Department of Earth Technology, Vocational School, Gadjah Mada University, Indonesia 55288, Indonesia
BibTex Citation Data :
@article{ELIPSOIDA31985, author = {Trischa Auzy and Hidayat Panuntun}, title = {ACCURACY EVALUATION OF OIL PALM TREE COUNT USING OBIA AT TENERA SUMBER REJEKI FARMERS GROUP PLANTATION, TERANGKEH, KOTABARU, SOUTH KALIMANTAN}, journal = {Elipsoida : Jurnal Geodesi dan Geomatika}, volume = {9}, number = {1}, year = {2026}, keywords = {}, abstract = { Indonesia holds the largest oil palm plantation area in the world, making accurate tree count data essential for plantation management. Conventional field survey methods are limited in time and cost efficiency, making them impractical for large-scale areas. This final project aims to automatically count oil palm trees using the Object Based Image Analysis (OBIA) method, evaluate detection accuracy, and produce a tree distribution map at the Tenera Sumber Rejeki Farmer Group Plantation, Kotabaru Regency, South Kalimantan. Secondary data were obtained from PT Eshan Agro Sentosa, comprising aerial photo processing results and field survey records. Data processing was conducted using eCognition Developer and QGIS through segmentation and classification stages. Segmentation using the Multiresolution Segmentation algorithm yielded optimal parameters: Scale Parameter (200), Shape (0.3), and Compactness (0.7). Classification was performed using the Nearest Neighbor method with Cluster Random Sampling across five object classes. The OBIA method detected 1,479 oil palm trees within a 10.51-hectare study area, compared to 1,521 trees in the field survey. Accuracy assessment yielded a Detection Percentage (DP) of 93.17% and Branch Factor (BF) of 5.88%, both classified as excellent. Results were visualized in a distribution map integrating OBIA outputs with field survey data. }, issn = {2621-9883}, pages = {43--54} doi = {10.14710/elipsoida.2026.31985}, url = {https://ejournal2.undip.ac.id/index.php/elipsoida/article/view/31985} }
Refworks Citation Data :
Indonesia holds the largest oil palm plantation area in the world, making accurate tree count data essential for plantation management. Conventional field survey methods are limited in time and cost efficiency, making them impractical for large-scale areas. This final project aims to automatically count oil palm trees using the Object Based Image Analysis (OBIA) method, evaluate detection accuracy, and produce a tree distribution map at the Tenera Sumber Rejeki Farmer Group Plantation, Kotabaru Regency, South Kalimantan. Secondary data were obtained from PT Eshan Agro Sentosa, comprising aerial photo processing results and field survey records. Data processing was conducted using eCognition Developer and QGIS through segmentation and classification stages. Segmentation using the Multiresolution Segmentation algorithm yielded optimal parameters: Scale Parameter (200), Shape (0.3), and Compactness (0.7). Classification was performed using the Nearest Neighbor method with Cluster Random Sampling across five object classes. The OBIA method detected 1,479 oil palm trees within a 10.51-hectare study area, compared to 1,521 trees in the field survey. Accuracy assessment yielded a Detection Percentage (DP) of 93.17% and Branch Factor (BF) of 5.88%, both classified as excellent. Results were visualized in a distribution map integrating OBIA outputs with field survey data.
Article Metrics:
Last update:
Starting from 2021, the author(s) whose article is published in the Elipsoida : Jurnal Geodesi dan Geomatika attain the copyright for their article and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. By submitting the manuscript to Elipsoida : Jurnal Geodesi dan Geomatika, the author(s) agree with this policy. No special document approval is required.
The author(s) guarantee that:
The author(s) retain all rights to the published work, such as (but not limited to) the following rights:
Suppose the article was prepared jointly by more than one author. Each author submitting the manuscript warrants that all co-authors have given their permission to agree to copyright and license notices (agreements) on their behalf and notify co-authors of the terms of this policy. Elipsoida : Jurnal Geodesi dan Geomatika will not be held responsible for anything arising because of the writer's internal dispute. Elipsoida : Jurnal Geodesi dan Geomatika will only communicate with correspondence authors.
Authors should also understand that their articles (and any additional files, including data sets and analysis/computation data) will become publicly available once published. The license of published articles (and additional data) will be governed by a Creative Commons Attribution-ShareAlike 4.0 International License. Elipsoida : Jurnal Geodesi dan Geomatika allows users to copy, distribute, display and perform work under license. Users need to attribute the author(s) and Elipsoida : Jurnal Geodesi dan Geomatika to distribute works in journals and other publication media. Unless otherwise stated, the author(s) is a public entity as soon as the article is published.
Editorial Office of Elipsoida : Jurnal Geodesi dan Geomatika View statisticsThe Old Dean Building (2nd Floor) Faculty of Engineering, Diponegoro UniversityJl Prof Soedarto SH, Tembalang. Semarang, Indonesia, 50275Email : redaksi.elipsoida@ft.undip.ac.id, Telephone : 081802403435