This study is centered on automatic mapping approach to identify and count coconut trees in the municipality of San Fernando, Cebu for the purpose of source mapping for viable sustainable construction materials. Through the employment of theories and applications of Object-Based Image Analysis (OBIA), a rule set was developed in eCognition Developer to automatically identify and count coconut trees in orchards. The data used in the rule set were the red, green and blue (RGB) spectral bands of the orthophoto with a spatial resolution of 0.50m, and the Normalized Digital Surface Elevation (NDSM) with a spatial resolution of 1.0m. The mapping approach yielded an overall accuracy, user accuracy and producer accuracy of 71.19%, 78.82% and 88.02%, respectively. The run time of automatic detection of the coconut trees in the sampling area was recorded to be 30 seconds, taking a significantly shorter amount of time than visually analysing the area with a recorded time of 90 minutes. The application of the developed rule set to the entire municipality resulted in 96, 099 detected coconut trees with Barangay Cabatbatan having the highest tree count of 36, 621 in a land area of 19.336 square kilometres.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.