Pushing the Limits of Deep CNNs for Pedestrian Detection

IEEE Transactions on Circuits and Systems for Video Technology

Volumn 28, Issue 6, 2018, Pages 1358-1368

  Hu, Qichang ^a,b   Wang, Peng ^a   Shen, Chunhua ^a,c   Van Den Hengel, Anton ^a,c   Porikli, Fatih ^b  

^a UNIVERSITY OF ADELAIDE   (Australia)

^b CSIRO   (Australia)

^c AUSTRALIAN CENTRE FOR ROBOTIC VISION   (Australia)

Author keywords

Convolutional feature map (CFM); ensemble model; pedestrian detection

Indexed keywords

CONVOLUTION; NEURAL NETWORKS;

CONVOLUTIONAL NEURAL NETWORK; DETECTION PERFORMANCE; ENSEMBLE MODELING; FEATURE MAP; OCCLUSION HANDLING; PEDESTRIAN DETECTION; STATE OF THE ART; STATE-OF-THE-ART APPROACH;

FEATURE EXTRACTION;

EID: 85048216257     PISSN: 10518215     EISSN: None     Source Type: Journal    
DOI: 10.1109/TCSVT.2017.2648850     Document Type: Article

References (50)

1. S. Branson, G. Van Horn, S. Belongie, and P. Perona, "Bird species categorization using pose normalized deep convolutional nets," in Proc. Brit. Conf. Mach. Vis., 2014, pp. 1-14.
2. Z. Cai, M. Saberian, and N. Vasconcelos, "Learning complexity-aware cascades for deep pedestrian detection," in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Dec. 2015, pp. 3361-3369.
3. L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille, "Semantic image segmentation with deep convolutional nets and fully connected CRFs," in Proc. Int. Conf. Learn. Represent., 2015, pp. 1-14.
4. X. Chen et al., "3D object proposals for accurate object class detection," in Proc. Adv. Neural Inf. Process. Syst., 2015, pp. 424-432.
5. M. Cordts et al., "The cityscapes dataset," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops, 2015, pp. 1-4.
6. N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection," in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2005, pp. 886-893.
7. A. Demiriz, K. Bennett, and J. Shawe-Taylor, "Linear programming boosting via column generation," Mach. Learn., vol. 46, nos. 1-3, pp. 225-254, 2002.
8. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, "ImageNet: A large-scale hierarchical image database," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2009, pp. 248-255.
9. P. Dollär, R. Appel, S. Belongie, and P. Perona, "Fast feature pyramids for object detection," IEEE Trans. Pattern Anal. Mach. Intell., vol. 36, no. 8, pp. 1532-1545, Aug. 2014.
10. P. Dollár, C. Wojek, B. Schiele, and P. Perona, "Pedestrian detection: An evaluation of the state of the art," IEEE Trans. Pattern Anal. Mach. Intell., vol. 34, no. 4, pp. 743-761, Apr. 2012.
11. M. Enzweiler, A. Eigenstetter, B. Schiele, and D. M. Gavrila, "Multi-cue pedestrian classification with partial occlusion handling," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2010, pp. 990-997.
12. P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan, "Object detection with discriminatively trained part-based models," IEEE Trans. Pattern Anal. Mach. Intell., vol. 32, no. 9, pp. 1627-1645, Sep. 2010.
13. S. Fidler, R. Mottaghi, A. Yuille, and R. Urtasun, "Bottom-up segmentation for top-down detection," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2013, pp. 3294-3301.
14. R. E. Schapire, "A brief introduction to boosting," in Proc. Int. Joint Conf. Arti. Intell., vol. 2. Aug. 1999, pp. 1401-1406.
15. A. Geiger, P. Lenz, and R. Urtasun, "Are we ready for autonomous driving? The KITTI vision benchmark suite," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2012, pp. 3354-3361.
16. R. Girshick, "Fast R-CNN," in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Dec. 2015, pp. 1440-1448.
17. R. Girshick, J. Donahue, T. Darrell, and J. Malik, "Rich feature hierarchies for accurate object detection and semantic segmentation," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2014, pp. 580-587.
18. R. Girshick, F. Iandola, T. Darrell, and J. Malik, "Deformable part models are convolutional neural networks," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2015, pp. 437-446.
19. B. Hariharan, P. Arbeláez, R. Girshick, and J. Malik, "Simultaneous detection and segmentation," in Proc. Eur. Conf. Comput. Vis., Sep. 2014, pp. 297-312.
20. B. Hariharan, P. Arbeláez, R. Girshick, and J. Malik, "Hypercolumns for object segmentation and fine-grained localization," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2015, pp. 447-456.
21. J. Franklin, "The elements of statistical learning: Data mining, inference and prediction," Math. Intell., vol. 27, no. 2, pp. 83-85, 2005.
22. J. Hosang, M. Omran, R. Benenson, and B. Schiele, "Taking a deeper look at pedestrians," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2015, pp. 4073-4082.
23. P. Krähenbühl and V. Koltun, "Efficient inference in fully connected CRFs with Gaussian edge potentials," in Proc. Adv. Neural Inf. Process. Syst., 2011, pp. 109-117.
24. A. Krizhevsky and G. Hinton, "Learning multiple layers of features from tiny images," Dept. Comput. Sci., Univ. Toronto, Toronto, ON, Canada, Tech. Rep., 2009.
25. A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," in Proc. Adv. Neural Inf. Process. Syst., 2012, pp. 1097-1105.
26. L.-J. Li, H. Su, Y. Lim, and L. Fei-Fei, "Object bank: An object-level image representation for high-level visual recognition," Int. J. Comput. Vis., vol. 107, no. 1, pp. 20-39, Mar. 2014.
27. G. Lin, C. Shen, A. van dan Hengel, and I. Reid. (Apr. 2015). "Efficient piecewise training of deep structured models for semantic segmentation." [Online]. Available: https://arxiv.org/abs/1504.01013
28. L. Lin, X. Wang, W. Yang, and J.-H. Lai, "Discriminatively trained And-Or graph models for object shape detection," IEEE Trans. Pattern Anal. Mach. Intell., vol. 37, no. 5, pp. 959-972, May 2015.
29. J. Long, E. Shelhamer, and T. Darrell, "Fully convolutional networks for semantic segmentation," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2015, pp. 3431-3440.
30. P. Luo, Y. Tian, X. Wang, and X. Tang, "Switchable deep network for pedestrian detection," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2014, pp. 899-906.
31. M. Mathias, R. Benenson, R. Timofte, and L. Van Gool, "Handling occlusions with franken-classifiers," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Dec. 2013, pp. 1505-1512.
32. W. Nam, P. Dollár, and J. H. Han, "Local decorrelation for improved pedestrian detection," in Proc. Adv. Neural Inf. Process. Syst., Dec. 2014, pp. 424-432.
33. W. Ouyang and X. Wang, "A discriminative deep model for pedestrian detection with occlusion handling," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2012, pp. 3258-3265.
34. W. Ouyang and X. Wang, "Joint deep learning for pedestrian detection," in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Dec. 2013, pp. 2056-2063.
35. W. Ouyang and X. Wang, "Single-pedestrian detection aided by multi-pedestrian detection," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2013, pp. 3198-3205.
36. S. Paisitkriangkrai, C. Shen, and A. van den Hengel, "Pedestrian detection with spatially pooled features and structured ensemble learning," IEEE Trans. Pattern Anal. Mach. Intell., vol. 38, no. 6, pp. 1243-1257, Jun. 2015.
37. S. Paisitkriangkrai, C. Shen, and A. van den Hengel, "Strengthening the effectiveness of pedestrian detection with spatially pooled features," in Proc. Eur. Conf. Comput. Vis., Sep. 2014, pp. 546-561.
38. S. Ren, K. He, R. Girshick, X. Zhang, and J. Sun. (Apr. 2015). "Object detection networks on convolutional feature maps." [Online]. Available: https://arxiv.org/abs/1504.06066
39. E. Shechtman and M. Irani, "Matching local self-similarities across images and videos," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2007, pp. 1-8.
40. K. Simonyan and A. Zisserman, "Two-stream convolutional networks for action recognition in videos," in Proc. Adv. Neural Inf. Process. Syst., 2014, pp. 568-576.
41. K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," in Proc. Int. Conf. Learn. Represent., 2015, pp. 1-14.
42. C. Szegedy et al., "Going deeper with convolutions," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2015, pp. 1-9.
43. S. Tang, M. Andriluka, and B. Schiele, "Detection and tracking of occluded people," Int. J. Comput. Vis., vol. 110, no. 1, pp. 58-69, Oct. 2014.
44. Y. Tian, P. Luo, X. Wang, and X. Tang, "Deep learning strong parts for pedestrian detection," in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Dec. 2015, pp. 1904-1912.
45. J. J. Tompson, A. Jain, Y. LeCun, and C. Bregler, "Joint training of a convolutional network and a graphical model for human pose estimation," in Proc. Adv. Neural Inf. Process. Syst., 2014, pp. 1799-1807.
46. X. Wang, M. Yang, S. Zhu, and Y. Lin, "Regionlets for generic object detection," in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Dec. 2013, pp. 17-24.
47. J. Yan, Y. Yu, X. Zhu, Z. Lei, and S. Z. Li, "Object detection by labeling superpixels," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2015, pp. 5107-5116.
48. B. Yang, J. Yan, Z. Lei, and S. Z. Li, "Convolutional channel features," in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Dec. 2015, pp. 82-90.
49. S. Zhang, R. Benenson, and B. Schiele, "Filtered channel features for pedestrian detection," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2015, pp. 1751-1760.
50. S. Zheng et al. (Feb. 2015). "Conditional random fields as recurrent neural networks." [Online]. Available: https://arxiv.org/abs/1502.03240