https://orcid.org/0000-0002-3430-0541
![Sample our Geography journals, sign in here to start your FREE access for 14 days]({"type":"image" , "src" : "/sda/5937/TOC-Subject-Sample-2021-Geography.jpg"})
ABSTRACT
Stone Pine (Pinus pinea L.) is currently the pine species with the highest commercial value with edible seeds. In this respect, this study introduces a new methodology for extracting Stone Pine trees from Digital Surface Models (DSMs) generated through an Unmanned Aerial Vehicle (UAV) mission. We developed a novel enhanced probability map of local maxima that facilitates the computation of the orientation symmetry by means of new probabilistic local minima information. Four test sites are used to evaluate our automated framework within one of the most important Stone Pine forest areas in Antalya, Turkey. A Hand-held Mobile Laser Scanner (HMLS) was utilized to collect the reference point cloud dataset. Our findings confirm that the proposed methodology, which uses a single DSM as an input, secures overall pixel-based and object-based F1-scores of 88.3% and 97.7%, respectively. The overall median Euclidean distance revealed between the automatically extracted stem locations and the manually extracted ones is computed to be 36 cm (less than 4 pixels), demonstrating the effectiveness and robustness of the proposed methodology. Finally, the comparison with the state-of-the-art reveals that the outcomes of the proposed methodology outperform the results of six previous studies in this context.
Acknowledgments
The authors would like to thank Geomatics Group Ltd. Company and ATAY Muhendislik for their help during this project. The source codes of the approaches Popescu and Wynne (2004) and Kwak et al. (2007) are from the Digital Forestry Toolbox and developed by Matthew Parkan. The authors would like to thank Dr. Michele Dalponte, and Dr. Tyson L. Swetnam for their help and graciously sharing the codes of their approaches. The authors are also grateful to four anonymous reviewers and the associate editor for their constructive comments.
Data availability statement
The data that support the findings of this study are available from the corresponding author upon reasonable request.
Disclosure statement
No potential competing interest was reported by the authors.
Additional information
Funding
Notes on contributors
Asli Ozdarici-Ok
Asli Ozdarici-Ok received her PhD degree from Middle East Technical University, Ankara, Turkey, in 2012. She is now an associate professor at the Academy of Land Registry, Ankara HBV University. Her research interests are in object detection, image classification for remote sensing, and applications of land and mass evaluation.
Ali Ozgun Ok
Ali Ozgun Ok received his PhD degree from Middle East Technical University, Ankara, Turkey, in 2011. He joined the Department of Geomatics Engineering at Hacettepe University in 2018, where he has been a full professor in the same department since 2021. His research interests are in the areas of photogrammetric processing and information extraction from airborne and spaceborne images, image processing, and computer vision with applications to remote sensing.
Mustafa Zeybek
Mustafa Zeybek received his PhD in 2017. Currently, he is the head of the Department of Architecture and Urban Planning at the Güneysınır Vocational School of Selcuk University and is a faculty member. His main research areas are UAV, mobile LiDAR, terrestrial laser scanning, deformation measurements and analysis, point cloud processing, forest measurements, and road surface distress analysis.
Ayhan Atesoglu
Ayhan Atesoglu received his PhD degree at the University of Bartin, Turkey. Now, he is a professor at the Department of Forest Engineering, Bartin University. His research interests are in remote sensing and geographic information systems integrated applications, and land use/cover classification and change detection.