PlaneSDF-Based Change Detection for Long-Term Dense Mapping
The ability to process environment maps across multiple sessions is critical for robots operating over extended periods of time. Specifically, it is desirable for autonomous agents to detect changes amongst maps of different sessions so as to gain a conflict-free understanding of the current environ...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/1721.1/153752 |
| _version_ | 1824458238132748288 |
|---|---|
| author | Fu, Jiahui Lin, Chengyuan Taguchi, Yuichi Cohen, Andrea Zhang, Yifu Mylabathula, Stephen Leonard, John J. |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Fu, Jiahui Lin, Chengyuan Taguchi, Yuichi Cohen, Andrea Zhang, Yifu Mylabathula, Stephen Leonard, John J. |
| author_sort | Fu, Jiahui |
| collection | MIT |
| description | The ability to process environment maps across multiple sessions is critical for robots operating over extended periods of time. Specifically, it is desirable for autonomous agents to detect changes amongst maps of different sessions so as to gain a conflict-free understanding of the current environment. In this letter, we look into the problem of change detection based on a novel map representation, dubbed Plane Signed Distance Fields (PlaneSDF), where dense maps are represented as a collection of planes and their associated geometric components in SDF volumes. Given point clouds of the source and target scenes, we propose a three-step PlaneSDF-based change detection approach: (1) PlaneSDF volumes are instantiated within each scene and registered across scenes using plane poses; 2D height maps and object maps are extracted per volume via height projection and connected component analysis. (2) Height maps are compared and intersected with the object map to produce a 2D change location mask for changed object candidates in the source scene. (3) 3D geometric validation is performed using SDF-derived features per object candidate for change mask refinement. We evaluate our approach on both synthetic and real-world datasets and demonstrate its effectiveness via the task of changed object detection. |
| first_indexed | 2024-09-23T13:31:29Z |
| format | Article |
| id | mit-1721.1/153752 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2025-02-19T04:22:43Z |
| publishDate | 2024 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1537522024-11-05T15:14:12Z PlaneSDF-Based Change Detection for Long-Term Dense Mapping Fu, Jiahui Lin, Chengyuan Taguchi, Yuichi Cohen, Andrea Zhang, Yifu Mylabathula, Stephen Leonard, John J. Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Artificial Intelligence Control and Optimization Computer Science Applications Computer Vision and Pattern Recognition Mechanical Engineering Human-Computer Interaction Biomedical Engineering Control and Systems Engineering The ability to process environment maps across multiple sessions is critical for robots operating over extended periods of time. Specifically, it is desirable for autonomous agents to detect changes amongst maps of different sessions so as to gain a conflict-free understanding of the current environment. In this letter, we look into the problem of change detection based on a novel map representation, dubbed Plane Signed Distance Fields (PlaneSDF), where dense maps are represented as a collection of planes and their associated geometric components in SDF volumes. Given point clouds of the source and target scenes, we propose a three-step PlaneSDF-based change detection approach: (1) PlaneSDF volumes are instantiated within each scene and registered across scenes using plane poses; 2D height maps and object maps are extracted per volume via height projection and connected component analysis. (2) Height maps are compared and intersected with the object map to produce a 2D change location mask for changed object candidates in the source scene. (3) 3D geometric validation is performed using SDF-derived features per object candidate for change mask refinement. We evaluate our approach on both synthetic and real-world datasets and demonstrate its effectiveness via the task of changed object detection. 2024-03-14T16:07:44Z 2024-03-14T16:07:44Z 2022-10 2024-03-14T15:59:15Z Article http://purl.org/eprint/type/JournalArticle 2377-3766 2377-3774 https://hdl.handle.net/1721.1/153752 J. Fu et al., "PlaneSDF-Based Change Detection for Long-Term Dense Mapping," in IEEE Robotics and Automation Letters, vol. 7, no. 4, pp. 9667-9674, Oct. 2022. en 10.1109/lra.2022.3191794 IEEE Robotics and Automation Letters Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) IEEE |
| spellingShingle | Artificial Intelligence Control and Optimization Computer Science Applications Computer Vision and Pattern Recognition Mechanical Engineering Human-Computer Interaction Biomedical Engineering Control and Systems Engineering Fu, Jiahui Lin, Chengyuan Taguchi, Yuichi Cohen, Andrea Zhang, Yifu Mylabathula, Stephen Leonard, John J. PlaneSDF-Based Change Detection for Long-Term Dense Mapping |
| title | PlaneSDF-Based Change Detection for Long-Term Dense Mapping |
| title_full | PlaneSDF-Based Change Detection for Long-Term Dense Mapping |
| title_fullStr | PlaneSDF-Based Change Detection for Long-Term Dense Mapping |
| title_full_unstemmed | PlaneSDF-Based Change Detection for Long-Term Dense Mapping |
| title_short | PlaneSDF-Based Change Detection for Long-Term Dense Mapping |
| title_sort | planesdf based change detection for long term dense mapping |
| topic | Artificial Intelligence Control and Optimization Computer Science Applications Computer Vision and Pattern Recognition Mechanical Engineering Human-Computer Interaction Biomedical Engineering Control and Systems Engineering |
| url | https://hdl.handle.net/1721.1/153752 |
| work_keys_str_mv | AT fujiahui planesdfbasedchangedetectionforlongtermdensemapping AT linchengyuan planesdfbasedchangedetectionforlongtermdensemapping AT taguchiyuichi planesdfbasedchangedetectionforlongtermdensemapping AT cohenandrea planesdfbasedchangedetectionforlongtermdensemapping AT zhangyifu planesdfbasedchangedetectionforlongtermdensemapping AT mylabathulastephen planesdfbasedchangedetectionforlongtermdensemapping AT leonardjohnj planesdfbasedchangedetectionforlongtermdensemapping |