Depth Estimation of Non-Rigid Objects For Time-Of-Flight Imaging
Depth sensing is useful for a variety of applications that range from augmented reality to robotics. Time-of-flight (TOF) cameras are appealing because they obtain dense depth measurements with low latency. However, for reasons ranging from power constraints to multi-camera interference, the frequen...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2018
|
| Online Access: | http://hdl.handle.net/1721.1/119397 https://orcid.org/0000-0001-8552-7458 https://orcid.org/0000-0003-4841-3990 |
| _version_ | 1826196867128492032 |
|---|---|
| author | Noraky, James Sze, Vivienne |
| author2 | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
| author_facet | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Noraky, James Sze, Vivienne |
| author_sort | Noraky, James |
| collection | MIT |
| description | Depth sensing is useful for a variety of applications that range from augmented reality to robotics. Time-of-flight (TOF) cameras are appealing because they obtain dense depth measurements with low latency. However, for reasons ranging from power constraints to multi-camera interference, the frequency at which accurate depth measurements can be obtained is reduced. To address this, we propose an algorithm that uses concurrently collected images to estimate the depth of non-rigid objects without using the TOF camera. Our technique models non-rigid objects as locally rigid and uses previous depth measurements along with the optical flow of the images to estimate depth. In particular, we show how we exploit the previous depth measurements to directly estimate pose and how we integrate this with our model to estimate the depth of non-rigid objects by finding the solution to a sparse linear system. We evaluate our technique on a RGB-D dataset of deformable objects, where we estimate depth with a mean relative error of 0.37% and outperform other adapted techniques. |
| first_indexed | 2024-09-23T10:38:55Z |
| format | Article |
| id | mit-1721.1/119397 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T10:38:55Z |
| publishDate | 2018 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1193972022-09-30T22:02:40Z Depth Estimation of Non-Rigid Objects For Time-Of-Flight Imaging Noraky, James Sze, Vivienne Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology. Microsystems Technology Laboratories Sze, Vivienne Noraky, James Sze, Vivienne Depth sensing is useful for a variety of applications that range from augmented reality to robotics. Time-of-flight (TOF) cameras are appealing because they obtain dense depth measurements with low latency. However, for reasons ranging from power constraints to multi-camera interference, the frequency at which accurate depth measurements can be obtained is reduced. To address this, we propose an algorithm that uses concurrently collected images to estimate the depth of non-rigid objects without using the TOF camera. Our technique models non-rigid objects as locally rigid and uses previous depth measurements along with the optical flow of the images to estimate depth. In particular, we show how we exploit the previous depth measurements to directly estimate pose and how we integrate this with our model to estimate the depth of non-rigid objects by finding the solution to a sparse linear system. We evaluate our technique on a RGB-D dataset of deformable objects, where we estimate depth with a mean relative error of 0.37% and outperform other adapted techniques. 2018-12-03T19:02:28Z 2018-12-03T19:02:28Z 2018-10 Article http://purl.org/eprint/type/ConferencePaper 978-1-4673-9961-6 2381-8549 http://hdl.handle.net/1721.1/119397 Noraky, James and Vivienne Sze. "Depth Estimation of Non-Rigid Objects For Time-Of-Flight Imaging." ICIP 2018: 2925-2929. https://orcid.org/0000-0001-8552-7458 https://orcid.org/0000-0003-4841-3990 en_US IEEE International Conference on Image Processing (ICIP) Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) Prof. Sze |
| spellingShingle | Noraky, James Sze, Vivienne Depth Estimation of Non-Rigid Objects For Time-Of-Flight Imaging |
| title | Depth Estimation of Non-Rigid Objects For Time-Of-Flight Imaging |
| title_full | Depth Estimation of Non-Rigid Objects For Time-Of-Flight Imaging |
| title_fullStr | Depth Estimation of Non-Rigid Objects For Time-Of-Flight Imaging |
| title_full_unstemmed | Depth Estimation of Non-Rigid Objects For Time-Of-Flight Imaging |
| title_short | Depth Estimation of Non-Rigid Objects For Time-Of-Flight Imaging |
| title_sort | depth estimation of non rigid objects for time of flight imaging |
| url | http://hdl.handle.net/1721.1/119397 https://orcid.org/0000-0001-8552-7458 https://orcid.org/0000-0003-4841-3990 |
| work_keys_str_mv | AT norakyjames depthestimationofnonrigidobjectsfortimeofflightimaging AT szevivienne depthestimationofnonrigidobjectsfortimeofflightimaging |