An unsupervised semantic segmentation method that combines the ImSE-Net model with SLICm superpixel optimization
ABSTRACTIn the field of remote sensing, using a large amount of labeled image data to supervise the training of fully convolutional networks for the semantic segmentation of images is expensive. However, using a small amount of labeled data can lead to reduced network performance. This paper propose...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-12-01
|
| Series: | International Journal of Digital Earth |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/17538947.2024.2341970 |
| _version_ | 1797204862977441792 |
|---|---|
| author | Zenan Yang Haipeng Niu Xiaoxuan Wang Liang Huang Kui Yang |
| author_facet | Zenan Yang Haipeng Niu Xiaoxuan Wang Liang Huang Kui Yang |
| author_sort | Zenan Yang |
| collection | DOAJ |
| description | ABSTRACTIn the field of remote sensing, using a large amount of labeled image data to supervise the training of fully convolutional networks for the semantic segmentation of images is expensive. However, using a small amount of labeled data can lead to reduced network performance. This paper proposes an unsupervised semantic segmentation method that combines the ImSE-Net model with SLICm superpixel optimization. First, the ImSE-Net model is used to extract semantic features from the image to obtain rough semantic segmentation results. Then, the SLICm superpixel segmentation algorithm is used to segment the input image into superpixel images. Finally, an unsupervised semantic segmentation model (UGLS) is used to combine high-level abstract semantic features with detailed information on superpixels to obtain edge-optimized semantic segmentation results. Experimental results show that compared with other semantic segmentation algorithms, our method more effectively handles unbalanced areas, such as object boundaries, and achieves better segmentation results, with higher semantic consistency. |
| first_indexed | 2024-04-24T08:41:59Z |
| format | Article |
| id | doaj.art-3d3c51e951a24906a9e9a23ca39e225f |
| institution | Directory Open Access Journal |
| issn | 1753-8947 1753-8955 |
| language | English |
| last_indexed | 2024-04-24T08:41:59Z |
| publishDate | 2024-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | International Journal of Digital Earth |
| spelling | doaj.art-3d3c51e951a24906a9e9a23ca39e225f2024-04-16T15:28:03ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552024-12-0117110.1080/17538947.2024.2341970An unsupervised semantic segmentation method that combines the ImSE-Net model with SLICm superpixel optimizationZenan Yang0Haipeng Niu1Xiaoxuan Wang2Liang Huang3Kui Yang4School of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo, People’s Republic of ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo, People’s Republic of ChinaKey Laboratory of Spatio-temporal Information and Ecological Restoration of Mines of Natural Resources of the People’s Republic of China, Henan Polytechnic University, Jiaozuo, People’s Republic of ChinaFaculty of Land Resources Engineering, Kunming University of Science and Technology, Kunming, People’s Republic of ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo, People’s Republic of ChinaABSTRACTIn the field of remote sensing, using a large amount of labeled image data to supervise the training of fully convolutional networks for the semantic segmentation of images is expensive. However, using a small amount of labeled data can lead to reduced network performance. This paper proposes an unsupervised semantic segmentation method that combines the ImSE-Net model with SLICm superpixel optimization. First, the ImSE-Net model is used to extract semantic features from the image to obtain rough semantic segmentation results. Then, the SLICm superpixel segmentation algorithm is used to segment the input image into superpixel images. Finally, an unsupervised semantic segmentation model (UGLS) is used to combine high-level abstract semantic features with detailed information on superpixels to obtain edge-optimized semantic segmentation results. Experimental results show that compared with other semantic segmentation algorithms, our method more effectively handles unbalanced areas, such as object boundaries, and achieves better segmentation results, with higher semantic consistency.https://www.tandfonline.com/doi/10.1080/17538947.2024.2341970High-spatial-resolution remote sensing imagessemantic segmentationImSE-Net modelSLICm superpixel optimization modelunsupervised semantic segmentation model |
| spellingShingle | Zenan Yang Haipeng Niu Xiaoxuan Wang Liang Huang Kui Yang An unsupervised semantic segmentation method that combines the ImSE-Net model with SLICm superpixel optimization International Journal of Digital Earth High-spatial-resolution remote sensing images semantic segmentation ImSE-Net model SLICm superpixel optimization model unsupervised semantic segmentation model |
| title | An unsupervised semantic segmentation method that combines the ImSE-Net model with SLICm superpixel optimization |
| title_full | An unsupervised semantic segmentation method that combines the ImSE-Net model with SLICm superpixel optimization |
| title_fullStr | An unsupervised semantic segmentation method that combines the ImSE-Net model with SLICm superpixel optimization |
| title_full_unstemmed | An unsupervised semantic segmentation method that combines the ImSE-Net model with SLICm superpixel optimization |
| title_short | An unsupervised semantic segmentation method that combines the ImSE-Net model with SLICm superpixel optimization |
| title_sort | unsupervised semantic segmentation method that combines the imse net model with slicm superpixel optimization |
| topic | High-spatial-resolution remote sensing images semantic segmentation ImSE-Net model SLICm superpixel optimization model unsupervised semantic segmentation model |
| url | https://www.tandfonline.com/doi/10.1080/17538947.2024.2341970 |
| work_keys_str_mv | AT zenanyang anunsupervisedsemanticsegmentationmethodthatcombinestheimsenetmodelwithslicmsuperpixeloptimization AT haipengniu anunsupervisedsemanticsegmentationmethodthatcombinestheimsenetmodelwithslicmsuperpixeloptimization AT xiaoxuanwang anunsupervisedsemanticsegmentationmethodthatcombinestheimsenetmodelwithslicmsuperpixeloptimization AT lianghuang anunsupervisedsemanticsegmentationmethodthatcombinestheimsenetmodelwithslicmsuperpixeloptimization AT kuiyang anunsupervisedsemanticsegmentationmethodthatcombinestheimsenetmodelwithslicmsuperpixeloptimization AT zenanyang unsupervisedsemanticsegmentationmethodthatcombinestheimsenetmodelwithslicmsuperpixeloptimization AT haipengniu unsupervisedsemanticsegmentationmethodthatcombinestheimsenetmodelwithslicmsuperpixeloptimization AT xiaoxuanwang unsupervisedsemanticsegmentationmethodthatcombinestheimsenetmodelwithslicmsuperpixeloptimization AT lianghuang unsupervisedsemanticsegmentationmethodthatcombinestheimsenetmodelwithslicmsuperpixeloptimization AT kuiyang unsupervisedsemanticsegmentationmethodthatcombinestheimsenetmodelwithslicmsuperpixeloptimization |