Sub-Category Optimization through Cluster Performance Analysis for Multi-View Multi-Pose Object Detection

Dipankar DAS; Yoshinori KOBAYASHI; Yoshinori KUNO

doi:10.1587/transinf.E94.D.1467

Sub-Category Optimization through Cluster Performance Analysis for Multi-View Multi-Pose Object Detection

Dipankar DAS, Yoshinori KOBAYASHI, Yoshinori KUNO

Full Text Views

0

Share
Cite this

Summary :

The detection of object categories with large variations in appearance is a fundamental problem in computer vision. The appearance of object categories can change due to intra-class variations, background clutter, and changes in viewpoint and illumination. For object categories with large appearance changes, some kind of sub-categorization based approach is necessary. This paper proposes a sub-category optimization approach that automatically divides an object category into an appropriate number of sub-categories based on appearance variations. Instead of using predefined intra-category sub-categorization based on domain knowledge or validation datasets, we divide the sample space by unsupervised clustering using discriminative image features. We then use a cluster performance analysis (CPA) algorithm to verify the performance of the unsupervised approach. The CPA algorithm uses two performance metrics to determine the optimal number of sub-categories per object category. Furthermore, we employ the optimal sub-category representation as the basis and a supervised multi-category detection system with χ² merging kernel function to efficiently detect and localize object categories within an image. Extensive experimental results are shown using a standard and the authors' own databases. The comparison results reveal that our approach outperforms the state-of-the-art methods.

Publication: IEICE TRANSACTIONS on Information Vol.E94-D No.7 pp.1467-1478

Publication Date: 2011/07/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E94.D.1467

Type of Manuscript: PAPER

Category: Image Recognition, Computer Vision

Cite this

Copy

Dipankar DAS, Yoshinori KOBAYASHI, Yoshinori KUNO, "Sub-Category Optimization through Cluster Performance Analysis for Multi-View Multi-Pose Object Detection" in IEICE TRANSACTIONS on Information, vol. E94-D, no. 7, pp. 1467-1478, July 2011, doi: 10.1587/transinf.E94.D.1467.
Abstract: The detection of object categories with large variations in appearance is a fundamental problem in computer vision. The appearance of object categories can change due to intra-class variations, background clutter, and changes in viewpoint and illumination. For object categories with large appearance changes, some kind of sub-categorization based approach is necessary. This paper proposes a sub-category optimization approach that automatically divides an object category into an appropriate number of sub-categories based on appearance variations. Instead of using predefined intra-category sub-categorization based on domain knowledge or validation datasets, we divide the sample space by unsupervised clustering using discriminative image features. We then use a cluster performance analysis (CPA) algorithm to verify the performance of the unsupervised approach. The CPA algorithm uses two performance metrics to determine the optimal number of sub-categories per object category. Furthermore, we employ the optimal sub-category representation as the basis and a supervised multi-category detection system with χ² merging kernel function to efficiently detect and localize object categories within an image. Extensive experimental results are shown using a standard and the authors' own databases. The comparison results reveal that our approach outperforms the state-of-the-art methods.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E94.D.1467/_p

Copy

@ARTICLE{e94-d_7_1467,
author={Dipankar DAS, Yoshinori KOBAYASHI, Yoshinori KUNO, },
journal={IEICE TRANSACTIONS on Information},
title={Sub-Category Optimization through Cluster Performance Analysis for Multi-View Multi-Pose Object Detection},
year={2011},
volume={E94-D},
number={7},
pages={1467-1478},
abstract={The detection of object categories with large variations in appearance is a fundamental problem in computer vision. The appearance of object categories can change due to intra-class variations, background clutter, and changes in viewpoint and illumination. For object categories with large appearance changes, some kind of sub-categorization based approach is necessary. This paper proposes a sub-category optimization approach that automatically divides an object category into an appropriate number of sub-categories based on appearance variations. Instead of using predefined intra-category sub-categorization based on domain knowledge or validation datasets, we divide the sample space by unsupervised clustering using discriminative image features. We then use a cluster performance analysis (CPA) algorithm to verify the performance of the unsupervised approach. The CPA algorithm uses two performance metrics to determine the optimal number of sub-categories per object category. Furthermore, we employ the optimal sub-category representation as the basis and a supervised multi-category detection system with χ² merging kernel function to efficiently detect and localize object categories within an image. Extensive experimental results are shown using a standard and the authors' own databases. The comparison results reveal that our approach outperforms the state-of-the-art methods.},
keywords={},
doi={10.1587/transinf.E94.D.1467},
ISSN={1745-1361},
month={July},}

Copy

TY - JOUR
TI - Sub-Category Optimization through Cluster Performance Analysis for Multi-View Multi-Pose Object Detection
T2 - IEICE TRANSACTIONS on Information
SP - 1467
EP - 1478
AU - Dipankar DAS
AU - Yoshinori KOBAYASHI
AU - Yoshinori KUNO
PY - 2011
DO - 10.1587/transinf.E94.D.1467
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E94-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2011
AB - The detection of object categories with large variations in appearance is a fundamental problem in computer vision. The appearance of object categories can change due to intra-class variations, background clutter, and changes in viewpoint and illumination. For object categories with large appearance changes, some kind of sub-categorization based approach is necessary. This paper proposes a sub-category optimization approach that automatically divides an object category into an appropriate number of sub-categories based on appearance variations. Instead of using predefined intra-category sub-categorization based on domain knowledge or validation datasets, we divide the sample space by unsupervised clustering using discriminative image features. We then use a cluster performance analysis (CPA) algorithm to verify the performance of the unsupervised approach. The CPA algorithm uses two performance metrics to determine the optimal number of sub-categories per object category. Furthermore, we employ the optimal sub-category representation as the basis and a supervised multi-category detection system with χ² merging kernel function to efficiently detect and localize object categories within an image. Extensive experimental results are shown using a standard and the authors' own databases. The comparison results reveal that our approach outperforms the state-of-the-art methods.
ER -