Sub-Pixel Mapping Based on MAP Model and Spatial Attraction Theory for Remotely Sensed Image
There are a lot of mixed pixels in the remotely sensed imagery, which can seriously limit the utility of classification. Sub-pixel mapping (SPM) is a promising technique to solve this problem. It can generate a fine resolution land cover map from coarse resolution fractional images by predicting the...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2017-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8093612/ |
id |
doaj-4a2fa748e6b3416195a06bc385ce3e24 |
---|---|
record_format |
Article |
spelling |
doaj-4a2fa748e6b3416195a06bc385ce3e242021-03-29T19:57:02ZengIEEEIEEE Access2169-35362017-01-015251262513210.1109/ACCESS.2017.27685438093612Sub-Pixel Mapping Based on MAP Model and Spatial Attraction Theory for Remotely Sensed ImageKe Wu0https://orcid.org/0000-0001-9692-4221Qian Du1Xiangyun Hu2Xianmin Wang3Institute of Geophysics and Geomatics, China University of Geosciences, Wuhan, ChinaDepartment of Electrical and Computer Engineering, Mississippi State University, Starkville, MS, USAInstitute of Geophysics and Geomatics, China University of Geosciences, Wuhan, ChinaInstitute of Geophysics and Geomatics, China University of Geosciences, Wuhan, ChinaThere are a lot of mixed pixels in the remotely sensed imagery, which can seriously limit the utility of classification. Sub-pixel mapping (SPM) is a promising technique to solve this problem. It can generate a fine resolution land cover map from coarse resolution fractional images by predicting the spatial locations of different land cover classes at sub-pixel scale.However, the accuracy and detail are always limited. Especially when the scale factor is large among sub-pixels per pixel, the data volumes are amplified and the sub-pixel distribution becomes complex. The traditional methods are carried out only by the fractions of land cover and the spatial dependence theory, which cannot satisfy the requirement of the SPM. For avoiding the above flaw, a new SPM method based on maximum a posteriori (MAP) model with subpixel/pixel spatial attraction theory aimed at the largescale factor is proposed. First, MAP is proposed to improve the resolution of the fractional images and obtain the initial sub-pixel locations; after that, the pixel swapping algorithm is used to optimize and produce the final SPM result. In this paper, the proposed model is tested by a simple simulated font image and real remotely sensed imagery, which can both demonstrate that it can outperform traditional algorithm with a more accurate sub-pixel scale land cover map.https://ieeexplore.ieee.org/document/8093612/Mixed pixelsub-pixel mappingMAPPSA |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ke Wu Qian Du Xiangyun Hu Xianmin Wang |
spellingShingle |
Ke Wu Qian Du Xiangyun Hu Xianmin Wang Sub-Pixel Mapping Based on MAP Model and Spatial Attraction Theory for Remotely Sensed Image IEEE Access Mixed pixel sub-pixel mapping MAP PSA |
author_facet |
Ke Wu Qian Du Xiangyun Hu Xianmin Wang |
author_sort |
Ke Wu |
title |
Sub-Pixel Mapping Based on MAP Model and Spatial Attraction Theory for Remotely Sensed Image |
title_short |
Sub-Pixel Mapping Based on MAP Model and Spatial Attraction Theory for Remotely Sensed Image |
title_full |
Sub-Pixel Mapping Based on MAP Model and Spatial Attraction Theory for Remotely Sensed Image |
title_fullStr |
Sub-Pixel Mapping Based on MAP Model and Spatial Attraction Theory for Remotely Sensed Image |
title_full_unstemmed |
Sub-Pixel Mapping Based on MAP Model and Spatial Attraction Theory for Remotely Sensed Image |
title_sort |
sub-pixel mapping based on map model and spatial attraction theory for remotely sensed image |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2017-01-01 |
description |
There are a lot of mixed pixels in the remotely sensed imagery, which can seriously limit the utility of classification. Sub-pixel mapping (SPM) is a promising technique to solve this problem. It can generate a fine resolution land cover map from coarse resolution fractional images by predicting the spatial locations of different land cover classes at sub-pixel scale.However, the accuracy and detail are always limited. Especially when the scale factor is large among sub-pixels per pixel, the data volumes are amplified and the sub-pixel distribution becomes complex. The traditional methods are carried out only by the fractions of land cover and the spatial dependence theory, which cannot satisfy the requirement of the SPM. For avoiding the above flaw, a new SPM method based on maximum a posteriori (MAP) model with subpixel/pixel spatial attraction theory aimed at the largescale factor is proposed. First, MAP is proposed to improve the resolution of the fractional images and obtain the initial sub-pixel locations; after that, the pixel swapping algorithm is used to optimize and produce the final SPM result. In this paper, the proposed model is tested by a simple simulated font image and real remotely sensed imagery, which can both demonstrate that it can outperform traditional algorithm with a more accurate sub-pixel scale land cover map. |
topic |
Mixed pixel sub-pixel mapping MAP PSA |
url |
https://ieeexplore.ieee.org/document/8093612/ |
work_keys_str_mv |
AT kewu subpixelmappingbasedonmapmodelandspatialattractiontheoryforremotelysensedimage AT qiandu subpixelmappingbasedonmapmodelandspatialattractiontheoryforremotelysensedimage AT xiangyunhu subpixelmappingbasedonmapmodelandspatialattractiontheoryforremotelysensedimage AT xianminwang subpixelmappingbasedonmapmodelandspatialattractiontheoryforremotelysensedimage |
_version_ |
1724195610723090432 |