Exploiting Superpixel-Based Contextual Information on Active Learning for High Spatial Resolution Remote Sensing Image Classification
Superpixel-based classification using Active Learning (AL) has shown great potential in high spatial resolution remote sensing image classification tasks. However, in existing superpixel-based classification models using AL, the expert labeling information is only used on the selected informative su...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/3/715 |
| _version_ | 1797623319289135104 |
|---|---|
| author | Jiechen Tang Hengjian Tong Fei Tong Yun Zhang Weitao Chen |
| author_facet | Jiechen Tang Hengjian Tong Fei Tong Yun Zhang Weitao Chen |
| author_sort | Jiechen Tang |
| collection | DOAJ |
| description | Superpixel-based classification using Active Learning (AL) has shown great potential in high spatial resolution remote sensing image classification tasks. However, in existing superpixel-based classification models using AL, the expert labeling information is only used on the selected informative superpixel while its neighboring superpixels are ignored. Actually, as most superpixels are over-segmented, a ground object always contains multiple superpixels. Thus, the center superpixel tends to have the same label as its neighboring superpixels. In this paper, to make full use of the expert labeling information, a Similar Neighboring Superpixels Search and Labeling (SNSSL) method was proposed and used in the AL process. Firstly, we identify superpixels with certain categories and uncertain superpixels by supervised learning. Secondly, we use the active learning method to process those uncertain superpixels. In each round of AL, the expert labeling information is not only used to enrich the training set but also used to label the similar neighboring superpixels. Similar neighboring superpixels are determined by computing the similarity of two superpixels according to CIELAB Dominant Colors distance, Correlation distance, Angular Second Moment distance and Contrast distance. The final classification map is composed of the supervised learning classification map and the active learning with SNSSL classification map. To demonstrate the performance of the proposed SNSSL method, the experiments were conducted on images from two benchmark high spatial resolution remote sensing datasets. The experiment shows that overall accuracy, average accuracy and kappa coefficients of the classification using the SNSSL have been improved obviously compared with the classification without the SNSSL. |
| first_indexed | 2024-03-11T09:27:05Z |
| format | Article |
| id | doaj.art-472ff8eb72ac434c801e3a2b2892e5d3 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T09:27:05Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-472ff8eb72ac434c801e3a2b2892e5d32023-11-16T17:53:12ZengMDPI AGRemote Sensing2072-42922023-01-0115371510.3390/rs15030715Exploiting Superpixel-Based Contextual Information on Active Learning for High Spatial Resolution Remote Sensing Image ClassificationJiechen Tang0Hengjian Tong1Fei Tong2Yun Zhang3Weitao Chen4School of Computer Science, China University of Geosciences, 68 Jincheng Street, East Lake New Technology Development Zone, Wuhan 430078, ChinaSchool of Computer Science, China University of Geosciences, 68 Jincheng Street, East Lake New Technology Development Zone, Wuhan 430078, ChinaDepartment of Geodesy and Geomatics Engineering, University of New Brunswick, 15 Dineen Drive, Fredericton, NB E3B 5A3, CanadaDepartment of Geodesy and Geomatics Engineering, University of New Brunswick, 15 Dineen Drive, Fredericton, NB E3B 5A3, CanadaSchool of Computer Science, China University of Geosciences, 68 Jincheng Street, East Lake New Technology Development Zone, Wuhan 430078, ChinaSuperpixel-based classification using Active Learning (AL) has shown great potential in high spatial resolution remote sensing image classification tasks. However, in existing superpixel-based classification models using AL, the expert labeling information is only used on the selected informative superpixel while its neighboring superpixels are ignored. Actually, as most superpixels are over-segmented, a ground object always contains multiple superpixels. Thus, the center superpixel tends to have the same label as its neighboring superpixels. In this paper, to make full use of the expert labeling information, a Similar Neighboring Superpixels Search and Labeling (SNSSL) method was proposed and used in the AL process. Firstly, we identify superpixels with certain categories and uncertain superpixels by supervised learning. Secondly, we use the active learning method to process those uncertain superpixels. In each round of AL, the expert labeling information is not only used to enrich the training set but also used to label the similar neighboring superpixels. Similar neighboring superpixels are determined by computing the similarity of two superpixels according to CIELAB Dominant Colors distance, Correlation distance, Angular Second Moment distance and Contrast distance. The final classification map is composed of the supervised learning classification map and the active learning with SNSSL classification map. To demonstrate the performance of the proposed SNSSL method, the experiments were conducted on images from two benchmark high spatial resolution remote sensing datasets. The experiment shows that overall accuracy, average accuracy and kappa coefficients of the classification using the SNSSL have been improved obviously compared with the classification without the SNSSL.https://www.mdpi.com/2072-4292/15/3/715high spatial resolution imagesuperpixel-based image classificationactive learningsupervised learninglabel spread |
| spellingShingle | Jiechen Tang Hengjian Tong Fei Tong Yun Zhang Weitao Chen Exploiting Superpixel-Based Contextual Information on Active Learning for High Spatial Resolution Remote Sensing Image Classification Remote Sensing high spatial resolution image superpixel-based image classification active learning supervised learning label spread |
| title | Exploiting Superpixel-Based Contextual Information on Active Learning for High Spatial Resolution Remote Sensing Image Classification |
| title_full | Exploiting Superpixel-Based Contextual Information on Active Learning for High Spatial Resolution Remote Sensing Image Classification |
| title_fullStr | Exploiting Superpixel-Based Contextual Information on Active Learning for High Spatial Resolution Remote Sensing Image Classification |
| title_full_unstemmed | Exploiting Superpixel-Based Contextual Information on Active Learning for High Spatial Resolution Remote Sensing Image Classification |
| title_short | Exploiting Superpixel-Based Contextual Information on Active Learning for High Spatial Resolution Remote Sensing Image Classification |
| title_sort | exploiting superpixel based contextual information on active learning for high spatial resolution remote sensing image classification |
| topic | high spatial resolution image superpixel-based image classification active learning supervised learning label spread |
| url | https://www.mdpi.com/2072-4292/15/3/715 |
| work_keys_str_mv | AT jiechentang exploitingsuperpixelbasedcontextualinformationonactivelearningforhighspatialresolutionremotesensingimageclassification AT hengjiantong exploitingsuperpixelbasedcontextualinformationonactivelearningforhighspatialresolutionremotesensingimageclassification AT feitong exploitingsuperpixelbasedcontextualinformationonactivelearningforhighspatialresolutionremotesensingimageclassification AT yunzhang exploitingsuperpixelbasedcontextualinformationonactivelearningforhighspatialresolutionremotesensingimageclassification AT weitaochen exploitingsuperpixelbasedcontextualinformationonactivelearningforhighspatialresolutionremotesensingimageclassification |