Skip to main content

Research Repository

Advanced Search

Prior knowledge-based deep learning method for indoor object recognition and application

Ding, Xintao; Luo, Yonglong; Li, Qingde; Cheng, Yongqiang; Cai, Guorong; Munnoch, Robert; Xue, Dongfei; Yu, Qingying; Zheng, Xiaoyao; Wang, Bing

Authors

Xintao Ding

Yonglong Luo

Guorong Cai

Robert Munnoch

Dongfei Xue

Qingying Yu

Xiaoyao Zheng



Abstract

Indoor object recognition is a key task for indoor navigation by mobile robots. Although previous work has produced impressive results in recognizing known and familiar objects, the research of indoor object recognition for robot is still insufficient. In order to improve the detection precision, our study proposed a prior knowledge-based deep learning method aimed to enable the robot to recognize indoor objects on sight. First, we integrate the public Indoor dataset and the private frames of videos (FoVs) dataset to train a convolutional neural network (CNN). Second, mean images, which are used as a type of colour knowledge, are generated for all the classes in the Indoor dataset. The distance between every mean image and the input image produces the class weight vector. Scene knowledge, which consists of frequencies of occurrence of objects in the scene, is then employed as another prior knowledge to determine the scene weight. Finally, when a detection request is launched, the two vectors together with a vector of classification probability instigated by the deep model are multiplied to produce a decision vector for classification. Experiments show that detection precision can be improved by employing the prior colour and scene knowledge. In addition, we applied the method to object recognition in a video. The results showed potential application of the method for robot vision.

Citation

Ding, X., Luo, Y., Li, Q., Cheng, Y., Cai, G., Munnoch, R., …Wang, B. (2018). Prior knowledge-based deep learning method for indoor object recognition and application. Systems Science and Control Engineering, 6(1), 249-257. https://doi.org/10.1080/21642583.2018.1482477

Journal Article Type Article
Acceptance Date May 26, 2018
Online Publication Date May 31, 2018
Publication Date May 31, 2018
Deposit Date Jul 19, 2018
Publicly Available Date Jul 20, 2018
Journal Systems Science & Control Engineering
Print ISSN 2164-2583
Electronic ISSN 2164-2583
Publisher Taylor and Francis
Peer Reviewed Peer Reviewed
Volume 6
Issue 1
Pages 249-257
DOI https://doi.org/10.1080/21642583.2018.1482477
Keywords Indoor object recognition; Deep learning; Prior knowledge
Public URL https://hull-repository.worktribe.com/output/936992
Publisher URL https://www.tandfonline.com/doi/full/10.1080/21642583.2018.1482477
Copyright Statement © 2018 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Additional Information Peer Review Statement: The publishing and review policy for this title is described in its Aims & Scope.; Aim & Scope: http://www.tandfonline....cope&journalCode=tssc20

Files

Published article (2 Mb)
PDF

Publisher Licence URL
https://creativecommons.org/licenses/by/4.0/

Copyright Statement
© 2018 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.



You might also like



Downloadable Citations