Tracking moving objects in surveillance video

Doctoral thesis English OPEN
Dunne, Peter John
  • Subject: H200

The thesis looks at approaches to the detection and tracking of potential objects of interest in surveillance video. The aim was to investigate and develop methods that might be suitable for eventual application through embedded software, running on a fixed-point processor, in analytics capable cameras.\ud \ud The work considers common approaches to object detection and representation, seeking out those that offer the necessary computational economy and the potential to be able to cope with constraints such as low frame rate due to possible limited processor time, or weak chromatic content that can occur in some typical surveillance contexts.\ud \ud The aim is for probabilistic tracking of objects rather than simple concatenation of frame by frame detections. This involves using recursive Bayesian estimation. The particle filter is a technique for implementing such a recursion and so it is examined in the context of both single target and combined multi-target tracking.\ud \ud A detailed examination of the operation of the single target tracking particle filter shows that objects can be tracked successfully using a relatively simple structured grey-scale histogram representation. It is shown that basic components of the particle filter can be simplified without loss in tracking quality. An analysis brings out the relationships between commonly used target representation distance measures and shows that in the context of the particle filter there is little to choose between them. With the correct choice of parameters, the simplest and computationally economic distance measure performs well. The work shows how to make that correct choice. Similarly, it is shown that a simple measurement likelihood function can be used in place of the more ubiquitous Gaussian.\ud \ud The important step of target state estimation is examined. The standard weighted mean approach is rejected, a recently proposed maximum a posteriori approach is shown to be not suitable in the context of the work, and a practical alternative is developed. \ud \ud Two methods are presented for tracker initialization. One of them is a simplification of an existing published method, the other is a novel approach. The aim is to detect trackable objects as they enter the scene, extract trackable features, then actively follow those features through subsequent frames. The multi-target tracking problem is then posed as one of management of multiple independent trackers.
  • References (82)
    82 references, page 1 of 9

    [1] Chipwrights, "Programmable Visual Signal Processors",

    [2] E. Maggio, M. Taj, and A. Cavallaro, "Efficient Multi-Target Visual Tracking using Random Finite Sets", IEEE Transactions on Systems and Circuits for Video Technology, 2008, pp1016-1027.

    [3] A. Bugeau and P. Peréz, "Track and Cut: Simultaneous Tracking and Segmentation of Multiple Objects with Track Cuts", EURASIP Journal on Advances in Signal Processing, 2008, pp1-14.

    [4] Z. Zhang, P. L. Venetianer, and A. J. Lipton, "A Robust Human Detection and Tracking System using a Human-Model-Based Camera Calibration", 8th International Workshop on Visual Surveillance, 2008,

    [5] R. Girisha and S. Murali, "Segmentation of Motion Objects from Surveillance Video Sequences using Partial Correlation", 6th IEEE International Conference on Image Processing, 2009,

    [6] T. Ko, S. Soatto, and D. Estrin, "Background Subtraction on Distributions", 10th European Conference on Computer Vision, 2008, pp276-289.

    [7] F. Porikli, "Integral Histogram: A Fast Way to extract Histograms in Cartesian Spaces", IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, pp829-836.

    [8] Home Office Scientific Development Branch, "i-LIDS Dataset for AVSS 2007 Sequence: AVSS pv medium", 2007,

    [9] P. Dunne and B. J. Matuszewski, "Choice of Similarity Measure, Likelihood Function and Parameters for Histogram-based Particle Filter Tracking in CCTV Grey Scale Video", Image and Vision Computing, 2011, pp178-189.

    [10] S. Arulampalam, S. Maskell, N. Gordon, and T. Clapp, "A Tutorial on Particle Filters for On-Line NonLinear/Non-Gaussian Bayesian Tracking", IEEE Transactions on Signal Processing, 2002, pp174-188.

  • Metrics
    views in OpenAIRE
    views in local repository
    downloads in local repository

    The information is available from the following content providers:

    From Number Of Views Number Of Downloads
    Central Lancashire Online Knowledge - IRUS-UK 0 298
Share - Bookmark