Human instance segmentation from video using detector-based conditional random fields
In this work, we propose a method for instance based human segmentation in images and videos, extending the recent detector-based conditional random field model of Ladicky et.al. Instance based human segmentation involves pixel level labeling of an image, partitioning it into distinct human instance...
| Main Authors: | , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
British Machine Vision Association
2011
|
| _version_ | 1826314906629046272 |
|---|---|
| author | Vineet, V Warrell, J Ladický, L Torr, PHS |
| author_facet | Vineet, V Warrell, J Ladický, L Torr, PHS |
| author_sort | Vineet, V |
| collection | OXFORD |
| description | In this work, we propose a method for instance based human segmentation in images and videos, extending the recent detector-based conditional random field model of Ladicky et.al. Instance based human segmentation involves pixel level labeling of an image, partitioning it into distinct human instances and background. To achieve our goal, we add three new components to their framework. First, we include human parts-based detection potentials to take advantage of the structure present in human instances. Further, in order to generate a consistent segmentation from different human parts, we incorporate shape prior information, which biases the segmentation to characteristic overall human shapes. Also, we enhance the representative power of the energy function by adopting exemplar instance based matching terms, which helps our method to adapt easily to different human sizes and poses. Finally, we extensively evaluate our proposed method on the Buffy dataset with our new segmented ground truth images, and show a substantial improvement over existing CRF methods. These new annotations will be made available for future use as well. © 2011. The copyright of this document resides with its authors. |
| first_indexed | 2024-12-09T03:16:05Z |
| format | Conference item |
| id | oxford-uuid:4b6d12ff-ce9f-435d-ab29-4215471ce03d |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-12-09T03:16:05Z |
| publishDate | 2011 |
| publisher | British Machine Vision Association |
| record_format | dspace |
| spelling | oxford-uuid:4b6d12ff-ce9f-435d-ab29-4215471ce03d2024-10-22T14:06:04ZHuman instance segmentation from video using detector-based conditional random fieldsConference itemhttp://purl.org/coar/resource_type/c_5794uuid:4b6d12ff-ce9f-435d-ab29-4215471ce03dEnglishSymplectic ElementsBritish Machine Vision Association2011Vineet, VWarrell, JLadický, LTorr, PHSIn this work, we propose a method for instance based human segmentation in images and videos, extending the recent detector-based conditional random field model of Ladicky et.al. Instance based human segmentation involves pixel level labeling of an image, partitioning it into distinct human instances and background. To achieve our goal, we add three new components to their framework. First, we include human parts-based detection potentials to take advantage of the structure present in human instances. Further, in order to generate a consistent segmentation from different human parts, we incorporate shape prior information, which biases the segmentation to characteristic overall human shapes. Also, we enhance the representative power of the energy function by adopting exemplar instance based matching terms, which helps our method to adapt easily to different human sizes and poses. Finally, we extensively evaluate our proposed method on the Buffy dataset with our new segmented ground truth images, and show a substantial improvement over existing CRF methods. These new annotations will be made available for future use as well. © 2011. The copyright of this document resides with its authors. |
| spellingShingle | Vineet, V Warrell, J Ladický, L Torr, PHS Human instance segmentation from video using detector-based conditional random fields |
| title | Human instance segmentation from video using detector-based conditional random fields |
| title_full | Human instance segmentation from video using detector-based conditional random fields |
| title_fullStr | Human instance segmentation from video using detector-based conditional random fields |
| title_full_unstemmed | Human instance segmentation from video using detector-based conditional random fields |
| title_short | Human instance segmentation from video using detector-based conditional random fields |
| title_sort | human instance segmentation from video using detector based conditional random fields |
| work_keys_str_mv | AT vineetv humaninstancesegmentationfromvideousingdetectorbasedconditionalrandomfields AT warrellj humaninstancesegmentationfromvideousingdetectorbasedconditionalrandomfields AT ladickyl humaninstancesegmentationfromvideousingdetectorbasedconditionalrandomfields AT torrphs humaninstancesegmentationfromvideousingdetectorbasedconditionalrandomfields |