Herlinawati, herlinawati and Purwiyanti, Sri and Muthia, Tiya and Mahmud, Haedar Aziz (2022) Obstacle Detection Using Raspberry Pi for Driving Safety Based on Hough Transform Method. In: ULICOSS 2021, 30 AGUSTUS 2021, Bandar Lampung.
|
Text
Ulicoste 2021 Herlinawati.pdf Download (2MB) | Preview |
Abstract
The rapid development of digital image processing technology can be used to simplify human life. This technology can be used in automotive technology which is also growing rapidly. Automotive technology leading to driverless automation cars is in dire need of image processing technology. This research aims to detect obstacle objects based on the detection of line changes emitted by line lasers. The line laser beam is captured using a camera and then using a Raspberry Pi to determine whether there is an obstacle or not. This research uses the Python programming language with the Hough Transform method. The Hough Transform method is used to detect lines in an image that is processed by looking at the consistency of the line laser. This research uses a box and a ball as obstacle objects. Research data collection was carried out in the afternoon in a closed room with an Illumination intensity of 10 Lux with parameters such as distance, camera angle, and line laser angle. An object can be said to be an obstacle if an image there is a laser line that is broken or not at the same pixel position. However, if in the image there is a consistent line or there is no line position change, then in the image there is no obstacle object. Based on the evaluation results of the calculation of the accuracy of the obstacle distance between the actual distance and the distance calculated by the program, the accuracy is above 90%.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Divisions: | Fakultas Teknik (FT) > Prodi Teknik Elektro |
| Depositing User: | Dr. Eng FX ARINTO SETYAWAN |
| Date Deposited: | 11 Nov 2022 01:07 |
| Last Modified: | 11 Nov 2022 01:07 |
| URI: | http://repository.lppm.unila.ac.id/id/eprint/46485 |
Actions (login required)
 |
View Item |