An Object-Based Markov Random Field with Partition-Global Alternately Updated for Semantic Segmentation of High Spatial Resolution Remote Sensing Image
The Markov random field (MRF) method is widely used in remote sensing image semantic segmentation because of its excellent spatial (relationship description) ability. However, there are some targets that are relatively small and sparsely distributed in the entire image, which makes it easy to miscla...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/1/127 |
| _version_ | 1797497731607953408 |
|---|---|
| author | Hongtai Yao Xianpei Wang Le Zhao Meng Tian Zini Jian Li Gong Bowen Li |
| author_facet | Hongtai Yao Xianpei Wang Le Zhao Meng Tian Zini Jian Li Gong Bowen Li |
| author_sort | Hongtai Yao |
| collection | DOAJ |
| description | The Markov random field (MRF) method is widely used in remote sensing image semantic segmentation because of its excellent spatial (relationship description) ability. However, there are some targets that are relatively small and sparsely distributed in the entire image, which makes it easy to misclassify these pixels into different classes. To solve this problem, this paper proposes an object-based Markov random field method with partition-global alternately updated (OMRF-PGAU). First, four partition images are constructed based on the original image, they overlap with each other and can be reconstructed into the original image; the number of categories and region granularity for these partition images are set. Then, the MRF model is built on the partition images and the original image, their segmentations are alternately updated. The update path adopts a circular path, and the correlation assumption is adopted to establish the connection between the label fields of partition images and the original image. Finally, the relationship between each label field is constantly updated, and the final segmentation result is output after the segmentation has converged. Experiments on texture images and different remote sensing image datasets show that the proposed OMRF-PGAU algorithm has a better segmentation performance than other selected state-of-the-art MRF-based methods. |
| first_indexed | 2024-03-10T03:24:24Z |
| format | Article |
| id | doaj.art-c45c60ea1e674e108fb0b8ace33b713d |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T03:24:24Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-c45c60ea1e674e108fb0b8ace33b713d2023-11-23T12:13:34ZengMDPI AGRemote Sensing2072-42922021-12-0114112710.3390/rs14010127An Object-Based Markov Random Field with Partition-Global Alternately Updated for Semantic Segmentation of High Spatial Resolution Remote Sensing ImageHongtai Yao0Xianpei Wang1Le Zhao2Meng Tian3Zini Jian4Li Gong5Bowen Li6Electronic Information School, Wuhan University, Wuhan 430072, ChinaElectronic Information School, Wuhan University, Wuhan 430072, ChinaSchool of Physics and Electronics, North China University of Water Resources and Electric Power, Zhengzhou 450046, ChinaElectronic Information School, Wuhan University, Wuhan 430072, ChinaElectronic Information School, Wuhan University, Wuhan 430072, ChinaElectronic Information School, Wuhan University, Wuhan 430072, ChinaElectronic Information School, Wuhan University, Wuhan 430072, ChinaThe Markov random field (MRF) method is widely used in remote sensing image semantic segmentation because of its excellent spatial (relationship description) ability. However, there are some targets that are relatively small and sparsely distributed in the entire image, which makes it easy to misclassify these pixels into different classes. To solve this problem, this paper proposes an object-based Markov random field method with partition-global alternately updated (OMRF-PGAU). First, four partition images are constructed based on the original image, they overlap with each other and can be reconstructed into the original image; the number of categories and region granularity for these partition images are set. Then, the MRF model is built on the partition images and the original image, their segmentations are alternately updated. The update path adopts a circular path, and the correlation assumption is adopted to establish the connection between the label fields of partition images and the original image. Finally, the relationship between each label field is constantly updated, and the final segmentation result is output after the segmentation has converged. Experiments on texture images and different remote sensing image datasets show that the proposed OMRF-PGAU algorithm has a better segmentation performance than other selected state-of-the-art MRF-based methods.https://www.mdpi.com/2072-4292/14/1/127object-based Markov random fieldhigh spatial resolution remote sensing imagesemantic segmentationcorrelation assumption |
| spellingShingle | Hongtai Yao Xianpei Wang Le Zhao Meng Tian Zini Jian Li Gong Bowen Li An Object-Based Markov Random Field with Partition-Global Alternately Updated for Semantic Segmentation of High Spatial Resolution Remote Sensing Image Remote Sensing object-based Markov random field high spatial resolution remote sensing image semantic segmentation correlation assumption |
| title | An Object-Based Markov Random Field with Partition-Global Alternately Updated for Semantic Segmentation of High Spatial Resolution Remote Sensing Image |
| title_full | An Object-Based Markov Random Field with Partition-Global Alternately Updated for Semantic Segmentation of High Spatial Resolution Remote Sensing Image |
| title_fullStr | An Object-Based Markov Random Field with Partition-Global Alternately Updated for Semantic Segmentation of High Spatial Resolution Remote Sensing Image |
| title_full_unstemmed | An Object-Based Markov Random Field with Partition-Global Alternately Updated for Semantic Segmentation of High Spatial Resolution Remote Sensing Image |
| title_short | An Object-Based Markov Random Field with Partition-Global Alternately Updated for Semantic Segmentation of High Spatial Resolution Remote Sensing Image |
| title_sort | object based markov random field with partition global alternately updated for semantic segmentation of high spatial resolution remote sensing image |
| topic | object-based Markov random field high spatial resolution remote sensing image semantic segmentation correlation assumption |
| url | https://www.mdpi.com/2072-4292/14/1/127 |
| work_keys_str_mv | AT hongtaiyao anobjectbasedmarkovrandomfieldwithpartitionglobalalternatelyupdatedforsemanticsegmentationofhighspatialresolutionremotesensingimage AT xianpeiwang anobjectbasedmarkovrandomfieldwithpartitionglobalalternatelyupdatedforsemanticsegmentationofhighspatialresolutionremotesensingimage AT lezhao anobjectbasedmarkovrandomfieldwithpartitionglobalalternatelyupdatedforsemanticsegmentationofhighspatialresolutionremotesensingimage AT mengtian anobjectbasedmarkovrandomfieldwithpartitionglobalalternatelyupdatedforsemanticsegmentationofhighspatialresolutionremotesensingimage AT zinijian anobjectbasedmarkovrandomfieldwithpartitionglobalalternatelyupdatedforsemanticsegmentationofhighspatialresolutionremotesensingimage AT ligong anobjectbasedmarkovrandomfieldwithpartitionglobalalternatelyupdatedforsemanticsegmentationofhighspatialresolutionremotesensingimage AT bowenli anobjectbasedmarkovrandomfieldwithpartitionglobalalternatelyupdatedforsemanticsegmentationofhighspatialresolutionremotesensingimage AT hongtaiyao objectbasedmarkovrandomfieldwithpartitionglobalalternatelyupdatedforsemanticsegmentationofhighspatialresolutionremotesensingimage AT xianpeiwang objectbasedmarkovrandomfieldwithpartitionglobalalternatelyupdatedforsemanticsegmentationofhighspatialresolutionremotesensingimage AT lezhao objectbasedmarkovrandomfieldwithpartitionglobalalternatelyupdatedforsemanticsegmentationofhighspatialresolutionremotesensingimage AT mengtian objectbasedmarkovrandomfieldwithpartitionglobalalternatelyupdatedforsemanticsegmentationofhighspatialresolutionremotesensingimage AT zinijian objectbasedmarkovrandomfieldwithpartitionglobalalternatelyupdatedforsemanticsegmentationofhighspatialresolutionremotesensingimage AT ligong objectbasedmarkovrandomfieldwithpartitionglobalalternatelyupdatedforsemanticsegmentationofhighspatialresolutionremotesensingimage AT bowenli objectbasedmarkovrandomfieldwithpartitionglobalalternatelyupdatedforsemanticsegmentationofhighspatialresolutionremotesensingimage |