Novel Descattering Approach for Stereo Vision in Dense Suspended Scatterer Environments
In this paper, we propose a model-based scattering removal method for stereo vision for robot manipulation in indoor scattering media where the commonly used ranging sensors are unable to work. Stereo vision is an inherently ill-posed and challenging problem. It is even more difficult in the case of...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/17/6/1425 |
| _version_ | 1811186519178739712 |
|---|---|
| author | Chanh D. Tr. Nguyen Jihyuk Park Kyeong-Yong Cho Kyung-Soo Kim Soohyun Kim |
| author_facet | Chanh D. Tr. Nguyen Jihyuk Park Kyeong-Yong Cho Kyung-Soo Kim Soohyun Kim |
| author_sort | Chanh D. Tr. Nguyen |
| collection | DOAJ |
| description | In this paper, we propose a model-based scattering removal method for stereo vision for robot manipulation in indoor scattering media where the commonly used ranging sensors are unable to work. Stereo vision is an inherently ill-posed and challenging problem. It is even more difficult in the case of images of dense fog or dense steam scenes illuminated by active light sources. Images taken in such environments suffer attenuation of object radiance and scattering of the active light sources. To solve this problem, we first derive the imaging model for images taken in a dense scattering medium with a single active illumination close to the cameras. Based on this physical model, the non-uniform backscattering signal is efficiently removed. The descattered images are then utilized as the input images of stereo vision. The performance of the method is evaluated based on the quality of the depth map from stereo vision. We also demonstrate the effectiveness of the proposed method by carrying out the real robot manipulation task. |
| first_indexed | 2024-04-11T13:46:50Z |
| format | Article |
| id | doaj.art-fd125d217b1c427baf5b100664efb0ad |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T13:46:50Z |
| publishDate | 2017-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-fd125d217b1c427baf5b100664efb0ad2022-12-22T04:21:00ZengMDPI AGSensors1424-82202017-06-01176142510.3390/s17061425s17061425Novel Descattering Approach for Stereo Vision in Dense Suspended Scatterer EnvironmentsChanh D. Tr. Nguyen0Jihyuk Park1Kyeong-Yong Cho2Kyung-Soo Kim3Soohyun Kim4Department of Mechanical Engineering, KAIST, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Korea;Department of Mechanical Engineering, KAIST, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Korea;Unmanned Safety Robot Research Center, KAIST, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Korea;Department of Mechanical Engineering, KAIST, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Korea;Department of Mechanical Engineering, KAIST, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Korea;In this paper, we propose a model-based scattering removal method for stereo vision for robot manipulation in indoor scattering media where the commonly used ranging sensors are unable to work. Stereo vision is an inherently ill-posed and challenging problem. It is even more difficult in the case of images of dense fog or dense steam scenes illuminated by active light sources. Images taken in such environments suffer attenuation of object radiance and scattering of the active light sources. To solve this problem, we first derive the imaging model for images taken in a dense scattering medium with a single active illumination close to the cameras. Based on this physical model, the non-uniform backscattering signal is efficiently removed. The descattered images are then utilized as the input images of stereo vision. The performance of the method is evaluated based on the quality of the depth map from stereo vision. We also demonstrate the effectiveness of the proposed method by carrying out the real robot manipulation task.http://www.mdpi.com/1424-8220/17/6/1425low visibilitybackscatteringdescatteringdefoggingstereo vision |
| spellingShingle | Chanh D. Tr. Nguyen Jihyuk Park Kyeong-Yong Cho Kyung-Soo Kim Soohyun Kim Novel Descattering Approach for Stereo Vision in Dense Suspended Scatterer Environments Sensors low visibility backscattering descattering defogging stereo vision |
| title | Novel Descattering Approach for Stereo Vision in Dense Suspended Scatterer Environments |
| title_full | Novel Descattering Approach for Stereo Vision in Dense Suspended Scatterer Environments |
| title_fullStr | Novel Descattering Approach for Stereo Vision in Dense Suspended Scatterer Environments |
| title_full_unstemmed | Novel Descattering Approach for Stereo Vision in Dense Suspended Scatterer Environments |
| title_short | Novel Descattering Approach for Stereo Vision in Dense Suspended Scatterer Environments |
| title_sort | novel descattering approach for stereo vision in dense suspended scatterer environments |
| topic | low visibility backscattering descattering defogging stereo vision |
| url | http://www.mdpi.com/1424-8220/17/6/1425 |
| work_keys_str_mv | AT chanhdtrnguyen noveldescatteringapproachforstereovisionindensesuspendedscattererenvironments AT jihyukpark noveldescatteringapproachforstereovisionindensesuspendedscattererenvironments AT kyeongyongcho noveldescatteringapproachforstereovisionindensesuspendedscattererenvironments AT kyungsookim noveldescatteringapproachforstereovisionindensesuspendedscattererenvironments AT soohyunkim noveldescatteringapproachforstereovisionindensesuspendedscattererenvironments |