Multiple Superpixel Graphs Learning Based on Adaptive Multiscale Segmentation for Hyperspectral Image Classification
Hyperspectral image classification (HSIC) methods usually require more training samples for better classification performance. However, a large number of labeled samples are difficult to obtain because it is cost- and time-consuming to label an HSI in a pixel-wise way. Therefore, how to overcome the...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/3/681 |
| _version_ | 1797484996525555712 |
|---|---|
| author | Chunhui Zhao Boao Qin Shou Feng Wenxiang Zhu |
| author_facet | Chunhui Zhao Boao Qin Shou Feng Wenxiang Zhu |
| author_sort | Chunhui Zhao |
| collection | DOAJ |
| description | Hyperspectral image classification (HSIC) methods usually require more training samples for better classification performance. However, a large number of labeled samples are difficult to obtain because it is cost- and time-consuming to label an HSI in a pixel-wise way. Therefore, how to overcome the problem of insufficient accuracy and stability under the condition of small labeled training sample size (SLTSS) is still a challenge for HSIC. In this paper, we proposed a novel multiple superpixel graphs learning method based on adaptive multiscale segmentation (MSGLAMS) for HSI classification to address this problem. First, the multiscale-superpixel-based framework can reduce the adverse effect of improper selection of a superpixel segmentation scale on the classification accuracy while saving the cost to manually seek a suitable segmentation scale. To make full use of the superpixel-level spatial information of different segmentation scales, a novel two-steps multiscale selection strategy is designed to adaptively select a group of complementary scales (multiscale). To fix the bias and instability of a single model, multiple superpixel-based graphical models obatined by constructing superpixel contracted graph of fusion scales are developed to jointly predict the final results via a pixel-level fusion strategy. Experimental results show that the proposed MSGLAMS has better performance when compared with other state-of-the-art algorithms. Specifically, its overall accuracy achieves 94.312%, 99.217%, 98.373% and 92.693% on Indian Pines, Salinas and University of Pavia, and the more challenging dataset Houston2013, respectively. |
| first_indexed | 2024-03-09T23:12:28Z |
| format | Article |
| id | doaj.art-2887740308354bd3a61636a6b054b188 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T23:12:28Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-2887740308354bd3a61636a6b054b1882023-11-23T17:41:44ZengMDPI AGRemote Sensing2072-42922022-01-0114368110.3390/rs14030681Multiple Superpixel Graphs Learning Based on Adaptive Multiscale Segmentation for Hyperspectral Image ClassificationChunhui Zhao0Boao Qin1Shou Feng2Wenxiang Zhu3College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, ChinaCollege of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, ChinaCollege of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, ChinaCollege of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, ChinaHyperspectral image classification (HSIC) methods usually require more training samples for better classification performance. However, a large number of labeled samples are difficult to obtain because it is cost- and time-consuming to label an HSI in a pixel-wise way. Therefore, how to overcome the problem of insufficient accuracy and stability under the condition of small labeled training sample size (SLTSS) is still a challenge for HSIC. In this paper, we proposed a novel multiple superpixel graphs learning method based on adaptive multiscale segmentation (MSGLAMS) for HSI classification to address this problem. First, the multiscale-superpixel-based framework can reduce the adverse effect of improper selection of a superpixel segmentation scale on the classification accuracy while saving the cost to manually seek a suitable segmentation scale. To make full use of the superpixel-level spatial information of different segmentation scales, a novel two-steps multiscale selection strategy is designed to adaptively select a group of complementary scales (multiscale). To fix the bias and instability of a single model, multiple superpixel-based graphical models obatined by constructing superpixel contracted graph of fusion scales are developed to jointly predict the final results via a pixel-level fusion strategy. Experimental results show that the proposed MSGLAMS has better performance when compared with other state-of-the-art algorithms. Specifically, its overall accuracy achieves 94.312%, 99.217%, 98.373% and 92.693% on Indian Pines, Salinas and University of Pavia, and the more challenging dataset Houston2013, respectively.https://www.mdpi.com/2072-4292/14/3/681hyperspectral image classificationsuperpixel segmentationgraph learningsparse representationmultiscale fusion |
| spellingShingle | Chunhui Zhao Boao Qin Shou Feng Wenxiang Zhu Multiple Superpixel Graphs Learning Based on Adaptive Multiscale Segmentation for Hyperspectral Image Classification Remote Sensing hyperspectral image classification superpixel segmentation graph learning sparse representation multiscale fusion |
| title | Multiple Superpixel Graphs Learning Based on Adaptive Multiscale Segmentation for Hyperspectral Image Classification |
| title_full | Multiple Superpixel Graphs Learning Based on Adaptive Multiscale Segmentation for Hyperspectral Image Classification |
| title_fullStr | Multiple Superpixel Graphs Learning Based on Adaptive Multiscale Segmentation for Hyperspectral Image Classification |
| title_full_unstemmed | Multiple Superpixel Graphs Learning Based on Adaptive Multiscale Segmentation for Hyperspectral Image Classification |
| title_short | Multiple Superpixel Graphs Learning Based on Adaptive Multiscale Segmentation for Hyperspectral Image Classification |
| title_sort | multiple superpixel graphs learning based on adaptive multiscale segmentation for hyperspectral image classification |
| topic | hyperspectral image classification superpixel segmentation graph learning sparse representation multiscale fusion |
| url | https://www.mdpi.com/2072-4292/14/3/681 |
| work_keys_str_mv | AT chunhuizhao multiplesuperpixelgraphslearningbasedonadaptivemultiscalesegmentationforhyperspectralimageclassification AT boaoqin multiplesuperpixelgraphslearningbasedonadaptivemultiscalesegmentationforhyperspectralimageclassification AT shoufeng multiplesuperpixelgraphslearningbasedonadaptivemultiscalesegmentationforhyperspectralimageclassification AT wenxiangzhu multiplesuperpixelgraphslearningbasedonadaptivemultiscalesegmentationforhyperspectralimageclassification |