Tracking of a Point Target in an IR Sequence using Dynamic Programming Approach

Abstract

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 of the IR sequence has been processed, the pixel with the highest accumulated score is chosen as the Target, and its path is found. The paper deals with the different issues characterizing the system, enabling it to have versatility over a wide range of scenes. Future work will involve the use of the system for tracking of targets in hyperspectral cubes.