Structural Sparse Representation for Object Detection

Classic sparse representation, as one of prevalent feature learning methods, is successfully applied for different computer vision tasks. However it has some intrinsic defects in object detection. Firstly, how to learn a discriminative dictionary for object detection is a hard problem. Secondly, it...

Full description

Saved in:
Bibliographic Details
Published in:Wuhan University journal of natural sciences 2017-08, Vol.22 (4), p.318-322
Main Authors: Fang, Wenhua, Chen, Jun, Hu, Ruimin
Format: Article
Language:English
Subjects:
Biomedical and Life Sciences
Classification
Computer Science
Computer vision
Defects
Dictionaries
Error detection
Learning
Life Sciences
Materials Science
Object recognition
VOCs
Volatile organic compounds
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Classic sparse representation, as one of prevalent feature learning methods, is successfully applied for different computer vision tasks. However it has some intrinsic defects in object detection. Firstly, how to learn a discriminative dictionary for object detection is a hard problem. Secondly, it is usually very time-consuming to learn dictionary based features in a traditional exhaustive search manner like sliding window. In this paper, we propose a novel feature learning framework for object detection with the structure sparsity constraint and classification error minimization constraint to learn a discriminative dictionary. For improving the efficiency, we just learn sparse representation coefficients from object candidate regions and feed them to a kernelized SVM classifier. Experiments on INRIA Person Dataset and Pascal VOC 2007 challenge dataset clearly demonstrate the effectiveness of the proposed approach compared with two state-of-the-art baselines.
ISSN:1007-1202
1993-4998
DOI:10.1007/s11859-017-1253-2