ANALYSIS OF MACHINE LEARNING ALGORITHMS PERFORMANCES FOR ROAD SEGMENTATION ON VERY HIGH-RESOLUTION SATELLITE IMAGERY AS SUPPORT OF ROAD INFRASTRUCTURE ASSESSMENT-Reference-Cited by-同舟云学术

ANALYSIS OF MACHINE LEARNING ALGORITHMS PERFORMANCES FOR ROAD SEGMENTATION ON VERY HIGH-RESOLUTION SATELLITE IMAGERY AS SUPPORT OF ROAD INFRASTRUCTURE ASSESSMENT

Published:2023-10-01 Issue: Volume: Page:
ISSN:1314-2704
Container-title:SGEM International Multidisciplinary Scientific GeoConference� EXPO Proceedings
language:
Short-container-title:

Author:

Brkic Ivan¹,Miler Mario¹,Sevrovic Marko²,Medak Damir¹

Affiliation:

1. University of Zagreb, Faculty of Geodesy

2. University of Zagreb, Faculty of Transport and Traffic Sciences

Abstract

Road traffic fatalities are a significant concern worldwide, as highlighted by data from the World Health Organization (WHO) and other international organizations. One approach to enhancing road safety is through the assessment of specific characteristics or features that contribute to the overall safety condition of roads. The International Road Safety Assessment Program (iRAP) identifies several attributes that have a direct impact on road safety. Some of these attributes can be collected from satellite imagery. One of first steps in using satellite imagery as source for road attributes collection is road extraction. Quality road extraction can provide a quality base for detection of road attributes. In this paper Random forests, Extreme Gradient Boosting and U-net algorithms were analyzed to get insight into which one is most suitable for road extraction. Analysis was performed on very high-resolution satellite imagery with four spectral bands and spatial resolution of 0.3m. Analysis has shown that U-net outperformed Random forests and XGBoost in each of evaluation measures and it is suggested as best option for road extraction as support of road infrastructure assessment process.

Publisher

STEF92 Technology

Reference10 articles.

1. [1] Passmore, J.; Yon, Y.; Mikkelsen, B. Progress in Reducing Road-Traffic Injuries in the WHO European Region. Lancet Public Health 2019, 4, e272�e273, doi:10.1016/S2468-2667(19)30074-X.

2. [2] Kavzoglu, T. Object-Oriented Random Forest for High Resolution Land Cover Mapping Using Quickbird-2 Imagery. Handbook of Neural Computation 2017, 607�619, doi:10.1016/B978-0-12-811318-9.00033-8.

3. [3] Gao, H.; Guo, J.; Guo, P.; Chen, X. Classification of Very-High-Spatial-Resolution Aerial Images Based on Multiscale Features with Limited Semantic Information. Remote Sensing 2021, Vol. 13, Page 364 2021, 13, 364, doi:10.3390/RS13030364.

4. [4] Abderrahim, N.Y.Q.; Abderrahim, S.; Rida, A. Road Segmentation Using U-Net Architecture. Proceedings - 2020 IEEE International Conference of Moroccan Geomatics, MORGEO 2020 2020, doi:10.1109/MORGEO49228.2020.9121887.

5. [5] Brkic, I.; Sevrovic, M.; Medak, D.; Miler, M. Utilizing High Resolution Satellite Imagery for Automated Road Infrastructure Safety Assessments. Sensors (Basel) 2023, 23, 4405, doi:10.3390/S23094405/S1.