Mangroves are known as salt-tolerant evergreen forests, whereas its create land-ocean interface ecosystems. Besides,
mangroves bring direct and indirect benefits to human activities and play a major role as significant habitat for
sustaining biodiversity. However, mangrove ecosystem study based on the mangrove species are very crucial to get a
better understanding of their characteristics and ways to separate among them. In this paper, discriminant functions
obtained using statistical approach were used to generate the score range for six mangrove species (Rhizophora
apiculata, Acrostichum aurem, Acrostichum speciosum, Acanthus ilicifolius, Ceriops tagal and Sonneratia ovata) in
Matang Mangrove Forest Reserve (MMFR), Perak. With the computation of score range for each species, the fraction of
the species can be determined using the proposed algorithm. The results indicate that by using 11 discriminant functions
out of 16 are more effective to separate the mangrove species as the higher accuracy was obtained. Overall, the
determination of leaf sample’s species is chosen base on the highest fraction measured among the six mangrove species.
The obtained accuracy for mangrove species using statistical approach is low since it is impossible to successfully
separate all the mangrove species in leaf level using their inherent reflectance properties. However, the obtained
accuracy results are satisfactory and able to discriminate the examined mangrove species at species scale.
Mangrove vegetation is widely employed and studied as it is a unique ecosystem which is able to provide plenty of goods and applications to our country. In this paper, high resolution airborne image data obtained the flight mission on Kuala Sepetang Mangrove Forest Reserve, Perak, Malaysia will be used for mangrove species mapping. Supervised classification using the retrieved surface reflectance will be performed to classify the airborne data using Geomatica 2013 software package. The ground truth data will be used to validate the classification accuracy. High correlation of R2=0.873 was achieved in this study indicate that high resolution airborne data is reliable and suitable used for mangrove species mapping.
The problem of difficulty in obtaining cloud-free scene at the Equatorial region from satellite platforms can be overcome by using airborne imagery. Airborne digital imagery has proved to be an effective tool for land cover studies. Airborne digital camera imageries were selected in this present study because of the airborne digital image provides higher spatial resolution data for mapping a small study area. The main objective of this study is to classify the RGB bands imageries taken from a low-altitude Cropcam UAV for land cover/use mapping over USM campus, penang Island, Malaysia. A conventional digital camera was used to capture images from an elevation of 320 meter on board on an UAV autopilot. This technique was cheaper and economical compared with other airborne studies. The artificial neural network (NN) and maximum likelihood classifier (MLC) were used to classify the digital imageries captured by using Cropcam UAV over USM campus, Penang Islands, Malaysia. The supervised classifier was chosen based on the highest overall accuracy (<80%) and Kappa statistic (<0.8). The classified land cover map was geometrically corrected to provide a geocoded map. The results produced by this study indicated that land cover features could be clearly identified and classified into a land cover map. This study indicates the use of a conventional digital camera as a sensor on board on an UAV autopilot can provide useful information for planning and development of a small area of coverage.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.