 |
Technical Program
Paper Detail
| Paper: | WA-P9.6 |
| Session: | Motion Tracking |
| Time: | Wednesday, October 11, 09:40 - 12:20 |
| Presentation: |
Poster
|
| Title: |
EFFICIENT BAYESIAN TRACK-BEFORE-DETECT |
| Authors: |
Serhat Tekinalp; Auburn University | | | | | A. Aydin Alatan; Middle East Technical University | | |
| Abstract: |
This paper presents a novel Bayesian recursive track-before-detect algorithm for detecting and tracking dim targets in optical image sequences. The algorithm recursively incorporates new data acquired through sensor to the existing information, eliminating need for storing all past data. It calculates the likelihood ratio for optimal detection and estimates target state simultaneously. The technique does not require velocity-matched filtering and capable of detecting any target moving in any direction. The algorithm is tested with both synthetic and real video sequences, and it is shown to be capable of performing sufficiently well for very low signal-to-noise ratio situations. |
|
