Accession Number : AD1037525


Title :   Video Object Segmentation through Spatially Accurate and Temporally Dense Extraction of Primary Object Regions


Descriptive Note : Conference Paper


Corporate Author : University of Central Florida Orlando United States


Personal Author(s) : Zhang,Dong ; Javed,Omar ; Shah,Mubarak


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/1037525.pdf


Report Date : 03 Oct 2013


Pagination or Media Count : 8


Abstract : In this paper, we propose a novel approach to extract primary object segments in videos in the object proposal' domain. The extracted primary object regions are then used to build object models for optimized video segmentation. The proposed approach has several contributions: First, a novel layered Directed Acyclic Graph (DAG) based framework is presented for detection and segmentation of the primary object in video. We exploit the fact that, in general, objects are spatially cohesive and characterized by locally smooth motion trajectories, to extract the primary object from the set of all available proposals based on motion, appearance and predicted-shape similarity across frames. Second, the DAG is initialized with an enhanced object proposal set where motion based proposal predictions (from adjacent frames) are used to expand the set of object proposals for a particular frame. Last, the paper presents a motion scoring function for selection of object proposals that emphasizes high optical flow gradients at proposal boundaries to discriminate between moving objects and the background. The proposed approach is evaluated using several challenging benchmark videos and it outperforms both unsupervised and supervised state-of-the-art methods.


Descriptors :   video frames , optimization , pattern recognition , digital data , extraction , image recognition , heuristic methods , graphs , computer programming , recognition , image processing , equations


Subject Categories : Operations Research
      Cybernetics


Distribution Statement : APPROVED FOR PUBLIC RELEASE