Optical Flow Based Multiple Object Detection and Tracking System in Static and Dynamic Environment

Abstract

Estimation and tracking of multiple moving objects in a dynamic environment is a challenging task in computer vision. It demands real-time computation with reliable accuracy on embedded processors. This project focuses on the identification, analysis and implementation of suitable single and multiple moving object detection and tracking algorithm which makes use of spatiotemporal information. In this Thesis, the spatiotemporal information is obtained using Optic Flow computation. Optical Flow is a vector field which gives both magnitude and direction of the pixel movements with respect to consecutive frames. Horn and Schunck algorithm is used in this work for computation of Optical Flow vectors. Single and multiple objects based on the computed vectors are segmented using intensity based thresholding. Image enhancement techniques consisting of morphological operations and pixel connectivity are applied to enhance the segmented objects. The designed tracking algorithm is implemented MATLAB. The developed algorithm is first validated and its parameters tuned using real and virtual data with static background. For tracking in dynamic background the segmented objects are identified and the user is asked to choose one of the objects to