Learning object boundary detection from motion data
A significant barrier to applying the techniques of machine learning to the domain of object boundary detection is the need to obtain a large database of correctly labeled examples. Inspired by developmental psychology, this paper proposes that boundary detection can be learned from the output of a...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | en_US |
| Published: |
2003
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/3686 |
| _version_ | 1811091840951123968 |
|---|---|
| author | Ross, Michael G. Kaelbling, Leslie P. |
| author_facet | Ross, Michael G. Kaelbling, Leslie P. |
| author_sort | Ross, Michael G. |
| collection | MIT |
| description | A significant barrier to applying the techniques of machine learning to the domain of object boundary detection is the need to obtain a large database of correctly labeled examples. Inspired by developmental psychology, this paper proposes that boundary detection can be learned from the output of a motion tracking algorithm that separates moving objects from their static surroundings. Motion segmentation solves the database problem by providing cheap, unlimited, labeled training data. A probabilistic model of the textural and shape properties of object boundaries can be trained from this data and then used to efficiently detect boundaries in novel images via loopy belief propagation. |
| first_indexed | 2024-09-23T15:08:53Z |
| format | Article |
| id | mit-1721.1/3686 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T15:08:53Z |
| publishDate | 2003 |
| record_format | dspace |
| spelling | mit-1721.1/36862019-04-12T08:36:04Z Learning object boundary detection from motion data Ross, Michael G. Kaelbling, Leslie P. machine learning boundary detection motion segmentation loopy belief propagation motion tracking algorithm A significant barrier to applying the techniques of machine learning to the domain of object boundary detection is the need to obtain a large database of correctly labeled examples. Inspired by developmental psychology, this paper proposes that boundary detection can be learned from the output of a motion tracking algorithm that separates moving objects from their static surroundings. Motion segmentation solves the database problem by providing cheap, unlimited, labeled training data. A probabilistic model of the textural and shape properties of object boundaries can be trained from this data and then used to efficiently detect boundaries in novel images via loopy belief propagation. Singapore-MIT Alliance (SMA) 2003-11-16T19:34:34Z 2003-11-16T19:34:34Z 2003-01 Article http://hdl.handle.net/1721.1/3686 en_US Computer Science (CS); 1220156 bytes application/pdf application/pdf |
| spellingShingle | machine learning boundary detection motion segmentation loopy belief propagation motion tracking algorithm Ross, Michael G. Kaelbling, Leslie P. Learning object boundary detection from motion data |
| title | Learning object boundary detection from motion data |
| title_full | Learning object boundary detection from motion data |
| title_fullStr | Learning object boundary detection from motion data |
| title_full_unstemmed | Learning object boundary detection from motion data |
| title_short | Learning object boundary detection from motion data |
| title_sort | learning object boundary detection from motion data |
| topic | machine learning boundary detection motion segmentation loopy belief propagation motion tracking algorithm |
| url | http://hdl.handle.net/1721.1/3686 |
| work_keys_str_mv | AT rossmichaelg learningobjectboundarydetectionfrommotiondata AT kaelblinglesliep learningobjectboundarydetectionfrommotiondata |