2018 Paper on “A novel approach for vegetation classification using UAV-based hyperspectral imaging”

5 Dec 2018 11:17 AM
By Joy Luza

Abstract

The use of unmanned aerial vehicle (UAV)-based spectral imaging offers considerable advantages in high-resolution remote-sensing applications. However, the number of sensors mountable on a UAV is limited, and selecting the optimal combination of spectral bands is complex but crucial for conventional UAV-based multispectral imaging systems. To overcome these limitations, we adopted a liquid crystal tunable filter (LCTF), which can transmit selected wavelengths without the need to exchange optical filters. For calibration and validation of the LCTF-based hyperspectral imaging system, a field campaign was conducted in the Philippines during March 28–April 3, 2016. In this campaign, UAV-based hyperspectral imaging was performed in several vegetated areas, and the spectral reflectances of 14 different ground objects were measured. Additionally, the machine learning (ML) approach using a support vector machine (SVM) model was applied to the obtained dataset, and a high-resolution classification map was then produced from the aerial hyperspectral images. The results clearly showed that a large amount of misclassification occurred in shaded areas due to the difference in spectral reflectance between sunlit and shaded areas. It was also found that the classification accuracy was drastically improved by training the SVM model with both sunlit and shaded spectral data. As a result, we achieved a classification accuracy of 94.5% in vegetated areas.

Authors

Joel Joseph S. Marciano Jr., PhD
Acting Director

Dr. Marciano, Jr. Joined the DOST-ASTI in March 2016 as its Acting Director. He is a licensed Electronics Engineer who graduated with a degree in Bachelor of Science in Electrical Engineering from the University of the Philippines, Diliman and was conferred with Doctorate Degree in Electrical Engineering from the University of New South Wales.

Under his leadership, the DOST-ASTI is reviving and ramping up its research on radio frequency (RF) electronics. This is done through various research projects, some of which are in collaboration with the UP-EEEI. Aside from form overseeing the operations of the DOST-ASTI, Dir. Marciano Jr. is currently engaged in several projects such as Communications Relay Buoys for the Communications Relay for CoCoMoNets, Development and Deployment of Advanced Spectrum Platform Network, Development of Software Defined Radio (SDR) based Satellite Telemetry and Telecommand System Simulator Projects, and Development of Extreme Weather Monitoring and Information Sharing System in the Philippines as Project Adviser, as well as the Project Leader of EPDC as Platform for Inclusive Innovation Program (EPIIC) and Synthetic Aperture Radar (SAR) and Automatic Identification System (AIS) for Innovative Terrestrial Monitoring and Maritime Surveillance.

Tetsuro Ishida

Junichi Kurihara

Fra Angelico Viray

Shielo Baes Namuco

Enrico Paringit

Gay Jane Perez

Yukihiro Takashi

Published on

January 2018

Published at

Elsevier B.V.

Link to Publication

https://www.sciencedirect.com/science/article/pii/S0168169917310499?via%3Dihub