Abstract
A real-time pedestrian detection and tracking system using a single video camera was developed to monitor pedestrians. This system contained six modules: video flow capture, pre-processing, movement detection, shadow removal, tracking, and object classification. The Gaussian mixture model was utilized to extract the moving object from an image sequence segmented by the mean-shift technique in the pre-processing module. Shadow removal was used to alleviate the negative impact of the shadow to the detected objects. A model-free method was adopted to identify pedestrians. The maximum and minimum integration methods were developed to integrate multiple cues into the mean-shift algorithm and the initial tracking iteration with the competent integrated probability distribution map for object tracking. A simple but effective algorithm was proposed to handle full occlusion cases. The system was tested using real traffic videos from different sites. The results of the test confirm that the system is reliable and has an overall accuracy of over 85%.
Similar content being viewed by others
References
HUGHES R, HUANG H, ZEGGEER C, CYNECKI M. Automated pedestrian detection used in conjunction with standard pedestrian push buttons at signalized intersections [J]. Transportation Research Record, 2000, 1705: 32–39.
COTTRELL W D, PAL D. Evaluation of pedestrian data needs and collection efforts [J]. Transportation Research Record, 2003, 1828: 12–19.
COIFMAN B, BEYMER D, MCLAUCHLAN P, MALIK J. A real-time computer vision system for vehicle tracking and traffic surveillance [J]. Transportation Research: Part C, 1998, 6(4): 71–288.
Image sensing systems inc. Applications of autoscope [EB/OL]. [2011-07-06]. http://autoscope.com/applications/.
ZHANG X, FORSHAW M R B. A parallel algorithm to extract information about the motion of road traffic using image analysis [J]. Transportation Research: Part C, 1997, 5(2): 141–152.
LIU X, XU X, DAI B. Vision-based long-distance lane perception and front vehicle location for full autonomous vehicles on highway roads [J]. Journal of Central South University, 2012, 19(5): 1454–1465.
KILAMBI P, RIBNICK E, JOSHI A J, MASOUD O, PAPANIKOLOPOULOS N. Estimating pedestrian counts in groups [J]. Computer Vision and Image Understanding, 2008, 110(1): 43–59.
LI J, SHAO C F, XU W T, LI J. A real-time system for tracking and classification of pedestrian and bicycles [J]. Transportation Research Record, 2010, 2198: 83–92.
MALINOVSKIY Y, ZHENG J Y, WANG Y H. Simple and model-free algorithm for real-time pedestrian detection and tracking [C]// The 86th Annual Meeting of the Transportation Research Board. Washington, D.C.: TRB, 2007.
Li Q, SHAO C F, YUE H. Real-time foreground-background segmentation based on improved codebook model [C]// Image and Signal Processing (CISP). Yantai, China: IEEE Press, 2010, 1: 269–273.
CHRISTODOULOU L, KASPARIS T, MARQUES O. Advanced statistical and adaptive threshold techniques for moving object detection and segmentation [C]// Digital Signal Processing (DSP). Corfu: IEEE Press, 2011: 1–6.
CHEN Y, CHEN C, HUANG C, HUNG Y. Efficient hierarchical method for background subtraction [J]. Pattern Recognition, 2007(40): 2706–2715.
PARUCHURI J K, SATHIYAMOORTHY E P, CHEUNG S S, CHEN C H. Spatially adaptive illumination modeling for background subtraction [C]// IEEE Computer Vision workshops. Kentucky, USA: IEEE Press, 2011: 1745–1752.
ZAHARESCU A, JAMIESON M. Multi-scale multi-feature codebook-based background subtraction [C]// IEEE Computer Vision Workshops, ON, Canada: IEEE Press, 2011: 1753–1760
KIM K, THANARAT H C, HARWOOD D, DAVIS L. Real-time foreground-background segmentation using codebook model [J]. Real-Time Imaging, 2005, 11(3): 172–185.
STAUFFER C, GRIMSON W E L. Adaptive background mixture models for real-time tracking [C]// Computer Vision and Pattern Recognition. Fort Collins, Colorado: IEEE Press, 1999: 246–252.
LI Z D, WANG W H, WANG Y, CHENG F, WANG Y. Visual tracking by proto-objects [J]. Pattern Recognition, 2013, 46(8): 2187–2201.
PAPADOURAKIS V, ARGYROS A. Multiple objects tracking in the presence of long-term occlusions [J]. Computer Vision and Image Understanding, 2010, 114(7): 835–846.
FU Z X, HAN Y. Centroid weighted Kalman filter for visual object tracking [J]. Measurement, 2012, 45(4): 650–655.
MEUTER M, IURGEL U, PARK S B, KUMMERT A. The unscented Kalman filter for pedestrian tracking from a moving host [C]// IEEE Intelligent Vehicles Symposium. Eindhoven, Holland: IEEE Press, 2008: 37–42.
RATSCH M, BLUMER C, VETTER T, TESCHKE G. Efficient object tracking by condentional and cascaded image sensing [J]. Computer Standards and Interfaces, 2012, 34(6): 549–557.
HU Z T, PAN Q, YANG F, CHENG Y M. An improved particle filtering algorithm based on observation inversion optimal sampling [J]. Journal of Central South University of Technology, 2009, 16(5): 815–820.
HOTTA K. Adaptive weighting of local classifiers by particle filters for robust tracking [J]. Pattern Recognition, 2009, 42(5): 619–628.
YAO A B, LIN X G, WANG G J, YU S. A compact association of particle filtering and kernel based object tracking [J]. Pattern Recognition, 2012, 45(7): 2584–2597.
WANG Z W, YANG X K, YI X, YU S Y. CamShift guided particle filter for visual tracking [J]. Pattern Recognition Letters, 2009, 30(4): 407–413.
LIU H, YU Z, ZHA H B, ZOU Y X, ZHANG L. Robust human tracking based on multi-cue integration and mean-shift [J]. Pattern Recognition Letters, 2009, 30(9): 827–837.
COLLINS R T. Mean-shift blob tracking through scale space [C]// IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Pittsburgh, USA: IEEE Press, 2003, 2: 234–240.
ZHANG Z X, HUANG K Q, WANG Y H, LI M. View independent object classification by exploring scene consistency information for traffic scene surveillance [J]. Neurocomputing, 2013, 99(1): 250–260.
OWENS J, HUNTER A, FLETCHER E. A fast model-free morphology-based object tracking algorithm [C]// British Machine Vision Conference. Cardiff, UK, 2002: 767–776.
COMANICIU D, MEER P. Mean-shift a robust approach toward feature space analysis [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24: 603–619.
CUCCHIARA R, GRANA C, PICCARDI M, PRATI A, SIROTTI S. Improving shadow suppression in moving object detection with HSV color information [C]// IEEE Intelligent Transportation Systems Conference. Oakland, CA: IEEE Press, 2001: 334–339.
COMANICIU D, RAMESH V, MEER P. Real-time tracking of non-rigid objects using mean shift [C]// IEEE Computer Vision Pattern Recognition. Hilton Head Island, SC: IEEE Press, 2000, 2: 142–149.
Author information
Authors and Affiliations
Corresponding author
Additional information
Foundation item: Project(50778015) supported by the National Natural Science Foundation of China; Project(2012CB725403) supported by the Major State Basic Research Development Program of China
Rights and permissions
About this article
Cite this article
Li, Q., Shao, Cf. & Zhao, Y. A robust system for real-time pedestrian detection and tracking. J. Cent. South Univ. 21, 1643–1653 (2014). https://doi.org/10.1007/s11771-014-2106-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11771-014-2106-1