DOI: https://doi.org/10.14710/teknik.v44i1.51908

Deteksi Kerusakan Jalan Menggunakan Pengolahan Citra Deep Learning di Kota Semarang

*Bandi Sasmito orcid scopus publons  -  Geodetic Engineering Departement - Faculty of Engineering, Diponegoro University, Semarang-Indonesia, Indonesia
Bagus Hario Setiadji  -  Departemen Teknik Sipil Fakultas Teknik, Universitas Diponegoro, Indonesia
Rizal Isnanto  -  Departemen Teknik Komputer Fakultas Teknik, Universitas Diponegoro, Indonesia
Open Access Copyright (c) 2023 TEKNIK

Citation Format:
Abstract
Jalan adalah kebutuhan krusial dalam aktivitas masyarakat. Jalan mempermudah akses transportasi dari tempat asal ke tujuan. Jalan juga penting sebagai infrastruktur transportasi darat untuk manusia dan barang. Namun, kondisi jalan yang tidak layak dapat menyebabkan kecelakaan. Pelacakan kondisi jalan sulit karena banyaknya jalan yang harus diperiksa. Penelitian ini menggunakan prinsip penginderaan jauh dengan teknologi Jaringan Syaraf Tiruan Deep Learning. YOLO (You Only Look Once) digunakan untuk deteksi kerusakan jalan. Hasil pendeteksian ditambahkan posisi atau lokasi dengan menggunakan Global Navigation Satellite System (GNSS), sehingga nantinya hasil deteksi dapat memberikan posisi atau lokasi yang akurat. Penelitian ini menghasilkan model identifikasi kerusakan jalan dengan nilai overall accuracy sebesar 88% dan nilai kappa accuracy sebesar 86% dan lokasi sebaran kerusakan yang memiliki koordinat posisi dengan akurasi RMSE sebesar ± 5,6 meter
Fulltext View|Download
Keywords: jaringan syaraf tiruan; deep learning; penginderaan jauh; identifikasi kerusakan jalan; transportasi jalan; YOLO (You Only Look Once)

Article Metrics:

Article Info
Section: Artikel
Language : ID
Recent articles
Analisis Faktor – Faktor yang Berpengaruh dalam Implementasi Konsep Green Untuk Peningkatan Kinerja Biaya menggunakan Structural Equation Modelling-Partial Least Square (SEM-PLS) Pengaruh Variasi Temperatur Solution Treatment pada Kekerasan dan Presipitat Paduan Co-30Cr-5Mo-0,32C-0,23N Studi Komparasi Dampak Lingkungan Produksi Campuran Aspal Hangat Modifikasi Polimer EVA dengan Campuran Aspal Panas Skala Laboratorium Menggunakan Life Cycle Assessment (LCA) Front Matter Back Matter More recent articles
Most cited articles
RISK ANALYSIS STUDY OF NOx, and SOx FROM TRANSPORTATION (CASE STUDY: MAIN STREETS OF D.I. JOGJAKARTA) Studi Kerentanan Air Tanah Terhadap Kontaminan Menggunakan Metode Drastic di Kota Pekalongan RISK ANALYSIS STUDY OF NOx, and SOx FROM TRANSPORTATION (CASE STUDY: MAIN STREETS OF D.I. JOGJAKARTA) KINETIKA REAKSI ESTERIFIKASI GLISEROL DAN ASAM ASETAT MENJADI TRIACETIN MENGGUNAKAN KATALIS ASAM SULFAT Analisis Desain Sistem Pembangkit Listrik Tenaga Surya Kapasitas 50 WP More cited articles
  1. Biros, D., Sharma, M. and Biros, J. (2019) ‘Vulnerability and risk mitigation in AI and machine learning’, Cutter business technology journal, 32(8)
  2. Bochkovskiy, A., Wang, C.Y. and Liao, H.Y.M. (2020) ‘YOLOv4’, CVPR Workshop on The Future of Datasets in Vision [Preprint]
  3. Charles D. Ghilani (2018) Adjustment Computations : Spatial Data Analysis. Sixth Edit. Hoboken, New Jersey: John Wiley & Sons, Inc
  4. Chen, Q. et al. (2020) ‘Road damage detection and classification using mask R-CNN with DenseNet backbone’, Computers, Materials and Continua, 65(3). Available at: https://doi.org/10.32604/cmc.2020.011191
  5. Congalton, R.G. and Green, K. (2019) ‘Analysis of Differences in the Error Matrix’, in Assessing the Accuracy of Remotely Sensed Data. Available at: https://doi.org/10.1201/9780429052729-9
  6. Fan, R. and Liu, M. (2020) ‘Road Damage Detection Based on Unsupervised Disparity Map Segmentation’, IEEE Transactions on Intelligent Transportation Systems, 21(11), pp. 4906–4911. Available at: https://doi.org/10.1109/TITS.2019.2947206
  7. Kamilaris, A. and Prenafeta-Boldú, F.X. (2018) ‘A review of the use of convolutional neural networks in agriculture’, Journal of Agricultural Science. Available at: https://doi.org/10.1017/S0021859618000436
  8. Kiranyaz, S. et al. (2021) ‘1D convolutional neural networks and applications: A survey’, Mechanical Systems and Signal Processing, 151. Available at: https://doi.org/10.1016/j.ymssp.2020.107398
  9. Lillesand, T.M. and Kiefer, R.W. (2008) Remote sensing and image interpretation, Distribution
  10. Maeda, H. et al. (2018) ‘Road Damage Detection and Classification Using Deep Neural Networks with Smartphone Images’, Computer-Aided Civil and Infrastructure Engineering, 33(12). Available at: https://doi.org/10.1111/mice.12387
  11. Pan, Y. et al. (2021) ‘Monitoring Asphalt Pavement Aging and Damage Conditions from Low-Altitude UAV Imagery Based on a CNN Approach ’, Canadian Journal of Remote Sensing, 47(3), pp. 432–449. Available at: https://doi.org/10.1080/07038992.2020.1870217
  12. Pisharoty, P.R. (1983) ‘Introduction to remote sensing’, Proceedings of the Indian Academy of Sciences Section C: Engineering Sciences [Preprint]. Available at: https://doi.org/10.1007/BF02842927
  13. Redmon, J. et al. (2016) ‘You only look once: Unified, real-time object detection’, Proceedings of the
  14. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016-Decem, pp. 779–788. Available at: https://doi.org/10.1109/CVPR.2016.91
  15. Rego, A. et al. (2018) ‘An Intelligent System for Video Surveillance in IoT Environments’, IEEE Access, 6. Available at: https://doi.org/10.1109/ACCESS.2018.2842034
  16. Sharma, A. (2018) ‘Confusion Matrix in Machine Learning’, Www.Geeksforgeeks.Org [Preprint]
  17. Wegman, F. (2017) ‘The future of road safety: A worldwide perspective’, IATSS Research, 40(2), pp. 66–71. Available at: https://doi.org/10.1016/j.iatssr.2016.05.003
  18. Zhang, X. et al. (2020) ‘Exploring the Tricks for Road Damage Detection with A One-Stage Detector’, in 2020 IEEE International Conference on Big Data (Big Data). IEEE, pp. 5616–5621. Available at: https://doi.org/10.1109/BigData50022.2020.9377923
  19. Zimmermann, T. et al. (2017) ‘When road-kill hotspots do not indicate the best sites for road-kill mitigation’, Journal of Applied Ecology, 54(5). Available at: https://doi.org/10.1111/1365-2664.12870

Last update:

No citation recorded.

Last update: 2024-05-10 09:13:22

No citation recorded.