Robust camera pose estimation by viewpoint classification using deep learning
Abstract Camera pose estimation with respect to target scenes is an important technology for superimposing virtual information in augmented reality (AR). However, it is difficult to estimate the camera pose for all possible view angles because feature descriptors such as SIFT are not completely inva...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2016-12-01
|
| Series: | Computational Visual Media |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1007/s41095-016-0067-z |
| _version_ | 1811322347942051840 |
|---|---|
| author | Yoshikatsu Nakajima Hideo Saito |
| author_facet | Yoshikatsu Nakajima Hideo Saito |
| author_sort | Yoshikatsu Nakajima |
| collection | DOAJ |
| description | Abstract Camera pose estimation with respect to target scenes is an important technology for superimposing virtual information in augmented reality (AR). However, it is difficult to estimate the camera pose for all possible view angles because feature descriptors such as SIFT are not completely invariant from every perspective. We propose a novel method of robust camera pose estimation using multiple feature descriptor databases generated for each partitioned viewpoint, in which the feature descriptor of each keypoint is almost invariant. Our method estimates the viewpoint class for each input image using deep learning based on a set of training images prepared for each viewpoint class. We give two ways to prepare these images for deep learning and generating databases. In the first method, images are generated using a projection matrix to ensure robust learning in a range of environments with changing backgrounds. The second method uses real images to learn a given environment around a planar pattern. Our evaluation results confirm that our approach increases the number of correct matches and the accuracy of camera pose estimation compared to the conventional method. |
| first_indexed | 2024-04-13T13:33:43Z |
| format | Article |
| id | doaj.art-5cc151e3a53440c29ceebe0473ced07c |
| institution | Directory Open Access Journal |
| issn | 2096-0433 2096-0662 |
| language | English |
| last_indexed | 2024-04-13T13:33:43Z |
| publishDate | 2016-12-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Computational Visual Media |
| spelling | doaj.art-5cc151e3a53440c29ceebe0473ced07c2022-12-22T02:44:51ZengSpringerOpenComputational Visual Media2096-04332096-06622016-12-013218919810.1007/s41095-016-0067-zRobust camera pose estimation by viewpoint classification using deep learningYoshikatsu Nakajima0Hideo Saito1Department of Science and Technology, Keio UniversityDepartment of Science and Technology, Keio UniversityAbstract Camera pose estimation with respect to target scenes is an important technology for superimposing virtual information in augmented reality (AR). However, it is difficult to estimate the camera pose for all possible view angles because feature descriptors such as SIFT are not completely invariant from every perspective. We propose a novel method of robust camera pose estimation using multiple feature descriptor databases generated for each partitioned viewpoint, in which the feature descriptor of each keypoint is almost invariant. Our method estimates the viewpoint class for each input image using deep learning based on a set of training images prepared for each viewpoint class. We give two ways to prepare these images for deep learning and generating databases. In the first method, images are generated using a projection matrix to ensure robust learning in a range of environments with changing backgrounds. The second method uses real images to learn a given environment around a planar pattern. Our evaluation results confirm that our approach increases the number of correct matches and the accuracy of camera pose estimation compared to the conventional method.http://link.springer.com/article/10.1007/s41095-016-0067-zpose estimationaugmented reality (AR)deep learningconvolutional neural network |
| spellingShingle | Yoshikatsu Nakajima Hideo Saito Robust camera pose estimation by viewpoint classification using deep learning Computational Visual Media pose estimation augmented reality (AR) deep learning convolutional neural network |
| title | Robust camera pose estimation by viewpoint classification using deep learning |
| title_full | Robust camera pose estimation by viewpoint classification using deep learning |
| title_fullStr | Robust camera pose estimation by viewpoint classification using deep learning |
| title_full_unstemmed | Robust camera pose estimation by viewpoint classification using deep learning |
| title_short | Robust camera pose estimation by viewpoint classification using deep learning |
| title_sort | robust camera pose estimation by viewpoint classification using deep learning |
| topic | pose estimation augmented reality (AR) deep learning convolutional neural network |
| url | http://link.springer.com/article/10.1007/s41095-016-0067-z |
| work_keys_str_mv | AT yoshikatsunakajima robustcameraposeestimationbyviewpointclassificationusingdeeplearning AT hideosaito robustcameraposeestimationbyviewpointclassificationusingdeeplearning |