Content and context boosting for mobile landmark recognition
Existing mobile landmark recognition techniques mainly use GPS location information to obtain the candidate images nearby the mobile device, followed by content analysis within the shortlist. This is insufficient since i) GPS often has large errors in dense build-up areas, and ii) direction is under...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/102784 http://hdl.handle.net/10220/16435 |
| _version_ | 1826114321632985088 |
|---|---|
| author | Yap, Kim-Hui Li, Zhen. |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Yap, Kim-Hui Li, Zhen. |
| author_sort | Yap, Kim-Hui |
| collection | NTU |
| description | Existing mobile landmark recognition techniques mainly use GPS location information to obtain the candidate images nearby the mobile device, followed by content analysis within the shortlist. This is insufficient since i) GPS often has large errors in dense build-up areas, and ii) direction is underutilized to further improve recognition. In this letter, visual content and two types of mobile context: location and direction, are integrated by the proposed boosting algorithm. Experimental results show that the proposed method outperforms the state-of-the-art methods by about 6%, 11%, and 15% on NTU Landmark-50, PKU Landmark-198, and the large-scale San Francisco landmark dataset, respectively. |
| first_indexed | 2024-10-01T03:37:16Z |
| format | Journal Article |
| id | ntu-10356/102784 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:37:16Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | ntu-10356/1027842020-03-07T14:00:35Z Content and context boosting for mobile landmark recognition Yap, Kim-Hui Li, Zhen. School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering Existing mobile landmark recognition techniques mainly use GPS location information to obtain the candidate images nearby the mobile device, followed by content analysis within the shortlist. This is insufficient since i) GPS often has large errors in dense build-up areas, and ii) direction is underutilized to further improve recognition. In this letter, visual content and two types of mobile context: location and direction, are integrated by the proposed boosting algorithm. Experimental results show that the proposed method outperforms the state-of-the-art methods by about 6%, 11%, and 15% on NTU Landmark-50, PKU Landmark-198, and the large-scale San Francisco landmark dataset, respectively. 2013-10-10T08:26:03Z 2019-12-06T21:00:11Z 2013-10-10T08:26:03Z 2019-12-06T21:00:11Z 2012 2012 Journal Article Li, Z., & Yap, K. H. (2012). Content and context boosting for mobile landmark recognition. IEEE signal processing letters, 19(8), 459-462. 1070-9908 https://hdl.handle.net/10356/102784 http://hdl.handle.net/10220/16435 10.1109/LSP.2012.2203120 en IEEE signal processing letters © 2012 IEEE |
| spellingShingle | DRNTU::Engineering::Electrical and electronic engineering Yap, Kim-Hui Li, Zhen. Content and context boosting for mobile landmark recognition |
| title | Content and context boosting for mobile landmark recognition |
| title_full | Content and context boosting for mobile landmark recognition |
| title_fullStr | Content and context boosting for mobile landmark recognition |
| title_full_unstemmed | Content and context boosting for mobile landmark recognition |
| title_short | Content and context boosting for mobile landmark recognition |
| title_sort | content and context boosting for mobile landmark recognition |
| topic | DRNTU::Engineering::Electrical and electronic engineering |
| url | https://hdl.handle.net/10356/102784 http://hdl.handle.net/10220/16435 |
| work_keys_str_mv | AT yapkimhui contentandcontextboostingformobilelandmarkrecognition AT lizhen contentandcontextboostingformobilelandmarkrecognition |