Home > Published Issues > 2020 > Volume 8, No. 4, December 2020 >

Road and Obstacle Detection for Autonomous Electrical Vehicle Robot

I Komang Somawirata 1, Kartiko A. Widodo 1, Sentot Achmadi 1, and Fitri Utaminingrum 2
1. Department of Electrical Engineering, National Institute of Technology Malang, Indonesia
2. Computer Vision Research Group, Faculty of Computer Science, Brawijaya University, Indonesia

Abstract—This paper proposed the combination of road and obstacle detection for guiding the autonomous electrical vehicle robot. The road is detected by combining a lane and surface detection that is obtained by double threshold. The upper and lower of threshold value is obtained from the RGB data set of lane and surface of the road. The output of threshold is binary image that used for mapping lane, road and obstacle in captured image. The confident road detection is taken between left and right of the lane. Obstacle is observed in the road area that has been detected. The method has been evaluated by using Precision, Recall and Accuracy. The value of Precision, Recall and Accuracy are 93.7, 85.6 and 92.2 respectively.

Index Terms—lane mark, road, obstacle, electrical vehicle robot

Cite: I Komang Somawirata, Kartiko A. Widodo, Sentot Achmadi, and Fitri Utaminingrum, "Road and Obstacle Detection for Autonomous Electrical Vehicle Robot," Journal of Image and Graphics, Vol. 8, No. 4, pp. 126-130, September 2020. doi: 10.18178/joig.8.4.126-130

Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.