The Influence of CLBP Window Size on Urban Vegetation Type Classification Using High Spatial Resolution Satellite Images
Urban vegetation can regulate ecological balance, reduce the influence of urban heat islands, and improve human beings’ mental state. Accordingly, classification of urban vegetation types plays a significant role in urban vegetation research. This paper presents various window sizes of completed loc...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/20/3393 |
| _version_ | 1797550717230120960 |
|---|---|
| author | Zhou Chen Xianyun Fei Xiangwei Gao Xiaoxue Wang Huimin Zhao Kapo Wong Jin Yeu Tsou Yuanzhi Zhang |
| author_facet | Zhou Chen Xianyun Fei Xiangwei Gao Xiaoxue Wang Huimin Zhao Kapo Wong Jin Yeu Tsou Yuanzhi Zhang |
| author_sort | Zhou Chen |
| collection | DOAJ |
| description | Urban vegetation can regulate ecological balance, reduce the influence of urban heat islands, and improve human beings’ mental state. Accordingly, classification of urban vegetation types plays a significant role in urban vegetation research. This paper presents various window sizes of completed local binary pattern (CLBP) texture features classifying urban vegetation based on high spatial-resolution WorldView-2 images in areas of Shanghai (China) and Lianyungang (Jiangsu province, China). To demonstrate the stability and universality of different CLBP window textures, two study areas were selected. Using spectral information alone and spectral information combined with texture information, imagery is classified using random forest (RF) method based on vegetation type, showing that use of spectral information with CLBP window textures can achieve 7.28% greater accuracy than use of only spectral information for urban vegetation type classification, with accuracy greater for single vegetation types than for mixed ones. Optimal window sizes of CLBP textures for grass, shrub, arbor, shrub-grass, arbor-grass, and arbor-shrub-grass are 3 × 3, 3 × 3, 11 × 11, 9 × 9, 9 × 9, 7 × 7 for urban vegetation type classification. Furthermore, optimal CLBP window size is determined by the roughness of vegetation texture. |
| first_indexed | 2024-03-10T15:34:19Z |
| format | Article |
| id | doaj.art-37c93c9d0bbe45fd8fbe221ca3cbe685 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T15:34:19Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-37c93c9d0bbe45fd8fbe221ca3cbe6852023-11-20T17:23:26ZengMDPI AGRemote Sensing2072-42922020-10-011220339310.3390/rs12203393The Influence of CLBP Window Size on Urban Vegetation Type Classification Using High Spatial Resolution Satellite ImagesZhou Chen0Xianyun Fei1Xiangwei Gao2Xiaoxue Wang3Huimin Zhao4Kapo Wong5Jin Yeu Tsou6Yuanzhi Zhang7School of Geomatics and Marine Information, Jiangsu Ocean University, Lianyungang 222002, ChinaSchool of Geomatics and Marine Information, Jiangsu Ocean University, Lianyungang 222002, ChinaSchool of Geomatics and Marine Information, Jiangsu Ocean University, Lianyungang 222002, ChinaSchool of Geomatics and Marine Information, Jiangsu Ocean University, Lianyungang 222002, ChinaSchool of Geomatics and Marine Information, Jiangsu Ocean University, Lianyungang 222002, ChinaDepartment of Systems Engineering and Engineering Management, City University of Hong Kong, Kowloon, Hong Kong, ChinaDepartment of Architecture and Civil Engineering, City University of Hong Kong, Hong Kong, ChinaFaculty of Social Science and Asia-Pacific Studies Institute, The Chinese University of Hong Kong, New Territories, Hong Kong, ChinaUrban vegetation can regulate ecological balance, reduce the influence of urban heat islands, and improve human beings’ mental state. Accordingly, classification of urban vegetation types plays a significant role in urban vegetation research. This paper presents various window sizes of completed local binary pattern (CLBP) texture features classifying urban vegetation based on high spatial-resolution WorldView-2 images in areas of Shanghai (China) and Lianyungang (Jiangsu province, China). To demonstrate the stability and universality of different CLBP window textures, two study areas were selected. Using spectral information alone and spectral information combined with texture information, imagery is classified using random forest (RF) method based on vegetation type, showing that use of spectral information with CLBP window textures can achieve 7.28% greater accuracy than use of only spectral information for urban vegetation type classification, with accuracy greater for single vegetation types than for mixed ones. Optimal window sizes of CLBP textures for grass, shrub, arbor, shrub-grass, arbor-grass, and arbor-shrub-grass are 3 × 3, 3 × 3, 11 × 11, 9 × 9, 9 × 9, 7 × 7 for urban vegetation type classification. Furthermore, optimal CLBP window size is determined by the roughness of vegetation texture.https://www.mdpi.com/2072-4292/12/20/3393urban vegetation typecompleted local binary pattern (CLBP)window size texturethe optimal window sizeroughness |
| spellingShingle | Zhou Chen Xianyun Fei Xiangwei Gao Xiaoxue Wang Huimin Zhao Kapo Wong Jin Yeu Tsou Yuanzhi Zhang The Influence of CLBP Window Size on Urban Vegetation Type Classification Using High Spatial Resolution Satellite Images Remote Sensing urban vegetation type completed local binary pattern (CLBP) window size texture the optimal window size roughness |
| title | The Influence of CLBP Window Size on Urban Vegetation Type Classification Using High Spatial Resolution Satellite Images |
| title_full | The Influence of CLBP Window Size on Urban Vegetation Type Classification Using High Spatial Resolution Satellite Images |
| title_fullStr | The Influence of CLBP Window Size on Urban Vegetation Type Classification Using High Spatial Resolution Satellite Images |
| title_full_unstemmed | The Influence of CLBP Window Size on Urban Vegetation Type Classification Using High Spatial Resolution Satellite Images |
| title_short | The Influence of CLBP Window Size on Urban Vegetation Type Classification Using High Spatial Resolution Satellite Images |
| title_sort | influence of clbp window size on urban vegetation type classification using high spatial resolution satellite images |
| topic | urban vegetation type completed local binary pattern (CLBP) window size texture the optimal window size roughness |
| url | https://www.mdpi.com/2072-4292/12/20/3393 |
| work_keys_str_mv | AT zhouchen theinfluenceofclbpwindowsizeonurbanvegetationtypeclassificationusinghighspatialresolutionsatelliteimages AT xianyunfei theinfluenceofclbpwindowsizeonurbanvegetationtypeclassificationusinghighspatialresolutionsatelliteimages AT xiangweigao theinfluenceofclbpwindowsizeonurbanvegetationtypeclassificationusinghighspatialresolutionsatelliteimages AT xiaoxuewang theinfluenceofclbpwindowsizeonurbanvegetationtypeclassificationusinghighspatialresolutionsatelliteimages AT huiminzhao theinfluenceofclbpwindowsizeonurbanvegetationtypeclassificationusinghighspatialresolutionsatelliteimages AT kapowong theinfluenceofclbpwindowsizeonurbanvegetationtypeclassificationusinghighspatialresolutionsatelliteimages AT jinyeutsou theinfluenceofclbpwindowsizeonurbanvegetationtypeclassificationusinghighspatialresolutionsatelliteimages AT yuanzhizhang theinfluenceofclbpwindowsizeonurbanvegetationtypeclassificationusinghighspatialresolutionsatelliteimages AT zhouchen influenceofclbpwindowsizeonurbanvegetationtypeclassificationusinghighspatialresolutionsatelliteimages AT xianyunfei influenceofclbpwindowsizeonurbanvegetationtypeclassificationusinghighspatialresolutionsatelliteimages AT xiangweigao influenceofclbpwindowsizeonurbanvegetationtypeclassificationusinghighspatialresolutionsatelliteimages AT xiaoxuewang influenceofclbpwindowsizeonurbanvegetationtypeclassificationusinghighspatialresolutionsatelliteimages AT huiminzhao influenceofclbpwindowsizeonurbanvegetationtypeclassificationusinghighspatialresolutionsatelliteimages AT kapowong influenceofclbpwindowsizeonurbanvegetationtypeclassificationusinghighspatialresolutionsatelliteimages AT jinyeutsou influenceofclbpwindowsizeonurbanvegetationtypeclassificationusinghighspatialresolutionsatelliteimages AT yuanzhizhang influenceofclbpwindowsizeonurbanvegetationtypeclassificationusinghighspatialresolutionsatelliteimages |