Object Tracking using Motion Estimation based on Block Matching Algorithm

Author(s):  
M. Sushma Sri ◽  
B. Rajendra Naik ◽  
K. Jayasankar

An object tracking increases loads of enthusiasm for dynamic research in applications such as video surveillance, vehicle navigation, highways, crowded public places, borders, forest and traffic monitoring areas. The system we develop aims to measure and analyze the application of background subtraction method and block matching algorithm to trace object movements through video-based. The making of video surveillance systems “smart” requires fast, reliable and robust algorithms for moving object detection and tracking. This research applies background subtraction method to detect moving object, assisted with block matching algorithm which aims to get good results on objects that have been detected. Performance evaluation is carried out to determine the various parameters. In this paper author design and develop a novel algorithm for moving object tracking in video surveillance also compares and analyse existing algorithms for moving object tracking. Author main aim to design and develop an algorithm for moving object tracking to handle occlusion and complex object shapes.


2000 ◽  
Vol 10 (05n06) ◽  
pp. 229-237
Author(s):  
KYUNG-SAENG KIM ◽  
KWYRO LEE

This letter describes a motion estimation architecture with complementary access types of memory banks, one for column vector access and the other for row vector access. It handles 2D image very efficiently for full-search block matching algorithm and maximizes a useful data transfer rate by reducing the overhead clocks for extra data reading and alignment. The results show that power saving is improved by using complementary access types of memory banks and amounts to 27.3% when the full-search block matching algorithm is applied for the CCIR-601 format compared to an identical design without the proposed enhancements.


Sign in / Sign up

Export Citation Format

Share Document