Title
Multiple Pedestrian Tracking Using Colour and Motion Models
Abstract
This paper presents a method that combines colour and motion information to track pedestrians in video sequences captured by a fixed camera. Pedestrians are firstly detected using the human detector proposed by Dalal and Triggs which involves computing the histogram of oriented gradients descriptors and classification using a linear support vector machine. For the colour-based model, we extract a 4-dimensional colour histogram for each detected pedestrian window and compare these colour histograms between consecutive video frames using the Bhattacharyya coefficient. For the motion model, we use a Kalman filter which recursively predicts and updates the estimates of the positions of pedestrians in the video frames. We evaluate our tracking method using videos from two pedestrian video datasets from the web. Our experimental results show that our tracking method outperforms one that uses only colour information and can handle partial occlusion.
Year
DOI
Venue
2010
10.1109/DICTA.2010.63
DICTA
Keywords
Field
DocType
motion model,human detector,video signal processing,kalman filter,kalman filters,world wide web,motion information,linear support vector machine,colour histogram,pedestrian detection,4-dimensional colour histogram extraction,colour information,histogram of oriented gradients descriptor,4-dimensional colour histogram,multiple pedestrian tracking,motion models,consecutive video frame,tracking method,colour model,position estimation,pedestrian tracking,image sequences,pedestrian video datasets,object detection,bhattacharyya coefficient,oriented gradients descriptor,video frame,image colour analysis,video sequence,colour-based model,4 dimensional,pixel,histograms,detectors,color,support vector machine
Computer vision,Object detection,Histogram,Bhattacharyya distance,Pattern recognition,Computer science,Support vector machine,Kalman filter,Histogram of oriented gradients,Pixel,Artificial intelligence,Pedestrian detection
Conference
ISBN
Citations 
PageRank 
978-0-7695-4271-3
6
0.63
References 
Authors
13
5
Name
Order
Citations
PageRank
Zhengqiang Jiang160.63
Du Q. Huynh231221.77
William Moran360.63
Subhash Challa425224.96
Nick Spadaccini5299.14