Tracking of a point target in an IR sequence using dynamic programming approach Conference Paper uri icon


  • Examination of more than one image is often needed for the detection of dim point targets in IR backgrounds. We introduce a novel tracking system based on the Track Before Detect Approach (TBD), designed to track and detect such dim maneuvering targets from an image sequence under low SNR conditions. The IR sequence is preprocessed first by using a whitening algorithm to reject clutter and emphasize targets. Afterwards, we use a Dynamic Programming Algorithm (DPA) which is not general since it requires a number of assumptions to hold, all satisfied in a first-order Hidden Markov Model (HMM). An IR sequence containing background noise, clutter, and a sub-pixel maneuvering target satisfies such model, where the target track is the hidden sequence of events, and the IR sequence frames are the observed sequence of events. At the end of this stage, after the last frame …

publication date

  • January 1, 2006