Improving pedestrian detection using motion-guided filtering

[en] In this letter, we show how a simple motion-guided nonlinear filter can drastically improve the accuracy of several pedestrian detectors. More specifically, we address the problem of how to pre-filter an image so almost any pedestrian detector will see its false detection rate decrease. First, we roughly identify moving pixels by cumulating their temporal gradient into a motion history image (MHI). The MHI is then used in conjunction with a nonlinear filter to filter out background details while leaving untouched foreground moving objects. We also show how a feedback loop as well as a merging procedure between the filtered and the unfiltered frames can further improve results. We tested our method on 26 videos from 6 categories. The results show that for a given miss rate, filtering out background details reduces the false detection rate by a factor of up to 69.6 times. Our method is simple, computationally light, and can be implemented with any pedestrian detector. Code is made publicly available at: https://bitbucket.org/wany1601/pedestriandetection.

Disciplines :

Electrical & electronics engineering

Author, co-author :

Wang, Yi

Pierard, Sébastien ; Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications

Su, Song-Zhi

Jodoin, Pierre-Marc

Language :

English

Title :

Improving pedestrian detection using motion-guided filtering

Publication date :

01 September 2017

Journal title :

Pattern Recognition Letters

ISSN :

0167-8655

Publisher :

Elsevier Science

Special issue title :

Special Issue on Scene Background Modeling and Initialization

Volume :

Pages :

106-112

Peer reviewed :

Peer Reviewed verified by ORBi

Available on ORBi :

since 29 November 2016

Statistics

Number of views

106 (11 by ULiège)

Number of downloads

1 (1 by ULiège)

More statistics

Scopus citations^®

Scopus citations^®
without self-citations

OpenCitations

Bibliography

Benenson, R., Mathias, M., Timofte, R., Van Gool, L., Pedestrian detection at 100 frames per second. Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2012, 2903–2910.
Benfold, B., Reid, I., Stable multi-target tracking in real-time surveillance video. Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2011, 3457–3464.
Bernardin, K., Stiefelhagen, R., Evaluating multiple object tracking performance: the CLEAR MOT metrics. J. Image Video Process 2008 (2008), 1–10.
Breitenstein, M.D., Reichlin, F., Leibe, B., Koller-Meier, E., Van Gool, L., Online multiperson tracking-by-detection from a single, uncalibrated camera. IEEE Trans. Pattern Anal. Mach. Intell. 33 (2011), 1820–1833.
CaviarDataset, http://homepages.inf.ed.ac.uk/rbf/CAVIAR/, 2003.
Chen, G., Ding, Y., Xiao, J., Han, T., Detection evolution with multi-order contextual co-occurrence. Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2013, 1798–1805.
Dalal, N., Triggs, B., Histograms of oriented gradients for human detection. Proc. IEEE Conf. Comput. Vis. Pattern Recog., volume 1, 2005, 886–893.
Davis, J.W., Hierarchical motion history images for recognizing human motion. Proc. IEEE Workshop Detection and Recog. of Events in Video, 2001, 39–46.
Dollár, P., Appel, R., Belongie, S., Perona, P., Fast feature pyramids for object detection. IEEE Trans. Pattern Anal. Mach. Intell. 36 (2014), 1532–1545.
Fardi, B., Schuenert, U., Wanielik, G., Shape and motion-based pedestrian detection in infrared images: a multi sensor approach. IEEE Proc. Intell. Vehicles Symposium, 2005, 18–23.
Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D., Object detection with discriminatively trained part based models. IEEE Trans. Pattern Anal. Mach. Intell. 32 (2010), 1627–1645.
Fernández-Caballero, A., Castillo, J.C., Serrano-Cuerda, J., Maldonado-Bascón, S., Real-time human segmentation in infrared videos. Expert Syst. Appl. 38 (2011), 2577–2584.
Gall, J., Lempitsky, V., Class-specific hough forests for object detection. Decis. Forests for Comput. Vis. and Med. Image Anal., 2013, Springer, 143–157.
Guo, W., Xiao, Y., Zhang, G., Multi-scale pedestrian detection by use of adaboost learning algorithm. Int. Conf. Virtual Reality and Vis., 2014, 266–271.
Hou, Y.-L., Pang, G.K., People counting and human detection in a challenging situation. IEEE Trans. Syst., Man, Cybern. A 41 (2011), 24–33.
Lai, C.Q., Teoh, S.S., A review on pedestrian detection techniques based on histogram of oriented gradient feature. Proc. IEEE Conf. Res. and Development (SCOReD), 2014, 1–6.
Li, W.-T., Chang, H.-S., Lien, K.-C., Chang, H.-T., Wang, Y.-C.F., Exploring visual and motion saliency for automatic video object extraction. IEEE Trans. Image process. 22 (2013), 2600–2610.
Lin, C.-F., Chen, C.-S., Hwang, W.-J., Chen, C.-Y., Hwang, C.-H., Chang, C.-L., Novel outline features for pedestrian detection system with thermal images. Pattern Recog., 2015.
Liu, D., Wang, X., Song, J., A robust pedestrian detection based on corner tracking. Int. Conf. Inf. Sci. and Technol., 2015, 207–211.
Llorca, D.F., Parra, I., Quintero, R., Fernández, C., Izquierdo, R., Sotelo, M., Stereo-based pedestrian detection in crosswalks for pedestrian behavioural modelling assessment. Int. Conf. Inf. in Control, Automa. and Robot., 2014, 102–109.
Ouyang, W., Wang, X., A discriminative deep model for pedestrian detection with occlusion handling. Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2012, 3258–3265.
Ouyang, W., Wang, X., Single-pedestrian detection aided by multi-pedestrian detection. Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2013, 3198–3205.
Paisitkriangkrai, S., Shen, C., van den Hengel, A., Pedestrian detection with spatially pooled features and structured ensemble learning. IEEE Trans. Pattern Anal. Mach. Intell. 38 (2016), 1243–1257.
Sermanet, P., Kavukcuoglu, K., Chintala, S., LeCun, Y., Pedestrian detection with unsupervised multi-stage feature learning. Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2013, 3626–3633.
Tomè, D., Monti, F., Baroffio, L., Bondi, L., Tagliasacchi, M., Tubaro, S., Deep convolutional neural networks for pedestrian detection. Signal Process. Image Commun. 47 (2016), 482–489.
Wang, J., Fu, W., Liu, J., Lu, H., Spatiotemporal group context for pedestrian counting. IEEE Trans. Circuits and Syst. for Video Technol. 24 (2014), 1620–1630.
Wang, M., Li, W., Wang, X., Transferring a generic pedestrian detector towards specific scenes. Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2012, 3274–3281.
Wang, X., Wang, M., Li, W., Scene-specific pedestrian detection for static video surveillance. IEEE Trans. Pattern Anal. Mach. Intell. 36 (2014), 361–374.
Wang, Y., Jodoin, P.-M., Porikli, F., Konrad, J., Benezeth, Y., Ishwar, P., Cdnet 2014: an expanded change detection benchmark dataset. Proc. IEEE Conf. Comput. Vis. Pattern Recog. Workshops, 2014, 393–400.
Wang, Y., Piérard, S., Su, S.-Z., Jodoin, P.-M., Nonlinear background filter to improve pedestrian detection. International Conference on Image Analysis and Processing, 2015, 535–543.
Wu, J., Rehg, J.M., CENTRIST: A visual descriptor for scene categorization. IEEE Trans. Pattern Anal. Mach. Intell. 33 (2011), 1489–1501.
Xia, Y., Hu, R., Wang, Z., Lu, T., Moving foreground detection based on spatio-temporal saliency. Int. J. Comput. Sci. Issues 10 (2013), 79–84.
Zhang, S., Bauckhage, C., Cremers, A., Informed haar-like features improve pedestrian detection. Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2014, 947–954.
Zhao, X., He, Z., Zhang, S., Liang, D., Robust pedestrian detection in thermal infrared imagery using a shape distribution histogram feature and modified sparse representation classification. Pattern Recog. 48 (2015), 1947–1960.
Zitouni, M.S., Bhaskar, H., Al-Mualla, M., Robust background modeling and foreground detection using dynamic textures. Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, 2016, Rome, Italy, 403–410.