Parsing Semantic Parts of Cars Using Graphical Models and Segment Appearance Consistency
Name
CBMM-Memo-018.pdf
Size
5.02 MB
Format
Adobe PDF
Checksum (MD5)
95a17607b3de718e70dd43550789369e
Author(s)
Lu, Wenhao
Lian, Xiaochen
Yuille, Alan L.
Date Issued
June 13, 2014
Publisher
Center for Brains, Minds and Machines (CBMM), arXiv
Citation
arXiv:1406.2375v2
Series/Report no.
CBMM Memo Series;018
Abstract
This paper addresses the problem of semantic part parsing (segmentation) of cars, i.e.assigning every pixel within the car to one of the parts (e.g.body, window, lights, license plates and wheels). We formulate this as a landmark identification problem, where a set of landmarks specifies the boundaries of the parts. A novel mixture of graphical models is proposed, which dynamically couples the landmarks to a hierarchy of segments. When modeling pairwise relation between landmarks, this coupling enables our model to exploit the local image contents in addition to spatial deformation, an aspect that most existing graphical models ignore. In particular, our model enforces appearance consistency between segments within the same part. Parsing the car, including finding the optimal coupling between landmarks and segments in the hierarchy, is performed by dynamic programming. We evaluate our method on a subset of PASCAL VOC 2010 car images and on the car subset of 3D Object Category dataset (CAR3D). We show good results and, in particular, quantify the effectiveness of using the segment appearance consistency in terms of accuracy of part localization and segmentation.
Subjects
Hierarchy
Vision
Object Recognition
Terms of Use
Attribution-NonCommercial 3.0 United States
Persistent DSpace Link
