An Integrated Approach: Watershed Segmentation with Local Maxima and Minima Algorithms for Tree Crown Delineation of Mango (Mangifera indica) using UAV Multispectral Imagery

Abstract

Precision forestry and agriculture rely on precise tree crown delineation as a fundamental component for effective forest management activities. The selection of appropriate techniques and algorithms for tree crown delineation significantly influences the accuracy and reliability of the outcomes. This study was conducted in a mango plantation at Universiti Teknologi MARA, Arau, Perlis, employing Unmanned Aerial Vehicle (UAV) multispectral imaging. The focus is to assess the accuracy of tree crown delineation using two different algorithms, namely watershed segmentation and local maxima and minima. The conventional method was used for reference parameter derivation and tree positioning, while object-based image analysis was employed for processing the multispectral images. Additionally, a manual digitization approach was utilized to conduct an accuracy assessment of the resulting tree crown delineation. The study findings indicated that the watershed algorithm exhibited superior accuracy, achieving 83.3% total 1:1 match and 73% goodness of fit, compared to the local maxima and minima algorithm, which yielded 81.7% and 71%, respectively. These results hold significant implications for forest management planning and remote sensing-based forest quantification estimation, enabling the development of efficient and effective forest management strategies for the future.