TY - JOUR
T1 - Urban tree analysis using unmanned aerial vehicle (uav) images and object-based classification (case study
T2 - 3rd International Geography Seminar 2019, IGEOS 2019
AU - Hernina, R.
AU - Wicaksono, Arif
N1 - Publisher Copyright:
© Published under licence by IOP Publishing Ltd.
PY - 2021/3/17
Y1 - 2021/3/17
N2 - This paper aims to analyze the urban trees located in University of Indonesia campus using UAV image and Object-based Image Analysis (OBIA). Herein, DJI Phantom 4 Pro was flown at 90 meter height to take image above the study area with spatial resolution of 2.4 cm/pixel. The image from UAV then processed using Agisoft Photoscan and underwent geometric correction. The image containing red, green and blue (RGB) bands then segmented with multi-resolution algorithm. Four Vegetation Indices (VIs) namely Normalized Green-red Difference Index (NGRDI), Visible Atmospherically Resistant Index (VARI), Visible-band Difference Vegetation Index (VDVI) and Red-Green Ratio Index (RGRI) were used to develop rule sets for land use land cover (LULC) classification. Vegetation class was separated from LULC image to be further analysed with ArcGIS using information from ground truth observation. Final product is urban tree map containing tree names and LULC classes.
AB - This paper aims to analyze the urban trees located in University of Indonesia campus using UAV image and Object-based Image Analysis (OBIA). Herein, DJI Phantom 4 Pro was flown at 90 meter height to take image above the study area with spatial resolution of 2.4 cm/pixel. The image from UAV then processed using Agisoft Photoscan and underwent geometric correction. The image containing red, green and blue (RGB) bands then segmented with multi-resolution algorithm. Four Vegetation Indices (VIs) namely Normalized Green-red Difference Index (NGRDI), Visible Atmospherically Resistant Index (VARI), Visible-band Difference Vegetation Index (VDVI) and Red-Green Ratio Index (RGRI) were used to develop rule sets for land use land cover (LULC) classification. Vegetation class was separated from LULC image to be further analysed with ArcGIS using information from ground truth observation. Final product is urban tree map containing tree names and LULC classes.
UR - http://www.scopus.com/inward/record.url?scp=85103437801&partnerID=8YFLogxK
U2 - 10.1088/1755-1315/683/1/012105
DO - 10.1088/1755-1315/683/1/012105
M3 - Conference article
AN - SCOPUS:85103437801
SN - 1755-1307
VL - 683
JO - IOP Conference Series: Earth and Environmental Science
JF - IOP Conference Series: Earth and Environmental Science
IS - 1
M1 - 012105
Y2 - 31 August 2019
ER -