3D object recognition using invariance
<p>The systems and concepts described in this paper document the evolution of the geometric invariance approach to object recognition over the last five years. Invariance overcomes one of the fundamental difficulties in recognising objects from images: that the appearance of an object depends...
| Autores principales: | , , , , , |
|---|---|
| Formato: | Journal article |
| Lenguaje: | English |
| Publicado: |
Elsevier
1995
|
| _version_ | 1826317534475845632 |
|---|---|
| author | Zisserman, A Forsyth, D Mundy, J Rothwell, C Liu, J Pillow, N |
| author_facet | Zisserman, A Forsyth, D Mundy, J Rothwell, C Liu, J Pillow, N |
| author_sort | Zisserman, A |
| collection | OXFORD |
| description | <p>The systems and concepts described in this paper document the evolution of the geometric invariance approach to object recognition over the last five years. Invariance overcomes one of the fundamental difficulties in recognising objects from images: that the appearance of an object depends on viewpoint. This problem is entirely avoided if the geometric description is unaffected by the imaging transformation. Such invariant descriptions can be measured from images without any prior knowledge of the position, orientation and calibration of the camera. These invariant measurements can be used to index a library of object models for recognition and provide a principled basis for the other stages of the recognition process such as feature grouping and hypothesis verification. Object models can be acquired directly from images, allowing efficient construction of model libraries without manual intervention.</p>
<p>A significant part of the paper is a summary of recent results on the construction of invariants for 3D objects from a single perspective view. A proposed recognition architecture is described which enables the integration of multiple general object classes and provides a means for enforcing global scene consistency.</p>
<p>Various criticisms of the invariant approach are articulated and addressed.</p> |
| first_indexed | 2025-02-19T04:39:48Z |
| format | Journal article |
| id | oxford-uuid:91d12a12-d2a5-4f1e-8d8d-78a720a10496 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2025-02-19T04:39:48Z |
| publishDate | 1995 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | oxford-uuid:91d12a12-d2a5-4f1e-8d8d-78a720a104962025-02-18T13:40:05Z3D object recognition using invarianceJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:91d12a12-d2a5-4f1e-8d8d-78a720a10496EnglishSymplectic ElementsElsevier1995Zisserman, AForsyth, DMundy, JRothwell, CLiu, JPillow, N<p>The systems and concepts described in this paper document the evolution of the geometric invariance approach to object recognition over the last five years. Invariance overcomes one of the fundamental difficulties in recognising objects from images: that the appearance of an object depends on viewpoint. This problem is entirely avoided if the geometric description is unaffected by the imaging transformation. Such invariant descriptions can be measured from images without any prior knowledge of the position, orientation and calibration of the camera. These invariant measurements can be used to index a library of object models for recognition and provide a principled basis for the other stages of the recognition process such as feature grouping and hypothesis verification. Object models can be acquired directly from images, allowing efficient construction of model libraries without manual intervention.</p> <p>A significant part of the paper is a summary of recent results on the construction of invariants for 3D objects from a single perspective view. A proposed recognition architecture is described which enables the integration of multiple general object classes and provides a means for enforcing global scene consistency.</p> <p>Various criticisms of the invariant approach are articulated and addressed.</p> |
| spellingShingle | Zisserman, A Forsyth, D Mundy, J Rothwell, C Liu, J Pillow, N 3D object recognition using invariance |
| title | 3D object recognition using invariance |
| title_full | 3D object recognition using invariance |
| title_fullStr | 3D object recognition using invariance |
| title_full_unstemmed | 3D object recognition using invariance |
| title_short | 3D object recognition using invariance |
| title_sort | 3d object recognition using invariance |
| work_keys_str_mv | AT zissermana 3dobjectrecognitionusinginvariance AT forsythd 3dobjectrecognitionusinginvariance AT mundyj 3dobjectrecognitionusinginvariance AT rothwellc 3dobjectrecognitionusinginvariance AT liuj 3dobjectrecognitionusinginvariance AT pillown 3dobjectrecognitionusinginvariance |