Cover Image

A recurrent deep architecture for enhancing indoor camera localization using motion blur elimination

Rapid growth and technological improvements in computer vision have enabled indoor camera localization. The accurate camera localization of an indoor environment is challenging because it has many complex problems, and motion blur is one of them. Motion blur introduces significant errors, degrades t...

Full description

Saved in:
Bibliographic Details
Main Authors: Alam, Muhammad Shamsul, Mohamed, Farhan, Selamat, Ali, Hossain, Akm. Bellal
Format: Article
Language:English
Published: Universitas Muhammadiyah Yogyakarta 2024
Subjects:
QA75 Electronic computers. Computer science
Online Access:http://eprints.utm.my/108927/1/MuhammadShamsul2024_ARecurrentDeepArchitectureforEnhancing.pdf
http://eprints.utm.my/108927/
https://journal.umy.ac.id/index.php/jrc/article/view/21930
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.108927
record_format eprints
spelling my.utm.1089272024-12-15T06:06:27Z http://eprints.utm.my/108927/ A recurrent deep architecture for enhancing indoor camera localization using motion blur elimination Alam, Muhammad Shamsul Mohamed, Farhan Selamat, Ali Hossain, Akm. Bellal QA75 Electronic computers. Computer science Rapid growth and technological improvements in computer vision have enabled indoor camera localization. The accurate camera localization of an indoor environment is challenging because it has many complex problems, and motion blur is one of them. Motion blur introduces significant errors, degrades the image quality, and affects feature matching, making it challenging to determine camera pose accurately. Improving the camera localization accuracy for some robotic applications is still necessary. In this study, we propose a recurrent neural network (RNN) approach to solve the indoor camera localization problem using motion blur reduction. Motion blur in an image is detected by analyzing its frequency spectrum. A low-frequency component indicates motion blur, and by investigating the direction of these low-frequency components, the location and amount of blur are estimated. Then, Wiener filtering deconvolution removes the blur and obtains a clear copy of the original image. The performance of the proposed approach is evaluated by comparing the original and blurred images using the peak signal-to-noise ratio (PSNR) and structural similarity index(SSIM). After that, the camera pose is estimated using recurrent neural architecture from deblurred images or videos. The average camera pose error obtained through our approach is (0.16m, 5.61◦). In two recent research, Deep Attention and CGAPoseNet, the average pose error is (19m, 6.25◦) and (0.27m, 9.39◦), respectively. The results obtained through the proposed approach improve the current research results. As a result, some applications of indoor camera localization, such as mobile robots and guide robots, will work more accurately. Universitas Muhammadiyah Yogyakarta 2024 Article PeerReviewed application/pdf en http://eprints.utm.my/108927/1/MuhammadShamsul2024_ARecurrentDeepArchitectureforEnhancing.pdf Alam, Muhammad Shamsul and Mohamed, Farhan and Selamat, Ali and Hossain, Akm. Bellal (2024) A recurrent deep architecture for enhancing indoor camera localization using motion blur elimination. Journal of Robotics and Control (JRC), 5 (4). pp. 1028-1040. ISSN 2715-5056 https://journal.umy.ac.id/index.php/jrc/article/view/21930 NA
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
language English
topic QA75 Electronic computers. Computer science
spellingShingle QA75 Electronic computers. Computer science
Alam, Muhammad Shamsul
Mohamed, Farhan
Selamat, Ali
Hossain, Akm. Bellal
A recurrent deep architecture for enhancing indoor camera localization using motion blur elimination
description Rapid growth and technological improvements in computer vision have enabled indoor camera localization. The accurate camera localization of an indoor environment is challenging because it has many complex problems, and motion blur is one of them. Motion blur introduces significant errors, degrades the image quality, and affects feature matching, making it challenging to determine camera pose accurately. Improving the camera localization accuracy for some robotic applications is still necessary. In this study, we propose a recurrent neural network (RNN) approach to solve the indoor camera localization problem using motion blur reduction. Motion blur in an image is detected by analyzing its frequency spectrum. A low-frequency component indicates motion blur, and by investigating the direction of these low-frequency components, the location and amount of blur are estimated. Then, Wiener filtering deconvolution removes the blur and obtains a clear copy of the original image. The performance of the proposed approach is evaluated by comparing the original and blurred images using the peak signal-to-noise ratio (PSNR) and structural similarity index(SSIM). After that, the camera pose is estimated using recurrent neural architecture from deblurred images or videos. The average camera pose error obtained through our approach is (0.16m, 5.61◦). In two recent research, Deep Attention and CGAPoseNet, the average pose error is (19m, 6.25◦) and (0.27m, 9.39◦), respectively. The results obtained through the proposed approach improve the current research results. As a result, some applications of indoor camera localization, such as mobile robots and guide robots, will work more accurately.
format Article
author Alam, Muhammad Shamsul
Mohamed, Farhan
Selamat, Ali
Hossain, Akm. Bellal
author_facet Alam, Muhammad Shamsul
Mohamed, Farhan
Selamat, Ali
Hossain, Akm. Bellal
author_sort Alam, Muhammad Shamsul
title A recurrent deep architecture for enhancing indoor camera localization using motion blur elimination
title_short A recurrent deep architecture for enhancing indoor camera localization using motion blur elimination
title_full A recurrent deep architecture for enhancing indoor camera localization using motion blur elimination
title_fullStr A recurrent deep architecture for enhancing indoor camera localization using motion blur elimination
title_full_unstemmed A recurrent deep architecture for enhancing indoor camera localization using motion blur elimination
title_sort recurrent deep architecture for enhancing indoor camera localization using motion blur elimination
publisher Universitas Muhammadiyah Yogyakarta
publishDate 2024
url http://eprints.utm.my/108927/1/MuhammadShamsul2024_ARecurrentDeepArchitectureforEnhancing.pdf
http://eprints.utm.my/108927/
https://journal.umy.ac.id/index.php/jrc/article/view/21930
_version_ 1818834067216400384
score 13.235362

Similar Items