17 April 2017

We are always looking for sharp and talented students who have a passion for machine vision and stochastic signal processing. If you are one of them, contact me and we may be able to provide you with a PhD scholarship.

1 March 2017

Check out our conference ICCAIS2017 that will be held in Thailand during Oct 31 - Nov 3, 2017. The papers are indexed by all major indexing databases such as Scopus and IEEExplore.

Statistical information fusion methods to integrate multiple-view sensor data in multi-object tracking applications have not been explored widely for random set filters. The commonly used Generalized Covariance Intersection (GCI) method is a consensus-based fusion method and in circumstances where sensors do not necessarily agree on existence and state of the same target, that target is either removed from, or appears with poor accuracy in the GCI-fusion outcomes.

We have developed a novel information-theoretic method that overcomes the drawbacks of the GCI-fusion method with involving adaptive weights in the formula that are automatically tuned based on the amount of information carried by the measurements from each sensor.

The following example shows how the measurements provided by sensors that have limited and different fields of view can be combined in a challenging multi-target tracking problem.

asp hit counter
Visits since March 1, 2017