Automatic target tracking in infrared image sequences using ensemble distance metric

Zhenyu Wang; Guotian Yang

doi:10.1117/12.855390

Translator Disclaimer

2 April 2010 Automatic target tracking in infrared image sequences using ensemble distance metric

Zhenyu Wang, Guotian Yang

Author Affiliations +

Proceedings Volume 7651, International Conference on Space Information Technology 2009; 76510N (2010) https://doi.org/10.1117/12.855390
Event: International Conference on Space Information Technology 2009, 2009, Beijing, China

Abstract

This paper presents a novel algorithm named Ensemble Distance Metric Tracking (EDMT) for target tracking in infrared imagery. Obtaining an appropriate distance metric function can significantly improve the performance of tracking algorithms. There are two problems in distance metric choosing for object tracking. First, we can't find the data model distribution beforehand for most tracking application. Second, the data model will change as both foreground and background appearance undergoes complex changes with the target object moving from place to place. So the distance metric function also needs to adapt dynamically during the tracking procedure. Most tracking applications are conducted using a fixed distance metric function, which is determined beforehand. We propose a new algorithm that can learn and update the distance metric dynamically, which is different from the conventional methods that use the predefined metric. In our new EDMT algorithm, the ensemble distance metric function is learnt by weighted training with different distance metrics on each feature element iteratively using the boosting learning method. The new distance metric function is adopted in particle filter to compute the weights of each particle. The experimental results demonstrate the effectiveness and robustness of our tracking algorithm in challenging infrared video sequences.

Citation Download Citation

Zhenyu Wang and Guotian Yang "Automatic target tracking in infrared image sequences using ensemble distance metric", Proc. SPIE 7651, International Conference on Space Information Technology 2009, 76510N (2 April 2010); https://doi.org/10.1117/12.855390

ACCESS THE FULL ARTICLE