Lane detection system for autonomous vehicle using image processing techniques
A completely autonomous vehicle is one in which a computer performs all the tasks that the human driver normally would. This would mean, to go to a specific destination, a driver will just has to key in the desired destination and the system will be enabled automatically by the computer. From...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2005
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/7968/1/24p%20SHAHIZUL%20EZA%20MOHD%20KIBLEE.pdf http://eprints.uthm.edu.my/7968/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | A completely autonomous vehicle is one in which a computer performs all the tasks that
the human driver normally would. This would mean, to go to a specific destination, a
driver will just has to key in the desired destination and the system will be enabled
automatically by the computer. From there, the car would take over and drive to
destination with no human input. The car would be able to sense its environment and
change maneuver and speed when necessary. A system for road marking detection has
been set up during the course of this master's thesis project. In the development of the
software, images acquired from a front looking video camera mounted inside the vehicle
were used.
The problem of using computer vision to develop lane detection system for autonomous
vehicle is road marking characteristic. Since the strongest characteristic of a road
marking image are the edges, the road marking detection step is based on edge detection.
For the detection of the straight edge lines, a Radon based method was chosen. Due to
peak spreading in Radon space, the difficulty of detecting the correct peak in Radon
space was encountered. A Radon peak detection algorithm was developed based on two
values, Rand O. These values make the system robust to the different types of road
marking such as continuous road marking, discontinuous road marking and road with
shadow.
The performance of the road marking detection algorithm was investigated over several
different short image sequences. The different sequences included normal countly road
driving, a number of different road marking configurations, such as continuous,
intermittent and combinations of and images with shadows. The system performs well
during the experiments within the difference road condition state above. The work done
in this thesis can be used as a starting point in the development of for example a lane
departure warning system. The potential of such a system is further increased by merging
information retrieved from images with information from the vehicle such as vehicle
speed, steering angle and acceleration. |
|---|