Volume XLII-4/W16
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-4/W16, 237–240, 2019
https://doi.org/10.5194/isprs-archives-XLII-4-W16-237-2019
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-4/W16, 237–240, 2019
https://doi.org/10.5194/isprs-archives-XLII-4-W16-237-2019
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

  01 Oct 2019

01 Oct 2019

URBAN VEGETATION CLASSIFICATION WITH NDVI THRESHOLD VALUE METHOD WITH VERY HIGH RESOLUTION (VHR) PLEIADES IMAGERY

H. Hashim1, Z. Abd Latif2, and N. A. Adnan3 H. Hashim et al.
  • 1Faculty of Architecture, Planning and Surveying, Universiti Teknologi MARA, 40450 Shah Alam, Selangor, Malaysia
  • 2Faculty of Architecture, Planning and Surveying, Universiti Teknologi MARA, Perak Branch, 32610 Seri Iskandar, Perak, Malaysia.
  • 3Applied Remote Sensing and Geospatial Research Group, Centre of Studies for Surveying, Science and Geomatics, Faculty of Architecture, Planning and Surveying, Universiti Teknologi MARA, 40450 Shah Alam, Selangor, Malaysia

Keywords: Remote Sensing, Pleiades, Normalized Difference Vegetation Index (NDVI), High Vegetation and Low Vegetation

Abstract. Recently the sensing data for urban mapping used is in high demand together with the accessible of very high resolution (VHR) satellite data such as Worldview and Pleiades. This article presents the use of very high resolution (VHR) remote sensing data for urban vegetation mapping. The research objectives were to assess the use of Pleiades imagery to extricate the data of urban vegetation in urban area of Kuala Lumpur. Normalized Difference Vegetation Index (NDVI) were employs with VHR data to find Vegetation Index for classification process of vegetation and non-vegetation classes. Land use classes are easily determined by computing their Normalized Difference Vegetation Index for Land use land cover classification. Maximum likelihood was conducted for the classification phase. NDVI were extracted from the imagery to assist the process of classification. NDVI method is use by referring to its features such as vegetation at different NDVI threshold values. The result showed three classes of land cover that consist of low vegetation, high vegetation and non-vegetation area. The accuracy assessment gained was then being implemented using the visual interpretation and overall accuracy achieved was 70.740% with kappa coefficient of 0.5. This study gained the proposed threshold method using NDVI value able to identify and classify urban vegetation with the use of VHR Pleiades imagery and need further improvement when apply to different area of interest and different land use land cover characteristics. The information achieved from the result able to help planners for future planning for conservation of vegetation in urban area.