Motion-Model-Based Boundary Extraction

Published

November 1, 1995

Author(s)

H Liu, Tsai H. Hong, Martin Herman, Rama Chellappa

Abstract

Motion boundary extraction and optical flow computation are two subproblems of the motion recovery problem that cannot be solved independently of each other. They represent the most common dilemma in motion research. A popular approach uses an iterative scheme that consists of motion boundary extraction and optical flow computation components and refines each result through iteration. This approach is typically timeconsuming and sometimes does not converge. We present a local, noniterative algorithm that extracts motion boundaries and computes optical flow simultaneously. This is achieved by modeling a 3-D image intensity block with a general motion model that presumes locally coherent motion. Local motion coherence, which is measured by the fitness of the motion model, is the criterion we use to determine whether motion should be estimated, or otherwise motion boundaries should be located. The motion boundary extraction algorithm is evaluated quantitatively and qualitatively against other existing algorithms in a scheme originally developed for edge detection. The results show that our algorithm is accurate in locating boundaries. The flow portion of the algorithm is presented in another paper[24] .

Proceedings Title

Proceedings of the 1995 IEEE International Symposium on Computer Vision

Conference Dates

November 1, 1995

Conference Location

Coral Gables, FL, USA

Conference Title

IEEE International Symposium on Computer Vision

Pub Type

Conferences

Download Paper

Local Download

Citation

Liu, H. , Hong, T. , Herman, M. and Chellappa, R. (1995), Motion-Model-Based Boundary Extraction, Proceedings of the 1995 IEEE International Symposium on Computer Vision, Coral Gables, FL, USA, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=820564 (Accessed March 14, 2025)