Article Per Year (5 Year)
p-Index From 2021 - 2026
1.325
P-Index
This Author published in this journals
All Journal JPNM : Jurnal Pustaka Nusantara Multidisiplin Ruang Jurnal Peweka Tadulako Center of Education Journal (CEJou)
Budi Andresi
Tadulako University
Religion Humanities Civil Engineering, Building, Construction & Architecture Economics, Econometrics & Finance Education Engineering Environmental Science Languange, Linguistic, Communication & Media Social Sciences Other

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Ruang

 1 
Penerapan GeoAI Berbasis Mask R-CNN untuk Deteksi Kendaraan pada Citra Orthophoto Kawasan Perkotaan Septyana, Dita; Andresi, Budi; Agustina, Nadine Sandra
JURNAL RUANG / ISSN : 2085-6962 Vol 20 No 1 (2026): JURNAL RUANG
Publisher : Jurusan Teknik Arsitektur, Fakultas Teknik Universitas Tadulako Kampus Bumi Tadulako Tondo Jl. Sukarno-Hatta Km.9, Palu 94118 e-mail :Jurusan Arsitektur, Fakultas Teknik Universitas Tadulako Kampus Bumi Tadulako Tondo Jl. Sukarno-Hatta Km.9, Palu 941

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22487/ruang.v20i1.333

Abstract

GeoAI technology, which integrates artificial intelligence with spatial analysis, offers a novel approach to extracting urban object information from high-resolution imagery. This study applies Mask R-CNN with a ResNet-50 backbone architecture to detect vehicle objects in orthophoto imagery derived from the processing of 100 UAV photographs over an urban area in Switzerland. A total of 80 vehicle objects were annotated and partitioned into training (70%), validation (15%), and testing (15%) datasets. Model evaluation was conducted using a multi-threshold Intersection over Union (IoU) approach at values of ≥0.5, ≥0.75, and ≥0.95, and analyzed through a confusion matrix alongside Precision, Recall, F1-score, and Mean Average Precision (mAP) metrics. The results demonstrate that the model achieved Precision and Recall scores of 1.00 at IoU ≥0.5; however, performance declined at stricter thresholds, with an aggregate mAP of 0.56, indicating moderate overall performance. These findings suggest that the model is effective for macro-spatial analytical needs such as vehicle count estimation and distribution mapping, yet remains insufficiently stable for applications requiring high geometric precision. Conceptually, this study underscores the importance of multi-threshold evaluation in the application of deep learning for urban spatial analysis, while demonstrating the potential of GeoAI integration in data-driven urban planning.
Co-Authors Agustina, Nadine Sandra Andi Idham Asman Aziz Budianta Aziz Budianta Dita Septyana Dita Septyana Muh Ikhlasul Amal L Muhammad Najib Putri Lillah Putri Lillah Rasdiana Rasdiana Rezki Awalia Rifai Rifai Mardin Septyana, Dita Silvana Supriadi Takwim Tatang Firman Wildani Pingkan Wildani Pingkan Yan Radhinal