A Review of Recurrent Neural Network Based Camera Localization for Indoor Environments
Camera localization involves the estimation of the camera pose of an image from a random scene. We used a single image or sequence of images or videos as the input. The output depends on the representation of the scene and method used. Several computer vision applications, such as robot navigation a...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10114389/ |
| _version_ | 1797829123139174400 |
|---|---|
| author | Muhammad Shamsul Alam Farhan Bin Mohamed Ali Selamat Akm Bellal Hossain |
| author_facet | Muhammad Shamsul Alam Farhan Bin Mohamed Ali Selamat Akm Bellal Hossain |
| author_sort | Muhammad Shamsul Alam |
| collection | DOAJ |
| description | Camera localization involves the estimation of the camera pose of an image from a random scene. We used a single image or sequence of images or videos as the input. The output depends on the representation of the scene and method used. Several computer vision applications, such as robot navigation and safety inspection, can benefit from camera localization. Camera localization is used to determine the position of an object on the camera in an image containing multiple images in a sequence. Structure-based localization techniques have achieved considerable success owing to a combination of image matching and coordinate regression. Absolute and relative pose regression techniques can provide end-to-end learning; however, they exhibit poor accuracies. Despite the rapid growth in computer vision, there has been no thorough review of the categorization, evaluation, and synthesis of structures and regression-based techniques. Input format and loss strategies for recurrent neural networks (RNN) have not been adequately described in the literature. The main topic is indoor camera pose regression, which is a part of the camera localization techniques. First, we discuss certain application areas for camera localization. We then discuss different camera localization techniques, such as feature and structure-based, absolute and relative pose regression techniques, and simultaneous localization and mapping (SLAM). We evaluated the frequently used datasets and qualitatively compared the absolute and relative camera pose estimation approaches. Finally, we discuss potential directions for future research, such as optimizing the computational cost of the features and evaluating the end-to-end characteristics of multiple cameras. |
| first_indexed | 2024-04-09T13:15:25Z |
| format | Article |
| id | doaj.art-3d2aaad77efc445db79ed9fded7f4856 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-09T13:15:25Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-3d2aaad77efc445db79ed9fded7f48562023-05-11T23:00:12ZengIEEEIEEE Access2169-35362023-01-0111439854400910.1109/ACCESS.2023.327247910114389A Review of Recurrent Neural Network Based Camera Localization for Indoor EnvironmentsMuhammad Shamsul Alam0https://orcid.org/0000-0002-9419-3928Farhan Bin Mohamed1https://orcid.org/0000-0002-5298-8642Ali Selamat2https://orcid.org/0000-0001-9746-8459Akm Bellal Hossain3Department of Emergent Computing, School of Computing, Faculty of Engineering, Universiti Teknologi Malaysia, Johor Bahru, Johor, MalaysiaDepartment of Emergent Computing, School of Computing, Faculty of Engineering, Universiti Teknologi Malaysia, Johor Bahru, Johor, MalaysiaMalaysia-Japan International Institute of Technology (MJIIT), Universiti Teknologi Malaysia, Kuala Lumpur, MalaysiaDepartment of Emergent Computing, School of Computing, Faculty of Engineering, Universiti Teknologi Malaysia, Johor Bahru, Johor, MalaysiaCamera localization involves the estimation of the camera pose of an image from a random scene. We used a single image or sequence of images or videos as the input. The output depends on the representation of the scene and method used. Several computer vision applications, such as robot navigation and safety inspection, can benefit from camera localization. Camera localization is used to determine the position of an object on the camera in an image containing multiple images in a sequence. Structure-based localization techniques have achieved considerable success owing to a combination of image matching and coordinate regression. Absolute and relative pose regression techniques can provide end-to-end learning; however, they exhibit poor accuracies. Despite the rapid growth in computer vision, there has been no thorough review of the categorization, evaluation, and synthesis of structures and regression-based techniques. Input format and loss strategies for recurrent neural networks (RNN) have not been adequately described in the literature. The main topic is indoor camera pose regression, which is a part of the camera localization techniques. First, we discuss certain application areas for camera localization. We then discuss different camera localization techniques, such as feature and structure-based, absolute and relative pose regression techniques, and simultaneous localization and mapping (SLAM). We evaluated the frequently used datasets and qualitatively compared the absolute and relative camera pose estimation approaches. Finally, we discuss potential directions for future research, such as optimizing the computational cost of the features and evaluating the end-to-end characteristics of multiple cameras.https://ieeexplore.ieee.org/document/10114389/Camera pose regressionabsolute pose regressionindoor positioningcamera localizationrobot navigationSLAM |
| spellingShingle | Muhammad Shamsul Alam Farhan Bin Mohamed Ali Selamat Akm Bellal Hossain A Review of Recurrent Neural Network Based Camera Localization for Indoor Environments IEEE Access Camera pose regression absolute pose regression indoor positioning camera localization robot navigation SLAM |
| title | A Review of Recurrent Neural Network Based Camera Localization for Indoor Environments |
| title_full | A Review of Recurrent Neural Network Based Camera Localization for Indoor Environments |
| title_fullStr | A Review of Recurrent Neural Network Based Camera Localization for Indoor Environments |
| title_full_unstemmed | A Review of Recurrent Neural Network Based Camera Localization for Indoor Environments |
| title_short | A Review of Recurrent Neural Network Based Camera Localization for Indoor Environments |
| title_sort | review of recurrent neural network based camera localization for indoor environments |
| topic | Camera pose regression absolute pose regression indoor positioning camera localization robot navigation SLAM |
| url | https://ieeexplore.ieee.org/document/10114389/ |
| work_keys_str_mv | AT muhammadshamsulalam areviewofrecurrentneuralnetworkbasedcameralocalizationforindoorenvironments AT farhanbinmohamed areviewofrecurrentneuralnetworkbasedcameralocalizationforindoorenvironments AT aliselamat areviewofrecurrentneuralnetworkbasedcameralocalizationforindoorenvironments AT akmbellalhossain areviewofrecurrentneuralnetworkbasedcameralocalizationforindoorenvironments AT muhammadshamsulalam reviewofrecurrentneuralnetworkbasedcameralocalizationforindoorenvironments AT farhanbinmohamed reviewofrecurrentneuralnetworkbasedcameralocalizationforindoorenvironments AT aliselamat reviewofrecurrentneuralnetworkbasedcameralocalizationforindoorenvironments AT akmbellalhossain reviewofrecurrentneuralnetworkbasedcameralocalizationforindoorenvironments |