Place recognition using semantic concepts of visual words
Applying the ‘bag-of-visual-words’ has recently become popular for image understanding. Although, using the histogram of visual words suffers the problem when the patches of an image faced with similar appearance corresponding to differentiate semantic concepts and vice versa. Due to varying views a...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Academic Journals
2011
|
Online Access: | http://psasir.upm.edu.my/id/eprint/22773/1/22773.pdf |
_version_ | 1796970228379287552 |
---|---|
author | Rostami, Vahid Ramli, Abdul Rahman Samsudin, Khairulmizam Saripan, M. Iqbal |
author_facet | Rostami, Vahid Ramli, Abdul Rahman Samsudin, Khairulmizam Saripan, M. Iqbal |
author_sort | Rostami, Vahid |
collection | UPM |
description | Applying the ‘bag-of-visual-words’ has recently become popular for image understanding. Although, using the histogram of visual words suffers the problem when the patches of an image faced with similar appearance corresponding to differentiate semantic concepts and vice versa. Due to varying views and dynamic objects, this problem is more complicated in the mobile robot applications such as global localization and place recognition systems. This paper presents a supervised learning framework for place recognition using the semantic concepts of visual words. Specifically, the k-mean algorithm is firstly applied to quantize the low-level visual features as bag-of-visual-words (BOVW). And then the visual latent semantic analysis (VLSA) is introduced to obtain semantic concepts of these words from the correlation of the image patches. Once obtained the semantic concepts, the corresponding of these concepts in a query image are formed as a vector of similarity density, which it can be exploited in the place recognition using the support vector machine (SVM) classifier. Experiments on synthesis and challenging indoor datasets reveal that the average recognition performance in two different datasets is improved from 77.54 to 90.92% using the histogram of BOVW and the proposed method respectively. |
first_indexed | 2024-03-06T07:54:56Z |
format | Article |
id | upm.eprints-22773 |
institution | Universiti Putra Malaysia |
language | English |
last_indexed | 2024-03-06T07:54:56Z |
publishDate | 2011 |
publisher | Academic Journals |
record_format | dspace |
spelling | upm.eprints-227732020-04-15T16:24:36Z http://psasir.upm.edu.my/id/eprint/22773/ Place recognition using semantic concepts of visual words Rostami, Vahid Ramli, Abdul Rahman Samsudin, Khairulmizam Saripan, M. Iqbal Applying the ‘bag-of-visual-words’ has recently become popular for image understanding. Although, using the histogram of visual words suffers the problem when the patches of an image faced with similar appearance corresponding to differentiate semantic concepts and vice versa. Due to varying views and dynamic objects, this problem is more complicated in the mobile robot applications such as global localization and place recognition systems. This paper presents a supervised learning framework for place recognition using the semantic concepts of visual words. Specifically, the k-mean algorithm is firstly applied to quantize the low-level visual features as bag-of-visual-words (BOVW). And then the visual latent semantic analysis (VLSA) is introduced to obtain semantic concepts of these words from the correlation of the image patches. Once obtained the semantic concepts, the corresponding of these concepts in a query image are formed as a vector of similarity density, which it can be exploited in the place recognition using the support vector machine (SVM) classifier. Experiments on synthesis and challenging indoor datasets reveal that the average recognition performance in two different datasets is improved from 77.54 to 90.92% using the histogram of BOVW and the proposed method respectively. Academic Journals 2011 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/22773/1/22773.pdf Rostami, Vahid and Ramli, Abdul Rahman and Samsudin, Khairulmizam and Saripan, M. Iqbal (2011) Place recognition using semantic concepts of visual words. Scientific Research and Essays, 6 (17). art. no. 51C36F134811. pp. 3751-3759. ISSN 1992-2248 https://academicjournals.org/journal/SRE/article-abstract/51C36F134811 10.5897/SRE11.861 |
spellingShingle | Rostami, Vahid Ramli, Abdul Rahman Samsudin, Khairulmizam Saripan, M. Iqbal Place recognition using semantic concepts of visual words |
title | Place recognition using semantic concepts of visual words |
title_full | Place recognition using semantic concepts of visual words |
title_fullStr | Place recognition using semantic concepts of visual words |
title_full_unstemmed | Place recognition using semantic concepts of visual words |
title_short | Place recognition using semantic concepts of visual words |
title_sort | place recognition using semantic concepts of visual words |
url | http://psasir.upm.edu.my/id/eprint/22773/1/22773.pdf |
work_keys_str_mv | AT rostamivahid placerecognitionusingsemanticconceptsofvisualwords AT ramliabdulrahman placerecognitionusingsemanticconceptsofvisualwords AT samsudinkhairulmizam placerecognitionusingsemanticconceptsofvisualwords AT saripanmiqbal placerecognitionusingsemanticconceptsofvisualwords |