Paper Info
Title
Can Motion Segmentation Improve Patch-Based Object Recognition?
Abstract
Patch-based methods, which constitute the state of the art in object recognition, are often applied to video data, where motion information provides a valuable clue for separating objects of interest from the background. We show that such motion-based segmentation improves the robustness of patch-based recognition with respect to clutter. Our approach, which employs segmentation information to rule out incorrect correspondences between training and test views, is demonstrated empirically to distinctly outperform baselines operating on unsegmented images. Relative improvements reach 50% for the recognition of specific objects, and 33% for object category retrieval.
Year
DOI
Venue
2010
10.1109/ICPR.2010.745
ICPR
Keywords
Field
DocType
object category retrieval,object recognition,patch-based recognition,patch-based method,motion information,incorrect correspondence,segmentation information,baselines operating,motion segmentation improve patch-based,motion-based segmentation,specific object,computer vision,information retrieval,image segmentation,clutter,visualization
Computer vision,3D single-object recognition,Pattern recognition,Computer science,Clutter,Segmentation,Visualization,Robustness (computer science),Image segmentation,Artificial intelligence,Cognitive neuroscience of visual object recognition
Conference
Citations 
PageRank 
References 
0
0.34
10
Authors
2
Name
Order
Citations
PageRank
Adrian Ulges132826.61
Thomas M. Breuel22362219.10