Recognizing 3D Object Using Photometric Invariant
In this paper we describe a new efficient algorithm for recognizing 3D objects by combining photometric and geometric invariants. Some photometric properties are derived, that are invariant to the changes of illumination and to relative object motion with respect to the camera and/or the light...
| Main Authors: | , |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/5945 |
| _version_ | 1826214437715968000 |
|---|---|
| author | Nagao, Kenji Grimson, Eric |
| author_facet | Nagao, Kenji Grimson, Eric |
| author_sort | Nagao, Kenji |
| collection | MIT |
| description | In this paper we describe a new efficient algorithm for recognizing 3D objects by combining photometric and geometric invariants. Some photometric properties are derived, that are invariant to the changes of illumination and to relative object motion with respect to the camera and/or the lighting source in 3D space. We argue that conventional color constancy algorithms can not be used in the recognition of 3D objects. Further we show recognition does not require a full constancy of colors, rather, it only needs something that remains unchanged under the varying light conditions sand poses of the objects. Combining the derived color invariants and the spatial constraints on the object surfaces, we identify corresponding positions in the model and the data space coordinates, using centroid invariance of corresponding groups of feature positions. Tests are given to show the stability and efficiency of our approach to 3D object recognition. |
| first_indexed | 2024-09-23T16:05:20Z |
| id | mit-1721.1/5945 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T16:05:20Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/59452019-04-10T17:24:22Z Recognizing 3D Object Using Photometric Invariant Nagao, Kenji Grimson, Eric AI MIT Artificial Intelligence In this paper we describe a new efficient algorithm for recognizing 3D objects by combining photometric and geometric invariants. Some photometric properties are derived, that are invariant to the changes of illumination and to relative object motion with respect to the camera and/or the lighting source in 3D space. We argue that conventional color constancy algorithms can not be used in the recognition of 3D objects. Further we show recognition does not require a full constancy of colors, rather, it only needs something that remains unchanged under the varying light conditions sand poses of the objects. Combining the derived color invariants and the spatial constraints on the object surfaces, we identify corresponding positions in the model and the data space coordinates, using centroid invariance of corresponding groups of feature positions. Tests are given to show the stability and efficiency of our approach to 3D object recognition. 2004-10-04T14:15:50Z 2004-10-04T14:15:50Z 1995-04-22 AIM-1523 http://hdl.handle.net/1721.1/5945 en_US AIM-1523 22 p. 15746167 bytes 1381542 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | AI MIT Artificial Intelligence Nagao, Kenji Grimson, Eric Recognizing 3D Object Using Photometric Invariant |
| title | Recognizing 3D Object Using Photometric Invariant |
| title_full | Recognizing 3D Object Using Photometric Invariant |
| title_fullStr | Recognizing 3D Object Using Photometric Invariant |
| title_full_unstemmed | Recognizing 3D Object Using Photometric Invariant |
| title_short | Recognizing 3D Object Using Photometric Invariant |
| title_sort | recognizing 3d object using photometric invariant |
| topic | AI MIT Artificial Intelligence |
| url | http://hdl.handle.net/1721.1/5945 |
| work_keys_str_mv | AT nagaokenji recognizing3dobjectusingphotometricinvariant AT grimsoneric recognizing3dobjectusingphotometricinvariant |