Simultaneous Object Segmentation and Recognition by Merging CNN Outputs from Uniformly Distributed Multiple Viewpoints
Summary :
We propose a novel object recognition system that is able to (i) work in real-time while reconstructing segmented 3D maps and simultaneously recognize objects in a scene, (ii) manage various kinds of objects, including those with smooth surfaces and those with a large number of categories, utilizing a CNN for feature extraction, and (iii) maintain high accuracy no matter how the camera moves by distributing the viewpoints for each object uniformly and aggregating recognition results from each distributed viewpoint as the same weight. Through experiments, the advantages of our system with respect to current state-of-the-art object recognition approaches are demonstrated on the UW RGB-D Dataset and Scenes and on our own scenes prepared to verify the effectiveness of the Viewpoint-Class-based approach.
- Publication
- IEICE TRANSACTIONS on Information Vol.E101-D No.5 pp.1308-1316
- Publication Date
- 2018/05/01
- Publicized
- 2018/02/16
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2017MVP0024
- Type of Manuscript
- Special Section PAPER (Special Section on Machine Vision and its Applications)
- Category
- Machine Vision and its Applications
Authors
Yoshikatsu NAKAJIMA
Keio University
Hideo SAITO
Keio University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Yoshikatsu NAKAJIMA, Hideo SAITO, "Simultaneous Object Segmentation and Recognition by Merging CNN Outputs from Uniformly Distributed Multiple Viewpoints" in IEICE TRANSACTIONS on Information,
vol. E101-D, no. 5, pp. 1308-1316, May 2018, doi: 10.1587/transinf.2017MVP0024.
Abstract: We propose a novel object recognition system that is able to (i) work in real-time while reconstructing segmented 3D maps and simultaneously recognize objects in a scene, (ii) manage various kinds of objects, including those with smooth surfaces and those with a large number of categories, utilizing a CNN for feature extraction, and (iii) maintain high accuracy no matter how the camera moves by distributing the viewpoints for each object uniformly and aggregating recognition results from each distributed viewpoint as the same weight. Through experiments, the advantages of our system with respect to current state-of-the-art object recognition approaches are demonstrated on the UW RGB-D Dataset and Scenes and on our own scenes prepared to verify the effectiveness of the Viewpoint-Class-based approach.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2017MVP0024/_p
Copy
@ARTICLE{e101-d_5_1308,
author={Yoshikatsu NAKAJIMA, Hideo SAITO, },
journal={IEICE TRANSACTIONS on Information},
title={Simultaneous Object Segmentation and Recognition by Merging CNN Outputs from Uniformly Distributed Multiple Viewpoints},
year={2018},
volume={E101-D},
number={5},
pages={1308-1316},
abstract={We propose a novel object recognition system that is able to (i) work in real-time while reconstructing segmented 3D maps and simultaneously recognize objects in a scene, (ii) manage various kinds of objects, including those with smooth surfaces and those with a large number of categories, utilizing a CNN for feature extraction, and (iii) maintain high accuracy no matter how the camera moves by distributing the viewpoints for each object uniformly and aggregating recognition results from each distributed viewpoint as the same weight. Through experiments, the advantages of our system with respect to current state-of-the-art object recognition approaches are demonstrated on the UW RGB-D Dataset and Scenes and on our own scenes prepared to verify the effectiveness of the Viewpoint-Class-based approach.},
keywords={},
doi={10.1587/transinf.2017MVP0024},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - Simultaneous Object Segmentation and Recognition by Merging CNN Outputs from Uniformly Distributed Multiple Viewpoints
T2 - IEICE TRANSACTIONS on Information
SP - 1308
EP - 1316
AU - Yoshikatsu NAKAJIMA
AU - Hideo SAITO
PY - 2018
DO - 10.1587/transinf.2017MVP0024
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2018
AB - We propose a novel object recognition system that is able to (i) work in real-time while reconstructing segmented 3D maps and simultaneously recognize objects in a scene, (ii) manage various kinds of objects, including those with smooth surfaces and those with a large number of categories, utilizing a CNN for feature extraction, and (iii) maintain high accuracy no matter how the camera moves by distributing the viewpoints for each object uniformly and aggregating recognition results from each distributed viewpoint as the same weight. Through experiments, the advantages of our system with respect to current state-of-the-art object recognition approaches are demonstrated on the UW RGB-D Dataset and Scenes and on our own scenes prepared to verify the effectiveness of the Viewpoint-Class-based approach.
ER -
English
