Camera Absolute Pose Estimation Using Hierarchical Attention in Multi-Scene
The multi-scene camera pose estimation approach aims to recover the camera pose from any given scene, catering to the demands of real-life mobile devices to perform tasks. Facing the challenge that it is difficult to extract efficient features in training multi-scene models, we present a modified mo...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10847815/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832542601458221056 |
|---|---|
| author | Xinhua Lu Jingui Miao Qingji Xue Hui Wan Hao Zhang |
| author_facet | Xinhua Lu Jingui Miao Qingji Xue Hui Wan Hao Zhang |
| author_sort | Xinhua Lu |
| collection | DOAJ |
| description | The multi-scene camera pose estimation approach aims to recover the camera pose from any given scene, catering to the demands of real-life mobile devices to perform tasks. Facing the challenge that it is difficult to extract efficient features in training multi-scene models, we present a modified model named Hierarchical Attention Absolute Pose Regression(H-AttnAPR) which can obtain different scales of feature dependencies. A Hierarchical Attention(HA) module is introduced prior to the scene classification module, where it captures both intra- and inter-correlations among image patches, utilizing both local and global key information from images to restore the absolute camera pose without the need for additional point cloud data. H-AttnAPR efficiently models global dependencies without compromising fine-grained feature information. Therefore, it overcomes the limitations that solely focus on long-range pixel-level feature dependencies within images while neglecting local patches of image feature dependencies. Our approach has been validated on the 7Scenes and Cambridge benchmark datasets. Compared to the baseline algorithm PoseNet, our algorithm has achieved a 41.1% reduction in translation error and a 61.1% decrease in rotation error, demonstrating superior performance in multi-scene absolute camera pose regression. |
| format | Article |
| id | doaj-art-b340b16eb1044fa888bf0f1f6c023cb7 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-b340b16eb1044fa888bf0f1f6c023cb72025-02-04T00:00:42ZengIEEEIEEE Access2169-35362025-01-0113196241963410.1109/ACCESS.2025.353189610847815Camera Absolute Pose Estimation Using Hierarchical Attention in Multi-SceneXinhua Lu0https://orcid.org/0000-0002-2338-7020Jingui Miao1https://orcid.org/0009-0004-0506-9063Qingji Xue2Hui Wan3https://orcid.org/0009-0001-3823-6399Hao Zhang4https://orcid.org/0009-0002-2784-1355Electronic Information Institute, Nanyang Institute of Technology, Nanyang, ChinaSchool of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, ChinaElectronic Information Institute, Nanyang Institute of Technology, Nanyang, ChinaSchool of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, ChinaSchool of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, ChinaThe multi-scene camera pose estimation approach aims to recover the camera pose from any given scene, catering to the demands of real-life mobile devices to perform tasks. Facing the challenge that it is difficult to extract efficient features in training multi-scene models, we present a modified model named Hierarchical Attention Absolute Pose Regression(H-AttnAPR) which can obtain different scales of feature dependencies. A Hierarchical Attention(HA) module is introduced prior to the scene classification module, where it captures both intra- and inter-correlations among image patches, utilizing both local and global key information from images to restore the absolute camera pose without the need for additional point cloud data. H-AttnAPR efficiently models global dependencies without compromising fine-grained feature information. Therefore, it overcomes the limitations that solely focus on long-range pixel-level feature dependencies within images while neglecting local patches of image feature dependencies. Our approach has been validated on the 7Scenes and Cambridge benchmark datasets. Compared to the baseline algorithm PoseNet, our algorithm has achieved a 41.1% reduction in translation error and a 61.1% decrease in rotation error, demonstrating superior performance in multi-scene absolute camera pose regression.https://ieeexplore.ieee.org/document/10847815/Image processingpose estimationattention mechanismsfeature extractiondeep learning |
| spellingShingle | Xinhua Lu Jingui Miao Qingji Xue Hui Wan Hao Zhang Camera Absolute Pose Estimation Using Hierarchical Attention in Multi-Scene IEEE Access Image processing pose estimation attention mechanisms feature extraction deep learning |
| title | Camera Absolute Pose Estimation Using Hierarchical Attention in Multi-Scene |
| title_full | Camera Absolute Pose Estimation Using Hierarchical Attention in Multi-Scene |
| title_fullStr | Camera Absolute Pose Estimation Using Hierarchical Attention in Multi-Scene |
| title_full_unstemmed | Camera Absolute Pose Estimation Using Hierarchical Attention in Multi-Scene |
| title_short | Camera Absolute Pose Estimation Using Hierarchical Attention in Multi-Scene |
| title_sort | camera absolute pose estimation using hierarchical attention in multi scene |
| topic | Image processing pose estimation attention mechanisms feature extraction deep learning |
| url | https://ieeexplore.ieee.org/document/10847815/ |
| work_keys_str_mv | AT xinhualu cameraabsoluteposeestimationusinghierarchicalattentioninmultiscene AT jinguimiao cameraabsoluteposeestimationusinghierarchicalattentioninmultiscene AT qingjixue cameraabsoluteposeestimationusinghierarchicalattentioninmultiscene AT huiwan cameraabsoluteposeestimationusinghierarchicalattentioninmultiscene AT haozhang cameraabsoluteposeestimationusinghierarchicalattentioninmultiscene |