Abstract
A pedestrian tracking algorithm is proposed in this paper which combines color and edge features in particle filter framework to resolve the pedestrian tracking problem in the video set. The color feature tracking work well when the object has low object deformation, scale variation and some rotation, while the edge feature is robust to the target with similar color to its background. In the paper, color histogram (HC) and four direction features (FDF) of the tracking objects is utilized, and experiments demonstrate that pedestrian tracking with multiple features fusion have a good performance even when objects are occluded by other human bodies, shelters or have low discrimination to background.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Fen, X., Ming, G.: Pedestrian Tracking Using Particle Filter Algorithm. In: International Conference on Electrical and Control Engineering, pp. 1478–1481 (2010)
Geronimo, D., Lopez, A., Angel, D.: Survey of Pedestrian Detection for Advanced Driver Assistance Systems. IEEE Transactions on Pattern Analysis and Machine Intelligence 32(7), 1239–1258 (2010)
Collins, R., Liu, Y., Leordeanu, M.: Online Selection of Discriminative Tracking Features. IEEE Transactions on Pattern Analysis and Machine Intelligence 27(10), 1631–1643 (2005)
Nummiaro, K., Meier, E., Gool, L.: An Adaptive Color-based Particle Filter. Image and Vision Computing 21(1), 99–110 (2003)
Xu, F., Gao, M.: Human Detection and Tracking based on HOG and Particle Filter. In: 3rd International Congress on Image and Signal Processing, pp. 1740–1743 (2011)
Niknejad, H., Takahashi, K., Mita, S., McAllester, D.: Embedded Multi-sensors Objects Detection and Tracking for Urban Autonomous Driving. In: IEEE Intelligent Vehicles Symposium, pp. 1128–1135 (2011)
Han, H., Ye, Q., Jiao, J.: Combined Feature Evaluation for Adaptive Visual Object Tracking. Computer Vision and Image Understanding 115(1), 69–80 (2011)
Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based Object Tracking. IEEE Transaction on Pattern Analysis and Machine Intelligence 25(5), 564–577 (2003)
Lin, J.: Divergence Measures Based on the Shannon Entropy. IEEE Transaction Information Theory 25(5), 3–10 (2000)
Chong, Y., Li, Q., Kuang, H.: Two-stage Pedestrian Detection Based on Multiple Features and Machine Learning. ACTA Automatica Sinica 38(3), 375–381 (2012)
Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 886–893 (2005)
VIVIDTrackingEvaluation, http://vision.cse.psu.edu/data/vividEval/datasets/datasets.html
CAVIARTestCaseScenarios, http://groups.inf.ed.ac.uk/vision/CAVIAR/CAVIARDATA1/
SDL Data Set, http://coe.gucas.ac.cn/SDL-HomePage/resource.asp
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chong, Y., Chen, R., Li, Q., Zheng, CH. (2012). Particle Filter Based on Multiple Cues Fusion for Pedestrian Tracking. In: Huang, DS., Gupta, P., Zhang, X., Premaratne, P. (eds) Emerging Intelligent Computing Technology and Applications. ICIC 2012. Communications in Computer and Information Science, vol 304. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-31837-5_47
Download citation
DOI: https://doi.org/10.1007/978-3-642-31837-5_47
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-31836-8
Online ISBN: 978-3-642-31837-5
eBook Packages: Computer ScienceComputer Science (R0)