Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Incremental discovery of object parts in video sequences
Drouin S., Hébert P., Parizeau M. Computer Vision and Image Understanding110 (1):60-74,2008.Type:Article
Date Reviewed: Jul 16 2008

Given a video and a segmentation algorithm, how does one reconstruct the foreground object from consecutive frames without having any predefined models? This paper describes a solution to this very fundamental and important topic.

To solve this problem, Drouin et al. propose a framework that consists of a tracker, a segmenter, and a modeler. The tracker estimates a new set of pose parameters for every frame, in such a way that the model fits the current frame. The segmenter uses the often-used graph-cut algorithm to create a traditional image segmentation of a video frame. Both tracking and segmentation are used by the modeler, which is mainly responsible for controlling the merging of newly found object parts.

The authors show image sequences of a human and a robot arm. Assuming that the method works as promised, the biggest downside of the technique seems to be the computational efficiency; according to the authors, it is far from real-time processing.

I worked in this field myself, a couple of years ago, and I have never read about such a sharp and well-thought-out idea in this area. I definitely recommend this paper to everybody who wants to work in the field of video-object extraction. Unfortunately, there is no clear benchmark evaluation given that would express both accuracy and robustness under different conditions, using an accepted error measurement.

Reviewer:  Gerald Friedland Review #: CR135841 (0906-0582)
Bookmark and Share
 
Video Analysis (I.2.10 ... )
 
 
Image Representation (I.4.10 )
 
 
Scene Analysis (I.4.8 )
 
Would you recommend this review?
yes
no
Other reviews under "Video Analysis": Date
Background subtraction based on logarithmic intensities
Wu Q., Jeng B. Pattern Recognition Letters 23(13): 1529-1536, 2002. Type: Article
Aug 6 2003
Video segmentation based on 2D image analysis: a coding theoretic approach
Guimarães S., Couprie M., Araújo A., Leite N. Pattern Recognition Letters 24(7): 947-957, 2003. Type: Article
Jun 20 2003
Multimodal video characterization and summarization (Kluwer International Series in Video Computing)
Smith M., Kanade T., Kluwer Academic Publishers, Norwell, MA, 2004. Type: Book (9781402074264)
Apr 22 2005
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy