Moving Object Detection Using Background Subtraction Algorithms

Master's Thesis from the year 2014 in the subject Computer Science - Theory, grade: 9.2, , language: English, abstract: In this thesis we present an operational computer video system for movingobject detection and tracking . The system captures monocular frames ofbackground as well as moving object and to detect tracking and identifiesthose moving objects. An approach to statistically modeling of moving objectdeveloped using Background Subtraction Algorithms. There are manymethods proposed for Background Subtraction algorithm in past years.Background subtraction algorithm is widely used for real time moving objectdetection in video surveillance system. In this paper we have studied andimplemented different types of methods used for segmentation in Backgroundsubtraction algorithm with static camera. This paper gives good understandingabout procedure to obtain foreground using existing common methods ofBackground Subtraction, their complexity, utility and also provide basics whichwill useful to improve performance in the future . First, we have explained thebasic steps and procedure used in vision based moving object detection.Then, we have debriefed the common methods of background subtraction likeSimple method, statistical methods like Mean and Median filter, FrameDifferencing and W4 System method , Running Gaussian Average andGaussian Mixture Model and last is Eigenbackground Model. After that wehave implemented all the above techniques on MATLAB software and showsome experimental results for the same and compare them in terms of speedand complexity criteria. Also we have improved one of the GMM algorithm bycombining it with optical flow method, which is also good method to detectmoving elements.