University of PardubiceFaculty of Economics and Administration

University

Employees
|
Students
Česky

Publication detail

Utilization of Visible Spectral Indices for Land Cover Identification: Processing of RGB UAV-Borne

Authors: Komárková Jitka | Sedlák Pavel | Jech Jakub | Mašín Oldřich

Year: 2021

Type of publication: ostatní - přednáška nebo poster

Page from-to: nestránkováno

Titles:

Language	Name	Abstract	Keywords
eng	Utilization of Visible Spectral Indices for Land Cover Identification: Processing of RGB UAV-Borne	Land use/land cover (LU/LC) identification and consequent identification of LU/LC changes in time belong to important tasks, which can significantly support many human activities, including e.g. environment protection, water management, and urban planning. Remotely sensed data are used to identify LU/LC and calculate changes. UAVs can serve as a cheap and fast source of remotely sensed data for smaller areas. Data sensed using UAVs has very high spatial resolution and can be collected on demand, of course with respect to legal rules and weather conditions. Cheaper UAVs are equipped with an RGB camera only. Processing of RGB UAV-borne imagery by means of visible spectral indices (sometimes called vegetation indices) is described. Data was sensed by authors in April by means of DJI Phantom 3 with a built-in RGB camera by the flight planned in advance. Namely, CIVE, ExG, ExR, NDI, VDVI indices, and R/G ratio are used to process data and identify clear water surface, green vegetation, and dry vegetation as key land cover types. Results are interpreted and visualized. Each index accentuates another land cover type. Along with visual interpretation, RGB data can be successfully used for LU/LC changes detection.	Land Cover; Visible Spectral Indices; UAV