A Shallow–Deep Feature Fusion Method for Pedestrian Detection
Source abstract
Abstract
In this paper, a shallow–deep feature fusion (SDFF) method is developed for pedestrian detection. Firstly, we propose a shallow feature-based method under the ACF framework of pedestrian detection. More precisely, improved Haar-like templates with Local FDA learning are used to filter the channel maps of ACF such that these Haar-like features are able to improve the discriminative power and therefore enhance the detection performance. The proposed shallow feature is also referred to as weighted subset-haar-like feature. It is efficient in pedestrian detection with a high recall rate and precise localization. Secondly, the proposed shallow feature-based detection method operates as a region proposal. A classifier equipped with ResNet is then used to refine the region proposals to judge whether each region contains a pedestrian or not. The extensive experiments evaluated on INRIA, Caltech, and TUD-Brussel datasets show that SDFF is an effective and efficient method for pedestrian detection.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Video Surveillance and Tracking Methods · Advanced Neural Network Applications · Anomaly Detection Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Intelligence Science, National University of Defense Technology, Changsha 410073, China
School of Automation, Southeast University, Nanjing 210096, China
School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, China
Funding
Macao S.A.R (FDCT)
References (59)
Show source-provided references
1. Hasan, I., Liao, S., Li, J., Akram, S.U., and Shao, L. (2021, January 21–24). Generalizable Pedestrian Detection: The Elephant in the Room. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR46437.2021.01117 ↗
2. Lima, J.P., Roberto, R., Figueiredo, L., Simoes, F., and Teichrieb, V. (2021, January 21–24). Generalizable Multi-Camera 3D Pedestrian Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Nashville, TN, USA.10.1109/CVPRW53098.2021.00135 ↗
3. Pedestrian detection: An evaluation of the state of the art10.1109/TPAMI.2011.155 ↗
4. Computer vision and deep learning techniques for pedestrian detection and tracking: A survey10.1016/j.neucom.2018.01.092 ↗
5. Dalal, N., and Triggs, B. (2005, January 20–25). Histograms of oriented gradients for human detection. Proceedings of the International Conference on Computer Vision & Pattern Recognition (CVPR’05), San Diego, CA, USA.
6. Felzenszwalb, P.F., McAllester, D.A., and Ramanan, D. (2008, January 23–28). A discriminatively trained, multiscale, deformable part model. Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA.10.1109/CVPR.2008.4587597 ↗
7. Zang, K., Shen, J., and Yang, W. (2017, January 22–23). Using LFDA to Learn Subset-Haar-Like Intermediate Feature Weights for Pedestrian Detection. Proceedings of the International Conference on Intelligent Science and Big Data Engineering, Dalian, China.10.1007/978-3-319-67777-4_19 ↗
8. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
9. Oren, M., Papageorgiou, C., Sinha, P., Osuna, E., and Poggio, T. (1997, January 17–19). Pedestrian detection using wavelet templates. Proceedings of the Computer Vision and Pattern Recognition, San Juan, PR, USA.
10. Viola, P., and Jones, M. (2001, January 8–14). Rapid object detection using a boosted cascade of simple features. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai, HI, USA.
11. Real-time moving pedestrian detection using contour features10.1007/s11042-018-6173-4 ↗
12. Zhu, Q., Yeh, M.C., Cheng, K.T., and Avidan, S. (2006, January 17–22). Fast human detection using a cascade of histograms of oriented gradients. Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’06), New York, NY, USA.
13. Wang, X., Han, T.X., and Yan, S. (October, January 29). An HOG-LBP human detector with partial occlusion handling. Proceedings of the 2009 IEEE 12th International Conference on Computer Vision, Kyoto, Japan.10.1109/ICCV.2009.5459207 ↗
14. Bourdev, L., and Malik, J. (October, January 29). Poselets: Body part detectors trained using 3d human pose annotations. Proceedings of the 2009 IEEE 12th International Conference on Computer Vision, Kyoto, Japan.10.1109/ICCV.2009.5459303 ↗
15. Object detection with discriminatively trained part-based models10.1109/TPAMI.2009.167 ↗
16. Dollár, P., Tu, Z., Perona, P., and Belongie, S. (2009, January 7–10). Integral Channel Features. Proceedings of the British Machine Conference, London, UK.10.5244/C.23.91 ↗
17. Filtered channel features for pedestrian detection
18. Nam, W., Dollár, P., and Han, J.H. (2014, January 8–13). Local decorrelation for improved pedestrian detection. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada.
19. A novel pixel neighborhood differential statistic feature for pedestrian and face detection10.1016/j.patcog.2016.09.010 ↗
20. An extended filtered channel framework for pedestrian detection10.1109/TITS.2018.2807199 ↗
21. Ouyang, W., Zeng, X., and Wang, X. (2013, January 23–28). Modeling mutual visibility relationship in pedestrian detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA.10.1109/CVPR.2013.414 ↗
22. Daniel Costea, A., and Nedevschi, S. (2016, January 27–30). Semantic channels for fast pedestrian detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.259 ↗
23. Filtered shallow-deep feature channels for pedestrian detection10.1016/j.neucom.2017.03.007 ↗
24. Park, D., Zitnick, C.L., Ramanan, D., and Dollár, P. (2013, January 23–28). Exploring weak stabilization for motion feature extraction. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA.10.1109/CVPR.2013.371 ↗
25. Cheng, M.M., Zhang, Z., Lin, W.Y., and Torr, P. (2014, January 23–28). BING: Binarized normed gradients for objectness estimation at 300fps. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.414 ↗
26. Zitnick, C.L., and Dollár, P. (2014, January 6–12). Edge boxes: Locating object proposals from edges. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland.10.1007/978-3-319-10602-1_26 ↗
27. Segmentation as selective search for object recognition
28. Measuring the objectness of image windows10.1109/TPAMI.2012.28 ↗
29. CPMC: Automatic object segmentation using constrained parametric min-cuts10.1109/TPAMI.2011.231 ↗
30. Girshick, R. (2015, January 7–13). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.169 ↗
31. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23–28). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.81 ↗
32. Backpropagation applied to handwritten zip code recognition10.1162/neco.1989.1.4.541 ↗
33. Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3–6). Imagenet classification with deep convolutional neural networks. Proceedings of the Advances in Neural Information Processing Systems, Lake Tahoe, Nevada.
34. Deep learning10.1038/nature14539 ↗
35. Ren, S., He, K., Girshick, R., and Sun, J. (2015, January 7–12). Faster r-cnn: Towards real-time object detection with region proposal networks. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada.
36. Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., and Pietikäinen, M. (2018). Deep learning for generic object detection: A survey. arXiv.10.1007/s11263-019-01247-4 ↗
37. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 11–14). Ssd: Single shot multibox detector. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_2 ↗
38. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
39. Cheng, B., Wei, Y., Shi, H., Feris, R.S., Xiong, J., and Huang, T.S. (2018, January 8–14). Revisiting RCNN: On Awakening the Classification Power of Faster RCNN. Proceedings of the European Conference on Computer Vision, Munich, Germany.10.1007/978-3-030-01267-0_28 ↗
40. Zhang, L., Lin, L., Liang, X., and He, K. (2016, January 11–14). Is faster r-cnn doing well for pedestrian detection?. Proceedings of the European Conference on Computer Visio, Amsterdam, The Netherlands.10.1007/978-3-319-46475-6_28 ↗
41. Cai, Z., Fan, Q., Feris, R.S., and Vasconcelos, N. (2016, January 11–14). A unified multi-scale deep convolutional neural network for fast object detection. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46493-0_22 ↗
42. Liu, S., and Huang, D. (2018, January 8–14). Receptive field block net for accurate and fast object detection. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01252-6_24 ↗
43. Dimensionality reduction of multimodal labeled data by local fisher discriminant analysis
44. Eigenfaces vs. fisherfaces: Recognition using class specific linear projection10.1109/34.598228 ↗
45. Srivastava, R.K., Greff, K., and Schmidhuber, J. (2015, January 7–12). Training very deep networks. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada.
46. Zhang, S., Benenson, R., Omran, M., Hosang, J., and Schiele, B. (2016, January 11–14). How far are we from solving pedestrian detection?. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Amsterdam, The Netherlands.10.1109/CVPR.2016.141 ↗
47. (2021, September 30). INRIA Person Dataset. Available online: http://pascal.inrialpes.fr/data/human/.
48. (2021, September 30). Caltech Pedestrian Detection Benchmark. Available online: http://www.vision.caltech.edu/Image_Datasets/CaltechPedestrians/.
49. Wojek, C., Walk, S., and Schiele, B. (2009, January 20–25). Multi-cue onboard pedestrian detection. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.10.1109/CVPR.2009.5206638 ↗
50. (2021, September 30). Piotr’s Computer Vision Matlab Toolbox. Available online: http://pdollar.github.io/toolbox/.
51. Fast Feature Pyramids for Object Detection10.1109/TPAMI.2014.2300479 ↗
52. Zhang, S., Bauckhage, C., and Cremers, A.B. (2014, January 23–28). Informed Haar-Like Features Improve Pedestrian Detection. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.126 ↗
53. Mathias, M., Benenson, R., Timofte, R., and Gool, L.V. (2013, January 1–8). Handling Occlusions with Franken-Classifiers. Proceedings of the 2013 IEEE International Conference on Computer Vision, Sydney, Australia.10.1109/ICCV.2013.190 ↗
54. Lim, J.J., Zitnick, C.L., and Dollár, P. (2013, January 1–8). Sketch Tokens: A Learned Mid-level Representation for Contour and Object Detection. Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, Sydney, Australia.10.1109/CVPR.2013.406 ↗
55. Pedestrian Detection with Spatially Pooled Features and Structured Ensemble Learning10.1109/TPAMI.2015.2474388 ↗
56. Jointly Learning Deep Features, Deformable Parts, Occlusion and Classification for Pedestrian Detection10.1109/TPAMI.2017.2738645 ↗
57. Yang, B., Yan, J., Lei, Z., and Li, S.Z. (2015, January 7–13). Convolutional Channel Features. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.10.1109/ICCV.2015.18 ↗
58. Tian, Y., Luo, P., Wang, X., and Tang, X. (2015, January 7–13). Pedestrian detection aided by deep learning semantic tasks. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Santiago, Chile.10.1109/CVPR.2015.7299143 ↗
59. Walk, S., Majer, N., Schindler, K., and Schiele, B. (2010, January 13–18). New features and insights for pedestrian detection. Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA.10.1109/CVPR.2010.5540102 ↗