Ultra-High-Definition Aerial Photo Categorization by an Enhanced Matrix Factorization Algorithm
In this work, we designed an effective ultra-high-definition (UHD) aerial photo categorization pipeline by designing an enhanced deep multi-clue matrix factorization (DMCMF). In detail, given a UHD aerial photo, those visually salient ground objects are extracted in the first place. In order to expl...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10364763/ |
| _version_ | 1797346334203707392 |
|---|---|
| author | Junwu Zhou Guifeng Wang Fuji Ren |
| author_facet | Junwu Zhou Guifeng Wang Fuji Ren |
| author_sort | Junwu Zhou |
| collection | DOAJ |
| description | In this work, we designed an effective ultra-high-definition (UHD) aerial photo categorization pipeline by designing an enhanced deep multi-clue matrix factorization (DMCMF). In detail, given a UHD aerial photo, those visually salient ground objects are extracted in the first place. In order to explicitly encode their spatial layout, multiple graphlets are constructed in each UHD aerial photo. Each is built by connecting those spatially neighboring object patches. Afterward, we propose a new matrix factorization (MF) model that intelligently uncover the underlying semantic features from graphlets. And multiple informative clues are encoded into the MF model. Notably, our DMCMF is optimized progressively. And we can represent each graphlet by a vector of binary hash codes. Lastly, each UHD aerial photograph can be effectively quantized into a feature vector by a kernel machine for multi-label categorization. Experiments have shown that our method is highly competitive in learning categorization model from imperfect labels at image-level. |
| first_indexed | 2024-03-08T11:31:52Z |
| format | Article |
| id | doaj.art-f438e4f8beda42c597a0b77fc6f2c8d2 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T11:31:52Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-f438e4f8beda42c597a0b77fc6f2c8d22024-01-26T00:01:15ZengIEEEIEEE Access2169-35362024-01-0112120531206110.1109/ACCESS.2023.334416410364763Ultra-High-Definition Aerial Photo Categorization by an Enhanced Matrix Factorization AlgorithmJunwu Zhou0Guifeng Wang1Fuji Ren2https://orcid.org/0009-0001-4935-8471School of Higher Vocational and Technical College, Shanghai Dianji University, Shanghai, ChinaKey Laboratory of Crop Harvesting Equipment Technology of Zhejiang Province, Jinhua Polytechnic, Jinhua, ChinaCollege of Computer Sciences, Hefei University of Technology, Hefei, ChinaIn this work, we designed an effective ultra-high-definition (UHD) aerial photo categorization pipeline by designing an enhanced deep multi-clue matrix factorization (DMCMF). In detail, given a UHD aerial photo, those visually salient ground objects are extracted in the first place. In order to explicitly encode their spatial layout, multiple graphlets are constructed in each UHD aerial photo. Each is built by connecting those spatially neighboring object patches. Afterward, we propose a new matrix factorization (MF) model that intelligently uncover the underlying semantic features from graphlets. And multiple informative clues are encoded into the MF model. Notably, our DMCMF is optimized progressively. And we can represent each graphlet by a vector of binary hash codes. Lastly, each UHD aerial photograph can be effectively quantized into a feature vector by a kernel machine for multi-label categorization. Experiments have shown that our method is highly competitive in learning categorization model from imperfect labels at image-level.https://ieeexplore.ieee.org/document/10364763/Media analysisaerial photomulti-cluematrix factorization |
| spellingShingle | Junwu Zhou Guifeng Wang Fuji Ren Ultra-High-Definition Aerial Photo Categorization by an Enhanced Matrix Factorization Algorithm IEEE Access Media analysis aerial photo multi-clue matrix factorization |
| title | Ultra-High-Definition Aerial Photo Categorization by an Enhanced Matrix Factorization Algorithm |
| title_full | Ultra-High-Definition Aerial Photo Categorization by an Enhanced Matrix Factorization Algorithm |
| title_fullStr | Ultra-High-Definition Aerial Photo Categorization by an Enhanced Matrix Factorization Algorithm |
| title_full_unstemmed | Ultra-High-Definition Aerial Photo Categorization by an Enhanced Matrix Factorization Algorithm |
| title_short | Ultra-High-Definition Aerial Photo Categorization by an Enhanced Matrix Factorization Algorithm |
| title_sort | ultra high definition aerial photo categorization by an enhanced matrix factorization algorithm |
| topic | Media analysis aerial photo multi-clue matrix factorization |
| url | https://ieeexplore.ieee.org/document/10364763/ |
| work_keys_str_mv | AT junwuzhou ultrahighdefinitionaerialphotocategorizationbyanenhancedmatrixfactorizationalgorithm AT guifengwang ultrahighdefinitionaerialphotocategorizationbyanenhancedmatrixfactorizationalgorithm AT fujiren ultrahighdefinitionaerialphotocategorizationbyanenhancedmatrixfactorizationalgorithm |