| Paper: | MA-L2.3 |
| Session: | Image And Video Segmentation I |
| Time: | Monday, September 17, 10:30 - 10:50 |
| Presentation: |
Lecture
|
| Title: |
COUPLED HIDDEN MARKOV MODELS FOR ROBUST EO/IR TARGET TRACKING |
| Authors: |
Jiading Gai; University of Notre Dame | | |
| | Yong Li; University of Notre Dame | | |
| | Robert L. Stevenson; University of Notre Dame | | |
| Abstract: |
Augmenting Electro-Optical (EO) based target tracking systems to the Infrared (IR) modality has been shown to effectively increase the accuracy rate. A key issue in designing such a multimodal tracking system is how to combine information observed from different sensor types in a systematic way to obtain desirable performance. In this paper, we present an investigation into integrating EO and IR sensors within hidden Markov model (HMM) based frameworks. We propose to use a coupled hidden Markov model (CHMM) to improve upon the existing fusion schemes. Another contribution is that we propose to use a robust t-distribution based subspace representation in the CHMM to model appearance changes of the target. Numerical experiments demonstrate that the proposed CHMM tracking system excels other integration schemes for situations where the target object is corrupted by noise or occlusion. |
