Superpixel Segmentation Based on Anisotropic Diffusion Model for Object-Oriented Remote Sensing Image Classification
Superpixel segmentation is an essential step of object-oriented remote sensing image classification; the accuracy of the superpixel segmentation boundary will directly affect the classification result. Most of the traditional superpixel segmentation algorithms rely on spectral similarity and spatial...
| 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/10286067/ |
| _version_ | 1827284908948586496 |
|---|---|
| author | Xiaoli Li Jinsong Chen Longlong Zhao Hongzhong Li Jin Wang Luyi Sun Shanxin Guo Pan Chen Xuemei Zhao |
| author_facet | Xiaoli Li Jinsong Chen Longlong Zhao Hongzhong Li Jin Wang Luyi Sun Shanxin Guo Pan Chen Xuemei Zhao |
| author_sort | Xiaoli Li |
| collection | DOAJ |
| description | Superpixel segmentation is an essential step of object-oriented remote sensing image classification; the accuracy of the superpixel segmentation boundary will directly affect the classification result. Most of the traditional superpixel segmentation algorithms rely on spectral similarity and spatial connectivity to construct superpixels. They cannot find the accurate boundary in the complex scenes, such as the spatial distribution of ground features being relatively broken, and large differences in the size and shape, especially long-thin shape and circular shape. Aiming at this problem, a superpixel segmentation algorithm based on an anisotropic diffusion model named ADS is proposed and applied to image classification. The anisotropic diffusion model originated in thermodynamics has excellent properties in which the diffusion is continuous and smooth and its diffusion speed depends on the medium, which provides convenience for smoothing homogeneous regions and establishing boundary constraints for different ground objects. With this advantage, the diffusion flux model is established to consider the influence of boundary factors and used to simulate the dissimilarity measure with boundary constraints between pixels and seed points by combining the traditional spectral and spatial distance. Then, the seed points of superpixel are optimized under the K-means framework. The effectiveness of the proposed algorithm is tested and verified with different spatial resolutions, such as Landsat 8 with 30 m, Sentinel-2 with 10 m, and SkySat with 0.5 m. A large number of experiments show that the proposed algorithm can better correct the superpixel boundary-fitting deviation problem in complex scenes and effectively promote the improvement of image classification accuracy. |
| first_indexed | 2024-04-24T10:06:18Z |
| format | Article |
| id | doaj.art-63e2200c5fb949428aebb49d911fba79 |
| institution | Directory Open Access Journal |
| issn | 1939-1404 2151-1535 |
| language | English |
| last_indexed | 2024-04-24T10:06:18Z |
| 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-63e2200c5fb949428aebb49d911fba792024-04-12T23:00:04ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352024-01-01177621763910.1109/JSTARS.2023.332477010286067Superpixel Segmentation Based on Anisotropic Diffusion Model for Object-Oriented Remote Sensing Image ClassificationXiaoli Li0https://orcid.org/0000-0002-6184-6718Jinsong Chen1https://orcid.org/0000-0002-6049-9259Longlong Zhao2https://orcid.org/0000-0003-3276-1130Hongzhong Li3https://orcid.org/0000-0003-4304-6378Jin Wang4https://orcid.org/0000-0003-2584-9644Luyi Sun5https://orcid.org/0000-0003-4575-0836Shanxin Guo6https://orcid.org/0000-0001-8911-0166Pan Chen7Xuemei Zhao8https://orcid.org/0000-0002-0996-3538Center for Geospatial Information, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaCenter for Geospatial Information, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaCenter for Geospatial Information, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaCenter for Geospatial Information, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaSchool of Geography, South China Normal University, Guangzhou, ChinaCenter for Geospatial Information, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaCenter for Geospatial Information, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaCenter for Geospatial Information, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaSchool of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin, ChinaSuperpixel segmentation is an essential step of object-oriented remote sensing image classification; the accuracy of the superpixel segmentation boundary will directly affect the classification result. Most of the traditional superpixel segmentation algorithms rely on spectral similarity and spatial connectivity to construct superpixels. They cannot find the accurate boundary in the complex scenes, such as the spatial distribution of ground features being relatively broken, and large differences in the size and shape, especially long-thin shape and circular shape. Aiming at this problem, a superpixel segmentation algorithm based on an anisotropic diffusion model named ADS is proposed and applied to image classification. The anisotropic diffusion model originated in thermodynamics has excellent properties in which the diffusion is continuous and smooth and its diffusion speed depends on the medium, which provides convenience for smoothing homogeneous regions and establishing boundary constraints for different ground objects. With this advantage, the diffusion flux model is established to consider the influence of boundary factors and used to simulate the dissimilarity measure with boundary constraints between pixels and seed points by combining the traditional spectral and spatial distance. Then, the seed points of superpixel are optimized under the K-means framework. The effectiveness of the proposed algorithm is tested and verified with different spatial resolutions, such as Landsat 8 with 30 m, Sentinel-2 with 10 m, and SkySat with 0.5 m. A large number of experiments show that the proposed algorithm can better correct the superpixel boundary-fitting deviation problem in complex scenes and effectively promote the improvement of image classification accuracy.https://ieeexplore.ieee.org/document/10286067/Anisotropic diffusiondiffusion fluxremote sensing image classificationsuperpixel segmentation |
| spellingShingle | Xiaoli Li Jinsong Chen Longlong Zhao Hongzhong Li Jin Wang Luyi Sun Shanxin Guo Pan Chen Xuemei Zhao Superpixel Segmentation Based on Anisotropic Diffusion Model for Object-Oriented Remote Sensing Image Classification IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Anisotropic diffusion diffusion flux remote sensing image classification superpixel segmentation |
| title | Superpixel Segmentation Based on Anisotropic Diffusion Model for Object-Oriented Remote Sensing Image Classification |
| title_full | Superpixel Segmentation Based on Anisotropic Diffusion Model for Object-Oriented Remote Sensing Image Classification |
| title_fullStr | Superpixel Segmentation Based on Anisotropic Diffusion Model for Object-Oriented Remote Sensing Image Classification |
| title_full_unstemmed | Superpixel Segmentation Based on Anisotropic Diffusion Model for Object-Oriented Remote Sensing Image Classification |
| title_short | Superpixel Segmentation Based on Anisotropic Diffusion Model for Object-Oriented Remote Sensing Image Classification |
| title_sort | superpixel segmentation based on anisotropic diffusion model for object oriented remote sensing image classification |
| topic | Anisotropic diffusion diffusion flux remote sensing image classification superpixel segmentation |
| url | https://ieeexplore.ieee.org/document/10286067/ |
| work_keys_str_mv | AT xiaolili superpixelsegmentationbasedonanisotropicdiffusionmodelforobjectorientedremotesensingimageclassification AT jinsongchen superpixelsegmentationbasedonanisotropicdiffusionmodelforobjectorientedremotesensingimageclassification AT longlongzhao superpixelsegmentationbasedonanisotropicdiffusionmodelforobjectorientedremotesensingimageclassification AT hongzhongli superpixelsegmentationbasedonanisotropicdiffusionmodelforobjectorientedremotesensingimageclassification AT jinwang superpixelsegmentationbasedonanisotropicdiffusionmodelforobjectorientedremotesensingimageclassification AT luyisun superpixelsegmentationbasedonanisotropicdiffusionmodelforobjectorientedremotesensingimageclassification AT shanxinguo superpixelsegmentationbasedonanisotropicdiffusionmodelforobjectorientedremotesensingimageclassification AT panchen superpixelsegmentationbasedonanisotropicdiffusionmodelforobjectorientedremotesensingimageclassification AT xuemeizhao superpixelsegmentationbasedonanisotropicdiffusionmodelforobjectorientedremotesensingimageclassification |