Comparison of Classification Algorithms and Training Sample Sizes in Urban Land Classification with Landsat Thematic Mapper Imagery
Although a large number of new image classification algorithms have been developed, they are rarely tested with the same classification task. In this research, with the same Landsat Thematic Mapper (TM) data set and the same classification scheme over Guangzhou City, China, we tested two unsupervi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2014-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2072-4292/6/2/964 |
| _version_ | 1818974417282138112 |
|---|---|
| author | Congcong Li Jie Wang Lei Wang Luanyun Hu Peng Gong |
| author_facet | Congcong Li Jie Wang Lei Wang Luanyun Hu Peng Gong |
| author_sort | Congcong Li |
| collection | DOAJ |
| description | Although a large number of new image classification algorithms have been developed, they are rarely tested with the same classification task. In this research, with the same Landsat Thematic Mapper (TM) data set and the same classification scheme over Guangzhou City, China, we tested two unsupervised and 13 supervised classification algorithms, including a number of machine learning algorithms that became popular in remote sensing during the past 20 years. Our analysis focused primarily on the spectral information provided by the TM data. We assessed all algorithms in a per-pixel classification decision experiment and all supervised algorithms in a segment-based experiment. We found that when sufficiently representative training samples were used, most algorithms performed reasonably well. Lack of training samples led to greater classification accuracy discrepancies than classification algorithms themselves. Some algorithms were more tolerable to insufficient (less representative) training samples than others. Many algorithms improved the overall accuracy marginally with per-segment decision making. |
| first_indexed | 2024-12-20T15:39:43Z |
| format | Article |
| id | doaj.art-d9bda5014bde42c68fd31c491a399819 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-20T15:39:43Z |
| publishDate | 2014-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-d9bda5014bde42c68fd31c491a3998192022-12-21T19:35:16ZengMDPI AGRemote Sensing2072-42922014-01-016296498310.3390/rs6020964rs6020964Comparison of Classification Algorithms and Training Sample Sizes in Urban Land Classification with Landsat Thematic Mapper ImageryCongcong Li0Jie Wang1Lei Wang2Luanyun Hu3Peng Gong4State Key Laboratory of Remote Sensing Science, and College of Global Change and Earth System Science, Beijing Normal University, Beijing 100875, ChinaState Key Laboratory of Remote Sensing Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, ChinaState Key Laboratory of Remote Sensing Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, ChinaMinistry of Education Key Laboratory for Earth System Modeling, Center for Earth System Science, Tsinghua University, Beijing 100084, ChinaState Key Laboratory of Remote Sensing Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, ChinaAlthough a large number of new image classification algorithms have been developed, they are rarely tested with the same classification task. In this research, with the same Landsat Thematic Mapper (TM) data set and the same classification scheme over Guangzhou City, China, we tested two unsupervised and 13 supervised classification algorithms, including a number of machine learning algorithms that became popular in remote sensing during the past 20 years. Our analysis focused primarily on the spectral information provided by the TM data. We assessed all algorithms in a per-pixel classification decision experiment and all supervised algorithms in a segment-based experiment. We found that when sufficiently representative training samples were used, most algorithms performed reasonably well. Lack of training samples led to greater classification accuracy discrepancies than classification algorithms themselves. Some algorithms were more tolerable to insufficient (less representative) training samples than others. Many algorithms improved the overall accuracy marginally with per-segment decision making.http://www.mdpi.com/2072-4292/6/2/964machine learningmaximum likelihood classificationlogistic regressionsupport vector machinetree classifiersrandom forests |
| spellingShingle | Congcong Li Jie Wang Lei Wang Luanyun Hu Peng Gong Comparison of Classification Algorithms and Training Sample Sizes in Urban Land Classification with Landsat Thematic Mapper Imagery Remote Sensing machine learning maximum likelihood classification logistic regression support vector machine tree classifiers random forests |
| title | Comparison of Classification Algorithms and Training Sample Sizes in Urban Land Classification with Landsat Thematic Mapper Imagery |
| title_full | Comparison of Classification Algorithms and Training Sample Sizes in Urban Land Classification with Landsat Thematic Mapper Imagery |
| title_fullStr | Comparison of Classification Algorithms and Training Sample Sizes in Urban Land Classification with Landsat Thematic Mapper Imagery |
| title_full_unstemmed | Comparison of Classification Algorithms and Training Sample Sizes in Urban Land Classification with Landsat Thematic Mapper Imagery |
| title_short | Comparison of Classification Algorithms and Training Sample Sizes in Urban Land Classification with Landsat Thematic Mapper Imagery |
| title_sort | comparison of classification algorithms and training sample sizes in urban land classification with landsat thematic mapper imagery |
| topic | machine learning maximum likelihood classification logistic regression support vector machine tree classifiers random forests |
| url | http://www.mdpi.com/2072-4292/6/2/964 |
| work_keys_str_mv | AT congcongli comparisonofclassificationalgorithmsandtrainingsamplesizesinurbanlandclassificationwithlandsatthematicmapperimagery AT jiewang comparisonofclassificationalgorithmsandtrainingsamplesizesinurbanlandclassificationwithlandsatthematicmapperimagery AT leiwang comparisonofclassificationalgorithmsandtrainingsamplesizesinurbanlandclassificationwithlandsatthematicmapperimagery AT luanyunhu comparisonofclassificationalgorithmsandtrainingsamplesizesinurbanlandclassificationwithlandsatthematicmapperimagery AT penggong comparisonofclassificationalgorithmsandtrainingsamplesizesinurbanlandclassificationwithlandsatthematicmapperimagery |