FAST MOTION ESTIMATION IN VIDEO SEQUENCES BY EDGE DETECTION

Telatar Z.

JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY, vol.24, no.2, pp.245-255, 2009 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 24 Issue: 2
  • Publication Date: 2009
  • Journal Name: JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, TR DİZİN (ULAKBİM)
  • Page Numbers: pp.245-255
  • Keywords: Motion estimation, object motion search, block matching, edge detection
  • Ankara University Affiliated: Yes

Abstract

In this paper, a fast approach to detect and estimate the multiple object motion in video sequences is presented. The method is based on transforming each image in the sequence of frames into vector projections formed by accumulating pixel shift value along the rows and columns of the image. The projections corresponding to consecutive frames are in turn used to detect and estimate the individual horizontal and vertical components of the possible shifts. For that reason, block matching and maximum absolute difference (MAD) algorithms were used in detecting and tracking the moving objects in sequences. Sharp transitions or shortly edges in each image frame are also considered as an efficient method in the algorithm for decreasing the computational costs. Experimental results show that, usefulness of the method is presented not only in the context of motion analysis and tracking ability of objects, but also for a decrease in process time required for detecting and tracking.