Tracking Human in Thermal Vision using Multi-feature Histogram

Abstract

This thesis presents a multi-feature histogram approach to track a person in thermal vision. Illumination variation is a primary constraint in the performance of object tracking in visible spectrum. Thermal infrared (IR) sensor, which measures the heat energy emitted from an object, is less sensitive to illumination variations. Therefore, thermal vision has immense advantage in object tracking in varying illumination conditions. Kernel based approaches such as mean shift tracking algorithm which uses a single feature histogram for object representation, has gained popularity in the field of computer vision due its efficiency and robustness to track non-rigid object in significant complex background. However, due to low resolution of IR images the gray level intensity information is not sufficient enough to give a strong cue for object representation using histogram. Multi-feature histogram, which is the combination of the gray level intensity information and edge information, generates an object representation which is more robust in thermal vision. The objective of this research is to develop a robust human tracking system which can autonomously detect, identify and track a person in a complex thermal IR scene. In this thesis the tracking procedure has been adapted from the well-known and efficient mean shift tracking algorithm and has been modified to enable fusion of multiple features to increase the robustness of the tracking procedure in thermal vision. In order to identify the object of interest before tracking, rapid human detection in thermal IR scene is achieved using Adaboost classification algorithm. Furthermore, a computationally efficient body pose recognition method is developed which uses Hu-invariant moments for matching object shapes. An experimental setup consisting of a Forward Looking Infrared (FLIR) camera, mounted on a Pioneer P3-DX mobile robot platform was used to test the proposed human tracking system in both indoor and uncontrolled outdoor environments. The performance evaluation of the proposed tracking system on the OTCBVS benchmark dataset shows improvement in tracking performance in comparison to the traditional mean-shift tracking algorithm. Moreover, experimental results in different indoor and outdoor tracking scenarios involving different appearances of people show tracking is robust under cluttered background, varying illumination and partial occlusion of target object.