Auto-Exposure Algorithm for Enhanced Mobile Robot Localization in Challenging Light Conditions
The success of robot localization based on visual odometry (VO) largely depends on the quality of the acquired images. In challenging light conditions, specialized auto-exposure (AE) algorithms that purposely select camera exposure time and gain to maximize the image information can therefore greatl...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Multidisciplinary Digital Publishing Institute
2022
|
| Online Access: | https://hdl.handle.net/1721.1/140285 |
| _version_ | 1826208067066265600 |
|---|---|
| author | Bégin, Marc-André Hunter, Ian |
| author2 | Massachusetts Institute of Technology. Department of Mechanical Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Mechanical Engineering Bégin, Marc-André Hunter, Ian |
| author_sort | Bégin, Marc-André |
| collection | MIT |
| description | The success of robot localization based on visual odometry (VO) largely depends on the quality of the acquired images. In challenging light conditions, specialized auto-exposure (AE) algorithms that purposely select camera exposure time and gain to maximize the image information can therefore greatly improve localization performance. In this work, an AE algorithm is introduced which, unlike existing algorithms, fully leverages the camera’s photometric response function to accurately predict the optimal exposure of future frames. It also features feedback that compensates for prediction inaccuracies due to image saturation and explicitly balances motion blur and image noise effects. For validation, stereo cameras mounted on a custom-built motion table allow different AE algorithms to be benchmarked on the same repeated reference trajectory using the stereo implementation of ORB-SLAM3. Experimental evidence shows that (1) the gradient information metric appropriately serves as a proxy of indirect/feature-based VO performance; (2) the proposed prediction model based on simulated exposure changes is more accurate than using <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>γ</mi></semantics></math></inline-formula> transformations; and (3) the overall accuracy of the estimated trajectory achieved using the proposed algorithm equals or surpasses classic exposure control approaches. The source code of the algorithm and all datasets used in this work are shared openly with the robotics community. |
| first_indexed | 2024-09-23T13:59:57Z |
| format | Article |
| id | mit-1721.1/140285 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T13:59:57Z |
| publishDate | 2022 |
| publisher | Multidisciplinary Digital Publishing Institute |
| record_format | dspace |
| spelling | mit-1721.1/1402852024-06-07T17:31:01Z Auto-Exposure Algorithm for Enhanced Mobile Robot Localization in Challenging Light Conditions Bégin, Marc-André Hunter, Ian Massachusetts Institute of Technology. Department of Mechanical Engineering The success of robot localization based on visual odometry (VO) largely depends on the quality of the acquired images. In challenging light conditions, specialized auto-exposure (AE) algorithms that purposely select camera exposure time and gain to maximize the image information can therefore greatly improve localization performance. In this work, an AE algorithm is introduced which, unlike existing algorithms, fully leverages the camera’s photometric response function to accurately predict the optimal exposure of future frames. It also features feedback that compensates for prediction inaccuracies due to image saturation and explicitly balances motion blur and image noise effects. For validation, stereo cameras mounted on a custom-built motion table allow different AE algorithms to be benchmarked on the same repeated reference trajectory using the stereo implementation of ORB-SLAM3. Experimental evidence shows that (1) the gradient information metric appropriately serves as a proxy of indirect/feature-based VO performance; (2) the proposed prediction model based on simulated exposure changes is more accurate than using <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>γ</mi></semantics></math></inline-formula> transformations; and (3) the overall accuracy of the estimated trajectory achieved using the proposed algorithm equals or surpasses classic exposure control approaches. The source code of the algorithm and all datasets used in this work are shared openly with the robotics community. 2022-02-11T16:21:05Z 2022-02-11T16:21:05Z 2022-01-22 2022-02-11T14:46:17Z Article http://purl.org/eprint/type/JournalArticle 1424-8220 https://hdl.handle.net/1721.1/140285 Bégin, M.-A.; Hunter, I. Auto-Exposure Algorithm for Enhanced Mobile Robot Localization in Challenging Light Conditions. Sensors 22 (3): 835 (2022) http://dx.doi.org/10.3390/s22030835 Sensors Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ application/pdf Multidisciplinary Digital Publishing Institute Multidisciplinary Digital Publishing Institute |
| spellingShingle | Bégin, Marc-André Hunter, Ian Auto-Exposure Algorithm for Enhanced Mobile Robot Localization in Challenging Light Conditions |
| title | Auto-Exposure Algorithm for Enhanced Mobile Robot Localization in Challenging Light Conditions |
| title_full | Auto-Exposure Algorithm for Enhanced Mobile Robot Localization in Challenging Light Conditions |
| title_fullStr | Auto-Exposure Algorithm for Enhanced Mobile Robot Localization in Challenging Light Conditions |
| title_full_unstemmed | Auto-Exposure Algorithm for Enhanced Mobile Robot Localization in Challenging Light Conditions |
| title_short | Auto-Exposure Algorithm for Enhanced Mobile Robot Localization in Challenging Light Conditions |
| title_sort | auto exposure algorithm for enhanced mobile robot localization in challenging light conditions |
| url | https://hdl.handle.net/1721.1/140285 |
| work_keys_str_mv | AT beginmarcandre autoexposurealgorithmforenhancedmobilerobotlocalizationinchallenginglightconditions AT hunterian autoexposurealgorithmforenhancedmobilerobotlocalizationinchallenginglightconditions |