| Title | Multi-target Tracking Using on-line Viterbi Optimisation and Stochastic Modelling |
| Authors | Håkan Ardö |
| Full-text | Available as PDF |
| Year | 2009 |
| Pages | 171 |
| Document type | Thesis |
| Language | eng |
| Publisher | Centre for Mathematical Sciences |
| Abstract English | To study and compare the safety of intersection, traffic scientists today typically manually monitor the intersection<br> during several days and count how often certain events such as evasive manoeuvres occur. This is a<br> laboursome and costly procedure. The aim of this thesis is to provide tools that can reduce the amount of manual<br> labour required by using automated video analytics. Two methods for creating for such tools are presented.<br> <br> The first method is a probabilistic background foreground segmentation that for each block of pixels calculate the<br> probability that this block currently views the static background or some moving foreground object. This is done<br> by deriving the probability distribution of the normalised cross correlation in the background and the foreground<br> case respectively. The background distribution depends on the amount of structure in the block.<br> <br> The second method is a multi-target tracker that uses the probabilistic background foreground segmentation to<br> produce the trajectories of all objects in the scene. It operates online but with a few seconds delay in order to<br> incorporate information from both past and future frames when deciding on the current state. This means that the<br> output is guaranteed to be consistent, i.e. no jumping between different hypothesis, and the respect constrains<br> placed on the system such as "objects may not occupy the same space at the same time" or "objects may only<br> appear at the border of the image".<br> <br> The methods have been tested both on synthetic and numerous sets of real data by implementing applications such<br> as people counting, loitering detection and traffic surveillance. The applications have been shown to perform very<br> well as long as the scene studied is not too large. |
| ISBN/ISSN/Other | ISSN: 1404-0034 ISBN: 978-628-7685-2 |
Questions: webmaster
Last update: 2013-04-11
Centre for Mathematical Sciences, Box 118, SE-22100, Lund. Telefon: +46 46-222 00 00 (vx)