Contour Based Object Tracking
Tracking of objects and simultaneously identifying an accurate outline of the tracked object is a complicated computer vision problem to solve because of the changing nature of the high-dimensional image information. Prior information is often included into models, such as probability distribution functions on a prior definition of shape to alleviate potential problems due to e.g. ambiguity as to what should actually be tracked in the image data. However supervised learning and or training is not always possible for new unseen objects or unforeseen configurations of shape, e.g. for silhouettes of 3-D objects. We are therefore interested and are currently investigating ways to include high-level shape information into active contour based tracking frameworks without a supervised pre-processing stage.
Example results - tracking a hand with increasing amount of image noise
 |  |  |  |
 |  |  |  |
Example results - tracking various object
Funding
- This project was funded under a Leverhulme Trust award proposed by Dr. Xianghua Xie and Professor Majid Mirmehdi (University of Bristol). Dr. John Chiverton was employed as a research assistant for two years (2006-2008) to work on this project.
Publications
- J. Chiverton, X. Xie, and M. Mirmehdi, Automatic Bootstrapping and Tracking of Object Contours, IEEE Transactions on Image Processing (T-IP), volume 21, issue 3, pages 1231 - 1245, March 2012.
- John Chiverton, Xianghua Xie and Majid Mirmehdi, Probabilistic Sequential Segmentation and Simultaneous On-Line Shape Learning of Multi-Dimensional Medical Imaging Data, In Proceedings of Probablistic Models for Medical Image Analysis, A MICCAI Workshop, September 2009.
- John Chiverton, Majid Mirmehdi and Xianghua Xie, On-line Learning of Shape Information for Object Segmentation and Tracking, In Proceedings of the 20th British Machine Vision Conference, BMVA press, September 2009.
- John Chiverton, Xianghua Xie and Majid Mirmehdi, Tracking with Active Contours Using Dynamically Updated Shape Information, In Proceedings of the 19th British Machine Vision Conference, BMVA press, September 2008.
- John Chiverton, Majid Mirmehdi and Xianghua Xie, Variational Logistic Maximum A Posteriori Model Similarity and Dissimilarity Matching, IEEE International Conference on Pattern Recognition, IEEE press, December 2008.