Combining static and dynamic features for real-time moving pedestrian detection
Article
First Online:
- 115 Downloads
Abstract
Pedestrian detecting and tracking are critical techniques in video monitoring. However, real-time pedestrian detection is still challenging in surveillance videos with complex background. In existing frameworks, feature extractions are usually time-consuming to achieve high detection accuracy. In this paper, we propose to combine sparse static and dynamic features to improve the feature extraction speed while keeping high detection accuracy. Firstly, the static sparse feature is extracted using a fast feature pyramid in each frame. Secondly, sparse optical flow is used to extract sparse dynamic feature among successive frames. Thirdly, we combine the two types of feature in the Adaboost classification. Experiments show that the average miss rate of our approach is 17%. The detection rate is up to 22 fps in a Matlab implementation. It shows that our approach achieves optimal detection accuracy compared to the state-of-the-art real-time pedestrian detection algorithms.
Keywords
Pedestrian detection Combined feature Sparse optical flowNotes
Acknowledgements
This research is partially supported by National Nature Science Foundation of China (61309009) and Natural Science Foundation of Hunan Province, China (14JJ2008).
References
- 1.Andriluka M, Roth S, Schiele B (2008) People-tracking-by-detection and people-detection-by-tracking. In: 2008 IEEE Conference on computer vision and pattern recognition, pp 1–8Google Scholar
- 2.Bin L, HSWZ (2010) Image quality assessment without references based on statistics of natural images. J Zhejiang Uni (industrial version) 44(2):248–252Google Scholar
- 3.Cao J, Pang Y, Li X (2016) Pedestrian detection inspired by appearance constancy and shape symmetry. In: 2016 IEEE Conference on computer vision and pattern recognition (CVPR), pp 1316–1324Google Scholar
- 4.Costea AD, Nedevschi S (2016) Semantic channels for fast pedestrian detection. In: 2016 IEEE Conference on computer vision and pattern recognition (CVPR), pp 2360–2368Google Scholar
- 5.Dollar P, Wojek C, Schiele B, Perona P (2012) Pedestrian detection: an evaluation of the state of the art. IEEE Trans Pattern Anal Mach Intell 34(4):743–761CrossRefGoogle Scholar
- 6.Dollr P, Appel R, Belongie S, Perona P (2014) Fast feature pyramids for object detection. IEEE Trans Pattern Anal Mach Intell 36(8):1532–1545CrossRefGoogle Scholar
- 7.Everingham M, Gool LV, Williams CKI, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis 88(2):303–338CrossRefGoogle Scholar
- 8.Ge W, Collins RT, Ruback RB (2012) Vision-based analysis of small groups in pedestrian crowds. IEEE Trans Pattern Anal Mach Intell 34(5):1003–1016CrossRefGoogle Scholar
- 9.Ghurye SG (1957) A characterization of the exponential function. Amer Math Month 64(4):255–257MathSciNetCrossRefGoogle Scholar
- 10.Hu R, Zhu X, Cheng D et al (2016) Graph self-representation method for unsupervised feature selection. Neurocomputing 220:130–137CrossRefGoogle Scholar
- 11.Kang W, Deng F (2007) Research on intelligent visual surveillance for public security. In: 6th IEEE/ACIS International conference on computer and information science (ICIS 2007), pp 824–829Google Scholar
- 12.Liang CW, Juang CF (2015) Moving object classification using a combination of static appearance features and spatial and temporal entropy values of optical flows. IEEE Trans Intell Transp Syst 16(6):3453–3464CrossRefGoogle Scholar
- 13.Lucas BD, Kanade T (1981) An iterative image registration technique with an application to stereo vision. In: International joint conference on artificial intelligence, pp 674–679Google Scholar
- 14.Ouyang W, Wang X (2013) Joint deep learning for pedestrian detection. In: 2013 IEEE International conference on computer vision, pp 2056–2063Google Scholar
- 15.Paisitkriangkrai S, Shen Cvd, Hengel A (2016) Pedestrian detection with spatially pooled features and structured ensemble learning. IEEE Trans Pattern Anal Mach Intell 38(6):1243–1257CrossRefGoogle Scholar
- 16.Ruderman DL, Bialek W (1994) Statistics of natural images: scaling in the woods. Phys Rev Lett 73(6):814–817CrossRefGoogle Scholar
- 17.Shi J, Tomasi C (1994) Good features to track. In: 1994 Proceedings of IEEE conference on computer vision and pattern recognition, pp 593–600Google Scholar
- 18.Solmaz B, Moore BE, Shah M (2012) Identifying behaviors in crowd scenes using stability analysis for dynamical systems. IEEE Trans Pattern Anal Mach Intell 34(10):2064–2070CrossRefGoogle Scholar
- 19.Walk S, Majer N, Schindler K, Schiele B (2010) New features and insights for pedestrian detection. In: 2010 IEEE Computer society conference on computer vision and pattern recognition, pp 1030–1037Google Scholar
- 20.Yang Y, Sundaramoorthi G (2015) Shape tracking with occlusions via coarse-to-fine region-based sobolev descent. IEEE Trans Pattern Anal Mach Intell 37(5):1053–1066CrossRefGoogle Scholar
- 21.Youssef SM, Hamza MA, Fayed AF (2010) Detection and tracking of multiple moving objects with occlusion in smart video surveillance systems. In: 2010 5th IEEE International conference intelligent systems, pp 120–125Google Scholar
- 22.Zhang C, Viola P (2007) Multiple-instance pruning for learning efficient cascade detectors. In: International conference on neural information processing systems, pp 1681–1688Google Scholar
- 23.Zhang S, Bauckhage C, Cremers AB (2014) Informed haar-like features improve pedestrian detection. In: 2014 IEEE Conference on computer vision and pattern recognition, pp 947–954Google Scholar
- 24.Zhang S, Benenson R, Schiele B (2015) Filtered channel features for pedestrian detection. In: 2015 IEEE Conference on computer vision and pattern recognition (CVPR), pp 1751–1760Google Scholar
- 25.Zhang S, Benenson R, Omran M, Hosang J, Schiele B (2016) How far are we from solving pedestrian detection? In: 2016 IEEE Conference on computer vision and pattern recognition (CVPR), pp 1259–1267Google Scholar
- 26.Zhu X, Suk HI, Wang L et al (2017) A novel relational regularization feature selection method for joint regression and classification in AD diagnosis. Med Image Anal 38:205–214CrossRefGoogle Scholar
Copyright information
© Springer Science+Business Media, LLC, part of Springer Nature 2018