Voting based object boundary reconstruction

Qi Tian; Like Zhang; Jingsheng Ma

doi:10.1117/12.633444

24 June 2005 Voting based object boundary reconstruction

Qi Tian, Like Zhang, Jingsheng Ma

Proceedings Volume 5960, Visual Communications and Image Processing 2005; 59606B (2005) https://doi.org/10.1117/12.633444
Event: Visual Communications and Image Processing 2005, 2005, Beijing, China

Abstract

A voting-based object boundary reconstruction approach is proposed in this paper. Morphological technique was adopted in many applications for video object extraction to reconstruct the missing pixels. However, when the missing areas become large, the morphological processing cannot bring us good results. Recently, Tensor voting has attracted people's attention, and it can be used for boundary estimation on curves or irregular trajectories. However, the complexity of saliency tensor creation limits its applications in real-time systems. An alternative approach based on tensor voting is introduced in this paper. Rather than creating saliency tensors, we use a "2-pass" method for orientation estimation. For the first pass, Sobel d*etector is applied on a coarse boundary image to get the gradient map. In the second pass, each pixel puts decreasing weights based on its gradient information, and the direction with maximum weights sum is selected as the correct orientation of the pixel. After the orientation map is obtained, pixels begin linking edges or intersections along their direction. The approach is applied to various video surveillance clips under different conditions, and the experimental results demonstrate significant improvement on the final extracted objects accuracy.

Citation Download Citation

Qi Tian, Like Zhang, and Jingsheng Ma "Voting based object boundary reconstruction", Proc. SPIE 5960, Visual Communications and Image Processing 2005, 59606B (24 June 2005); https://doi.org/10.1117/12.633444

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available