Joint optimization for object class segmentation and dense stereo reconstruction
The problems of dense stereo reconstruction and object class segmentation can both be formulated as Random Field labeling problems, in which every pixel in the image is assigned a label corresponding to either its disparity, or an object class such as road or building. While these two problems are m...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Springer
2011
|
| _version_ | 1811141088679821312 |
|---|---|
| author | Ladický, L Sturgess, P Russell, C Sengupta, S Bastanlar, Y Clocksin, W Torr, PHS |
| author_facet | Ladický, L Sturgess, P Russell, C Sengupta, S Bastanlar, Y Clocksin, W Torr, PHS |
| author_sort | Ladický, L |
| collection | OXFORD |
| description | The problems of dense stereo reconstruction and object class segmentation can both be formulated as Random Field labeling problems, in which every pixel in the image is assigned a label corresponding to either its disparity, or an object class such as road or building. While these two problems are mutually informative, no attempt has been made to jointly optimize their labelings. In this work we provide a flexible framework configured via cross-validation that unifies the two problems and demonstrate that, by resolving ambiguities, which would be present in real world data if the two problems were considered separately, joint optimization of the two problems substantially improves performance. To evaluate our method, we augment the Leuven data set (http://cms.brookes.ac.uk/research/visiongroup/files/Leuven.zip), which is a stereo video shot from a car driving around the streets of Leuven, with 70 hand labeled object class and disparity maps. We hope that the release of these annotations will stimulate further work in the challenging domain of street-view analysis. Complete source code is publicly available (http://cms.brookes.ac.uk/staff/Philip-Torr/ale.htm). |
| first_indexed | 2024-09-25T04:32:19Z |
| format | Journal article |
| id | oxford-uuid:b05a83e4-98cb-4981-b495-866d8897868d |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-09-25T04:32:19Z |
| publishDate | 2011 |
| publisher | Springer |
| record_format | dspace |
| spelling | oxford-uuid:b05a83e4-98cb-4981-b495-866d8897868d2024-09-02T16:01:56ZJoint optimization for object class segmentation and dense stereo reconstructionJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:b05a83e4-98cb-4981-b495-866d8897868dEnglishSymplectic ElementsSpringer2011Ladický, LSturgess, PRussell, CSengupta, SBastanlar, YClocksin, WTorr, PHSThe problems of dense stereo reconstruction and object class segmentation can both be formulated as Random Field labeling problems, in which every pixel in the image is assigned a label corresponding to either its disparity, or an object class such as road or building. While these two problems are mutually informative, no attempt has been made to jointly optimize their labelings. In this work we provide a flexible framework configured via cross-validation that unifies the two problems and demonstrate that, by resolving ambiguities, which would be present in real world data if the two problems were considered separately, joint optimization of the two problems substantially improves performance. To evaluate our method, we augment the Leuven data set (http://cms.brookes.ac.uk/research/visiongroup/files/Leuven.zip), which is a stereo video shot from a car driving around the streets of Leuven, with 70 hand labeled object class and disparity maps. We hope that the release of these annotations will stimulate further work in the challenging domain of street-view analysis. Complete source code is publicly available (http://cms.brookes.ac.uk/staff/Philip-Torr/ale.htm). |
| spellingShingle | Ladický, L Sturgess, P Russell, C Sengupta, S Bastanlar, Y Clocksin, W Torr, PHS Joint optimization for object class segmentation and dense stereo reconstruction |
| title | Joint optimization for object class segmentation and dense stereo reconstruction |
| title_full | Joint optimization for object class segmentation and dense stereo reconstruction |
| title_fullStr | Joint optimization for object class segmentation and dense stereo reconstruction |
| title_full_unstemmed | Joint optimization for object class segmentation and dense stereo reconstruction |
| title_short | Joint optimization for object class segmentation and dense stereo reconstruction |
| title_sort | joint optimization for object class segmentation and dense stereo reconstruction |
| work_keys_str_mv | AT ladickyl jointoptimizationforobjectclasssegmentationanddensestereoreconstruction AT sturgessp jointoptimizationforobjectclasssegmentationanddensestereoreconstruction AT russellc jointoptimizationforobjectclasssegmentationanddensestereoreconstruction AT senguptas jointoptimizationforobjectclasssegmentationanddensestereoreconstruction AT bastanlary jointoptimizationforobjectclasssegmentationanddensestereoreconstruction AT clocksinw jointoptimizationforobjectclasssegmentationanddensestereoreconstruction AT torrphs jointoptimizationforobjectclasssegmentationanddensestereoreconstruction |