EPI Light Field Depth Estimation Based on a Directional Relationship Model and Multiviewpoint Attention Mechanism
Light field (LF) image depth estimation is a critical technique for LF-related applications such as 3D reconstruction, target detection, and tracking. The refocusing property of LF images provide rich information for depth estimations; however, it is still challenging in cases of occlusion regions,...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/16/6291 |
| _version_ | 1797442004601274368 |
|---|---|
| author | Ming Gao Huiping Deng Sen Xiang Jin Wu Zeyang He |
| author_facet | Ming Gao Huiping Deng Sen Xiang Jin Wu Zeyang He |
| author_sort | Ming Gao |
| collection | DOAJ |
| description | Light field (LF) image depth estimation is a critical technique for LF-related applications such as 3D reconstruction, target detection, and tracking. The refocusing property of LF images provide rich information for depth estimations; however, it is still challenging in cases of occlusion regions, edge regions, noise interference, etc. The epipolar plane image (EPI) of LF can effectively deal with the depth estimation because of its characteristics of multidirectionality and pixel consistency—in which the LF depth estimations are converted to calculate the EPI slope. This paper proposed an EPI LF depth estimation algorithm based on a directional relationship model and attention mechanism. Unlike the subaperture LF depth estimation method, the proposed method takes EPIs as input images. Specifically, a directional relationship model was used to extract direction features of the horizontal and vertical EPIs, respectively. Then, a multiviewpoint attention mechanism combining channel attention and spatial attention is used to give more weight to the EPI slope information. Subsequently, multiple residual modules are used to eliminate the redundant features that interfere with the EPI slope information—in which a small stride convolution operation is used to avoid losing key EPI slope information. The experimental results revealed that the proposed algorithm outperformed the compared algorithms in terms of accuracy. |
| first_indexed | 2024-03-09T12:35:32Z |
| format | Article |
| id | doaj.art-08a4a441e549481cbe8b5b3e09042bf2 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T12:35:32Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-08a4a441e549481cbe8b5b3e09042bf22023-11-30T22:24:31ZengMDPI AGSensors1424-82202022-08-012216629110.3390/s22166291EPI Light Field Depth Estimation Based on a Directional Relationship Model and Multiviewpoint Attention MechanismMing Gao0Huiping Deng1Sen Xiang2Jin Wu3Zeyang He4School of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, ChinaSchool of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, ChinaSchool of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, ChinaSchool of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, ChinaSchool of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, ChinaLight field (LF) image depth estimation is a critical technique for LF-related applications such as 3D reconstruction, target detection, and tracking. The refocusing property of LF images provide rich information for depth estimations; however, it is still challenging in cases of occlusion regions, edge regions, noise interference, etc. The epipolar plane image (EPI) of LF can effectively deal with the depth estimation because of its characteristics of multidirectionality and pixel consistency—in which the LF depth estimations are converted to calculate the EPI slope. This paper proposed an EPI LF depth estimation algorithm based on a directional relationship model and attention mechanism. Unlike the subaperture LF depth estimation method, the proposed method takes EPIs as input images. Specifically, a directional relationship model was used to extract direction features of the horizontal and vertical EPIs, respectively. Then, a multiviewpoint attention mechanism combining channel attention and spatial attention is used to give more weight to the EPI slope information. Subsequently, multiple residual modules are used to eliminate the redundant features that interfere with the EPI slope information—in which a small stride convolution operation is used to avoid losing key EPI slope information. The experimental results revealed that the proposed algorithm outperformed the compared algorithms in terms of accuracy.https://www.mdpi.com/1424-8220/22/16/6291light field imagesdepth estimationepipolar plane imagepixel consistencyattention mechanism |
| spellingShingle | Ming Gao Huiping Deng Sen Xiang Jin Wu Zeyang He EPI Light Field Depth Estimation Based on a Directional Relationship Model and Multiviewpoint Attention Mechanism Sensors light field images depth estimation epipolar plane image pixel consistency attention mechanism |
| title | EPI Light Field Depth Estimation Based on a Directional Relationship Model and Multiviewpoint Attention Mechanism |
| title_full | EPI Light Field Depth Estimation Based on a Directional Relationship Model and Multiviewpoint Attention Mechanism |
| title_fullStr | EPI Light Field Depth Estimation Based on a Directional Relationship Model and Multiviewpoint Attention Mechanism |
| title_full_unstemmed | EPI Light Field Depth Estimation Based on a Directional Relationship Model and Multiviewpoint Attention Mechanism |
| title_short | EPI Light Field Depth Estimation Based on a Directional Relationship Model and Multiviewpoint Attention Mechanism |
| title_sort | epi light field depth estimation based on a directional relationship model and multiviewpoint attention mechanism |
| topic | light field images depth estimation epipolar plane image pixel consistency attention mechanism |
| url | https://www.mdpi.com/1424-8220/22/16/6291 |
| work_keys_str_mv | AT minggao epilightfielddepthestimationbasedonadirectionalrelationshipmodelandmultiviewpointattentionmechanism AT huipingdeng epilightfielddepthestimationbasedonadirectionalrelationshipmodelandmultiviewpointattentionmechanism AT senxiang epilightfielddepthestimationbasedonadirectionalrelationshipmodelandmultiviewpointattentionmechanism AT jinwu epilightfielddepthestimationbasedonadirectionalrelationshipmodelandmultiviewpointattentionmechanism AT zeyanghe epilightfielddepthestimationbasedonadirectionalrelationshipmodelandmultiviewpointattentionmechanism |