Street Mark Detection Using Raspberry PI for Self-Driving System

Sumardi Sumardi, Muhammad Taufiqurrahman, Munawar A Riyadi

Abstract


Self driving is an autonomous vehicle that can follow the road with less human intervention. The development of self driving utilizes various methods such as radar, lidar, GPS, camera, or combination of them. In this research, street mark detection system was designed using webcam and raspberry-pi mini computer for processing the image. The image was processed by HSV color filtering method. The processing rate of this algorithm was 137.98 ms correspondinig to 7.2 FPS. The self-driving prototype was found to be working optimally for “hue” threshold of 0-179, “saturation” threshold of 0-30, and “value” threshold of 200-255. Street mark detection has been obtained from the coordinates of street mark object which had range 4-167 on x axis and 4-139 on y axis. As a result, we have successfully built the street mark detection by COG method more effectively and smoothly in detection in comparison with Hough transform method.


Keywords


street mark detection; HSV color filtering; self-driving car;

Full Text:

PDF


DOI: http://dx.doi.org/10.12928/telkomnika.v16i2.4509

Refbacks

  • There are currently no refbacks.


Copyright (c) 2018 Universitas Ahmad Dahlan

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.


TELKOMNIKA Telecommunication, Computing, Electronics and Control
website: http://telkomnika.ee.uad.ac.id
online system: http://journal.uad.ac.id/index.php/TELKOMNIKA
Phone: +62 (274) 563515, 511830, 379418, 371120 ext: 3208
Fax    : +62 (274) 564604

View TELKOMNIKA Stats