Combining image descriptors to effectively retrieve events from visual lifelogs
The SenseCam is a wearable camera that passively captures approximately 3,000 images per day, which equates to almost one million images per year. It is used to create a personal visual recording of the wearer's life and generates information which can be helpful as a human memory aid. For such...
| Main Authors: | , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
2008
|
| _version_ | 1797101199204286464 |
|---|---|
| author | Doherty, A Conaire, C Blighe, M Smeaton, A O'connor, N |
| author_facet | Doherty, A Conaire, C Blighe, M Smeaton, A O'connor, N |
| author_sort | Doherty, A |
| collection | OXFORD |
| description | The SenseCam is a wearable camera that passively captures approximately 3,000 images per day, which equates to almost one million images per year. It is used to create a personal visual recording of the wearer's life and generates information which can be helpful as a human memory aid. For such a large amount of visual information to be of any use, it is accepted that it should be structured into "events", of which there are about 8,000 in a wearer's average year. In automatically segmenting SenseCam images into events, it will then be useful for users to locate other events similar to a given event e.g. "what other times was I walking in the park?", "show me other events when I was in a restaurant". On two datasets of 240k and 1.8M images containing topics with a variety of information needs, we evaluate the fusion of MPEG-7, SIFT, and SURF content-based retrieval techniques to address the event search issue. We have found that our proposed fusion approach of MPEG-7 and SURF offers an improvement on using either of those sources or SIFT individually, and we have also shown how a lifelog event is modeled has a large effect on the retrieval performance. Copyright 2008 ACM. |
| first_indexed | 2024-03-07T05:48:27Z |
| format | Journal article |
| id | oxford-uuid:e80238f5-610a-4d50-9fdf-bc27154b7724 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T05:48:27Z |
| publishDate | 2008 |
| record_format | dspace |
| spelling | oxford-uuid:e80238f5-610a-4d50-9fdf-bc27154b77242022-03-27T10:43:26ZCombining image descriptors to effectively retrieve events from visual lifelogsJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:e80238f5-610a-4d50-9fdf-bc27154b7724EnglishSymplectic Elements at Oxford2008Doherty, AConaire, CBlighe, MSmeaton, AO'connor, NThe SenseCam is a wearable camera that passively captures approximately 3,000 images per day, which equates to almost one million images per year. It is used to create a personal visual recording of the wearer's life and generates information which can be helpful as a human memory aid. For such a large amount of visual information to be of any use, it is accepted that it should be structured into "events", of which there are about 8,000 in a wearer's average year. In automatically segmenting SenseCam images into events, it will then be useful for users to locate other events similar to a given event e.g. "what other times was I walking in the park?", "show me other events when I was in a restaurant". On two datasets of 240k and 1.8M images containing topics with a variety of information needs, we evaluate the fusion of MPEG-7, SIFT, and SURF content-based retrieval techniques to address the event search issue. We have found that our proposed fusion approach of MPEG-7 and SURF offers an improvement on using either of those sources or SIFT individually, and we have also shown how a lifelog event is modeled has a large effect on the retrieval performance. Copyright 2008 ACM. |
| spellingShingle | Doherty, A Conaire, C Blighe, M Smeaton, A O'connor, N Combining image descriptors to effectively retrieve events from visual lifelogs |
| title | Combining image descriptors to effectively retrieve events from visual lifelogs |
| title_full | Combining image descriptors to effectively retrieve events from visual lifelogs |
| title_fullStr | Combining image descriptors to effectively retrieve events from visual lifelogs |
| title_full_unstemmed | Combining image descriptors to effectively retrieve events from visual lifelogs |
| title_short | Combining image descriptors to effectively retrieve events from visual lifelogs |
| title_sort | combining image descriptors to effectively retrieve events from visual lifelogs |
| work_keys_str_mv | AT dohertya combiningimagedescriptorstoeffectivelyretrieveeventsfromvisuallifelogs AT conairec combiningimagedescriptorstoeffectivelyretrieveeventsfromvisuallifelogs AT blighem combiningimagedescriptorstoeffectivelyretrieveeventsfromvisuallifelogs AT smeatona combiningimagedescriptorstoeffectivelyretrieveeventsfromvisuallifelogs AT oconnorn combiningimagedescriptorstoeffectivelyretrieveeventsfromvisuallifelogs |