LR Aerial Imagery Categorization by Transferring Cross-Resolution Perceptual Experiences
Hundreds of satellites orbiting at various altitudes capture an extensive array of aerial photographs daily. High-altitude satellites typically acquire low-resolution (LR) images that cover vast areas, whereas their low-altitude counterparts obtain high-resolution (HR) images detailing much smaller...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10443961/ |
| _version_ | 1797243319124754432 |
|---|---|
| author | Yue Yu Yi Li |
| author_facet | Yue Yu Yi Li |
| author_sort | Yue Yu |
| collection | DOAJ |
| description | Hundreds of satellites orbiting at various altitudes capture an extensive array of aerial photographs daily. High-altitude satellites typically acquire low-resolution (LR) images that cover vast areas, whereas their low-altitude counterparts obtain high-resolution (HR) images detailing much smaller regions. The accurate interpretation of LR aerial imagery is crucial in the field of computer vision, yet it presents significant challenges, including the complexity of emulating human hierarchical visual perception and the daunting task of annotating enough data for effective training. To address these challenges, we introduce a cross-resolution perceptual knowledge propagation (CPKP) framework, which aims to leverage the visual perceptual insights gained from HR aerial imagery to enhance the categorization of LR images. This approach involves a novel low-rank model that segments each LR aerial photo into distinct visually and semantically significant foreground regions, alongside less pertinent background areas. This model is capable of generating a gaze shifting path (GSP) that reflects human gaze patterns and formulating a deep feature for each GSP. Subsequently, a kernel-induced feature selection algorithm is deployed to extract a concise yet powerful set of deep GSP features that are effective across both LR and HR aerial images. Utilizing these features, a linear classifier is collaboratively trained using labels from both LR and HR images, facilitating the categorization of LR images. Notably, the CPKP framework enhances the efficiency of training the linear classifier, given that HR photo labels are more readily available. Our comprehensive visualizations and comparative analysis underscore the effectiveness and superiority of this innovative approach. |
| first_indexed | 2024-04-24T18:53:13Z |
| format | Article |
| id | doaj.art-adc2daf5c3cd4867acce1e3e25e81fb5 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-04-24T18:53:13Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-adc2daf5c3cd4867acce1e3e25e81fb52024-03-26T17:48:30ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352024-01-01176577658810.1109/JSTARS.2024.336941310443961LR Aerial Imagery Categorization by Transferring Cross-Resolution Perceptual ExperiencesYue Yu0https://orcid.org/0009-0004-3405-0548Yi Li1https://orcid.org/0000-0001-8425-7871Key Laboratory of Crop Harvesting Equipment Technology of Zhejiang Province, Jinhua Polytechnic, Jinhua, ChinaCollege of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, ChinaHundreds of satellites orbiting at various altitudes capture an extensive array of aerial photographs daily. High-altitude satellites typically acquire low-resolution (LR) images that cover vast areas, whereas their low-altitude counterparts obtain high-resolution (HR) images detailing much smaller regions. The accurate interpretation of LR aerial imagery is crucial in the field of computer vision, yet it presents significant challenges, including the complexity of emulating human hierarchical visual perception and the daunting task of annotating enough data for effective training. To address these challenges, we introduce a cross-resolution perceptual knowledge propagation (CPKP) framework, which aims to leverage the visual perceptual insights gained from HR aerial imagery to enhance the categorization of LR images. This approach involves a novel low-rank model that segments each LR aerial photo into distinct visually and semantically significant foreground regions, alongside less pertinent background areas. This model is capable of generating a gaze shifting path (GSP) that reflects human gaze patterns and formulating a deep feature for each GSP. Subsequently, a kernel-induced feature selection algorithm is deployed to extract a concise yet powerful set of deep GSP features that are effective across both LR and HR aerial images. Utilizing these features, a linear classifier is collaboratively trained using labels from both LR and HR images, facilitating the categorization of LR images. Notably, the CPKP framework enhances the efficiency of training the linear classifier, given that HR photo labels are more readily available. Our comprehensive visualizations and comparative analysis underscore the effectiveness and superiority of this innovative approach.https://ieeexplore.ieee.org/document/10443961/Aerial photocross resolutiongaze shiftinghuman perceptionknowledge propagation |
| spellingShingle | Yue Yu Yi Li LR Aerial Imagery Categorization by Transferring Cross-Resolution Perceptual Experiences IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Aerial photo cross resolution gaze shifting human perception knowledge propagation |
| title | LR Aerial Imagery Categorization by Transferring Cross-Resolution Perceptual Experiences |
| title_full | LR Aerial Imagery Categorization by Transferring Cross-Resolution Perceptual Experiences |
| title_fullStr | LR Aerial Imagery Categorization by Transferring Cross-Resolution Perceptual Experiences |
| title_full_unstemmed | LR Aerial Imagery Categorization by Transferring Cross-Resolution Perceptual Experiences |
| title_short | LR Aerial Imagery Categorization by Transferring Cross-Resolution Perceptual Experiences |
| title_sort | lr aerial imagery categorization by transferring cross resolution perceptual experiences |
| topic | Aerial photo cross resolution gaze shifting human perception knowledge propagation |
| url | https://ieeexplore.ieee.org/document/10443961/ |
| work_keys_str_mv | AT yueyu lraerialimagerycategorizationbytransferringcrossresolutionperceptualexperiences AT yili lraerialimagerycategorizationbytransferringcrossresolutionperceptualexperiences |