Paper Info
Title
Human Instance Segmentation From Video Using Detector-Based Conditional Random Fields
Abstract
In this work, we propose a method for instance based human segmentation in images and videos, extending the recent detector-based conditional random field model of Ladicky et.al. Instance based human segmentation involves pixel level labeling of an image, partitioning it into distinct human instances and background. To achieve our goal, we add three new components to their framework. First, we include human parts-based detection potentials to take advantage of the structure present in human instances. Further, in order to generate a consistent segmentation from different human parts, we incorporate shape prior information, which biases the segmentation to characteristic overall human shapes. Also, we enhance the representative power of the energy function by adopting exemplar instance based matching terms, which helps our method to adapt easily to different human sizes and poses. Finally, we extensively evaluate our proposed method on the Buffy dataset with our new segmented ground truth images, and show a substantial improvement over existing CRF methods. These new annotations will be made available for future use as well.
Year
DOI
Venue
2011
10.5244/C.25.80
PROCEEDINGS OF THE BRITISH MACHINE VISION CONFERENCE 2011
Keywords
Field
DocType
machine vision
Conditional random field,Computer vision,Scale-space segmentation,Pattern recognition,Segmentation,Computer science,Ground truth,Artificial intelligence,Pixel,Detector
Conference
Citations 
PageRank 
References 
13
0.72
20
Authors
4
Name
Order
Citations
PageRank
Vibhav Vineet1104337.41
Jonathan Warrell249418.95
Ladický L'ubor3101544.54
Philip H. S. Torr49140636.18