-sequence learning. IEEE Trans Ind Inform 13(2):616–624CrossRefGoogle Scholar

Copyright information

© The Natural Computing Applications Forum 2017

Authors and Affiliations

  1. 1.School of Computer Science and Engineering, Center for Robotics, Key Laboratory for NeuroInformation of Ministry of EducationUniversity of Electronic Science and Technology of ChinaChengduPeople’s Republic of China

Personalised recommendations