Perceptual Low-Rank Learning and Geometry-Preserving Feature Selection for Categorizing High-Resolution Aerial Photos
Recognizing the multiple categories of an high-resolution (HR) aerial photos is an indispensable technique in geoscience and remote sensing. In this work, a perceptual low-rank algorithm combined with a geometry-preserving feature selection (FS) is proposed for categorizing HR aerial photos. In prac...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10274965/ |
| _version_ | 1827791777666433024 |
|---|---|
| author | Junwu Zhou Fuji Ren |
| author_facet | Junwu Zhou Fuji Ren |
| author_sort | Junwu Zhou |
| collection | DOAJ |
| description | Recognizing the multiple categories of an high-resolution (HR) aerial photos is an indispensable technique in geoscience and remote sensing. In this work, a perceptual low-rank algorithm combined with a geometry-preserving feature selection (FS) is proposed for categorizing HR aerial photos. In practice, the theory of human visual perception indicates that for each scenery, the background non-salient regions are highly correlated, whereas the foreground visually/semantically salient regions are almost uncorrelated. Motivated by this, we design a novel low-rank algorithm that seeks a sparse set of foreground visually/semantically salient image patches. These patches are sequentially linked into a so- called GSP (path reflecting gaze movement) to mimick human vision system. Afterward, a geometry-preserving FS algorithm is proposed to select highly discriminative features from the aforementioned gaze features, wherein a classifier can be trained simultaneously. Comprehensive experimental validation on our Internet-scale image set have shown its superiority. |
| first_indexed | 2024-03-11T17:52:51Z |
| format | Article |
| id | doaj.art-2a40059351d84b95ae2668d99dfdd5df |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-11T17:52:51Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-2a40059351d84b95ae2668d99dfdd5df2023-10-17T23:00:30ZengIEEEIEEE Access2169-35362023-01-011111242911243710.1109/ACCESS.2023.332331710274965Perceptual Low-Rank Learning and Geometry-Preserving Feature Selection for Categorizing High-Resolution Aerial PhotosJunwu Zhou0Fuji Ren1https://orcid.org/0009-0001-4935-8471Higher Vocational and Technical College, Shanghai Dianji University, Shanghai, ChinaSchool of Computer Sciences, Anhui University, Hefei, ChinaRecognizing the multiple categories of an high-resolution (HR) aerial photos is an indispensable technique in geoscience and remote sensing. In this work, a perceptual low-rank algorithm combined with a geometry-preserving feature selection (FS) is proposed for categorizing HR aerial photos. In practice, the theory of human visual perception indicates that for each scenery, the background non-salient regions are highly correlated, whereas the foreground visually/semantically salient regions are almost uncorrelated. Motivated by this, we design a novel low-rank algorithm that seeks a sparse set of foreground visually/semantically salient image patches. These patches are sequentially linked into a so- called GSP (path reflecting gaze movement) to mimick human vision system. Afterward, a geometry-preserving FS algorithm is proposed to select highly discriminative features from the aforementioned gaze features, wherein a classifier can be trained simultaneously. Comprehensive experimental validation on our Internet-scale image set have shown its superiority.https://ieeexplore.ieee.org/document/10274965/Feature selectiongeometryhigh-resolutionlow-rank |
| spellingShingle | Junwu Zhou Fuji Ren Perceptual Low-Rank Learning and Geometry-Preserving Feature Selection for Categorizing High-Resolution Aerial Photos IEEE Access Feature selection geometry high-resolution low-rank |
| title | Perceptual Low-Rank Learning and Geometry-Preserving Feature Selection for Categorizing High-Resolution Aerial Photos |
| title_full | Perceptual Low-Rank Learning and Geometry-Preserving Feature Selection for Categorizing High-Resolution Aerial Photos |
| title_fullStr | Perceptual Low-Rank Learning and Geometry-Preserving Feature Selection for Categorizing High-Resolution Aerial Photos |
| title_full_unstemmed | Perceptual Low-Rank Learning and Geometry-Preserving Feature Selection for Categorizing High-Resolution Aerial Photos |
| title_short | Perceptual Low-Rank Learning and Geometry-Preserving Feature Selection for Categorizing High-Resolution Aerial Photos |
| title_sort | perceptual low rank learning and geometry preserving feature selection for categorizing high resolution aerial photos |
| topic | Feature selection geometry high-resolution low-rank |
| url | https://ieeexplore.ieee.org/document/10274965/ |
| work_keys_str_mv | AT junwuzhou perceptuallowranklearningandgeometrypreservingfeatureselectionforcategorizinghighresolutionaerialphotos AT fujiren perceptuallowranklearningandgeometrypreservingfeatureselectionforcategorizinghighresolutionaerialphotos |