Multi-Label Remote Sensing Scene Classification Using Multi-Bag Integration
For remote sensing (RS) scene classification, most of the existing techniques annotate a scene image with merely a single semantic label. However, with the recent advance of remote sensing technology, more abundant information is contained in high-resolution scenes, making a scene image having multi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8811498/ |
| _version_ | 1819174682123829248 |
|---|---|
| author | Xin Wang Xingnan Xiong Chen Ning |
| author_facet | Xin Wang Xingnan Xiong Chen Ning |
| author_sort | Xin Wang |
| collection | DOAJ |
| description | For remote sensing (RS) scene classification, most of the existing techniques annotate a scene image with merely a single semantic label. However, with the recent advance of remote sensing technology, more abundant information is contained in high-resolution scenes, making a scene image having multiple semantic meanings (i.e., multilabels). Since multi-label RS scene image annotation is a domain full of challenges due to the ambiguities between complicated scene contents and labels, it motivates us to present a novel algorithm which is based on multi-bag integration. First, to describe the semantic content of RS scene image, we propose to partition a scene image into image patches, defined by a regular grid, and extract the heterogeneous features within each. Second, two kinds of image instance bag, namely segmented instance bag (SIB) and layered instance bag (LIB), are designed to represent the scene image. Third, a Mahalanobis distance-based K-Medoids approach is applied to cluster SIB and LIB, respectively, to convert the multi-instance into single-instance, and then the obtained two single-instances are concatenated to generate more powerful scene-aware representation. At last, a multi-class classification technique is used to make predictions on the class labels. Experiments are performed on real remote sensing images and the results show that the proposed method is valid and can achieve superior performance to a number of state-of-the-art approaches. |
| first_indexed | 2024-12-22T20:42:51Z |
| format | Article |
| id | doaj.art-1ab4389196d142989b08d9f2c83e04ae |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T20:42:51Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-1ab4389196d142989b08d9f2c83e04ae2022-12-21T18:13:18ZengIEEEIEEE Access2169-35362019-01-01712039912041010.1109/ACCESS.2019.29371888811498Multi-Label Remote Sensing Scene Classification Using Multi-Bag IntegrationXin Wang0https://orcid.org/0000-0003-0203-9964Xingnan Xiong1Chen Ning2https://orcid.org/0000-0002-3026-2496College of Computer and Information, Hohai University, Nanjing, ChinaCollege of Computer and Information, Hohai University, Nanjing, ChinaSchool of Physics and Technology, Nanjing Normal University, Nanjing, ChinaFor remote sensing (RS) scene classification, most of the existing techniques annotate a scene image with merely a single semantic label. However, with the recent advance of remote sensing technology, more abundant information is contained in high-resolution scenes, making a scene image having multiple semantic meanings (i.e., multilabels). Since multi-label RS scene image annotation is a domain full of challenges due to the ambiguities between complicated scene contents and labels, it motivates us to present a novel algorithm which is based on multi-bag integration. First, to describe the semantic content of RS scene image, we propose to partition a scene image into image patches, defined by a regular grid, and extract the heterogeneous features within each. Second, two kinds of image instance bag, namely segmented instance bag (SIB) and layered instance bag (LIB), are designed to represent the scene image. Third, a Mahalanobis distance-based K-Medoids approach is applied to cluster SIB and LIB, respectively, to convert the multi-instance into single-instance, and then the obtained two single-instances are concatenated to generate more powerful scene-aware representation. At last, a multi-class classification technique is used to make predictions on the class labels. Experiments are performed on real remote sensing images and the results show that the proposed method is valid and can achieve superior performance to a number of state-of-the-art approaches.https://ieeexplore.ieee.org/document/8811498/Remote sensingmulti-labelscene classificationmulti-bag |
| spellingShingle | Xin Wang Xingnan Xiong Chen Ning Multi-Label Remote Sensing Scene Classification Using Multi-Bag Integration IEEE Access Remote sensing multi-label scene classification multi-bag |
| title | Multi-Label Remote Sensing Scene Classification Using Multi-Bag Integration |
| title_full | Multi-Label Remote Sensing Scene Classification Using Multi-Bag Integration |
| title_fullStr | Multi-Label Remote Sensing Scene Classification Using Multi-Bag Integration |
| title_full_unstemmed | Multi-Label Remote Sensing Scene Classification Using Multi-Bag Integration |
| title_short | Multi-Label Remote Sensing Scene Classification Using Multi-Bag Integration |
| title_sort | multi label remote sensing scene classification using multi bag integration |
| topic | Remote sensing multi-label scene classification multi-bag |
| url | https://ieeexplore.ieee.org/document/8811498/ |
| work_keys_str_mv | AT xinwang multilabelremotesensingsceneclassificationusingmultibagintegration AT xingnanxiong multilabelremotesensingsceneclassificationusingmultibagintegration AT chenning multilabelremotesensingsceneclassificationusingmultibagintegration |