Abstract
Accident prevention systems have recently been a part of many modern cars to reduce injuries and casualties on the road. However, the high cost of components and equipment have limited such safety systems to higher-end and luxury vehicles. This paper proposes an economical method of using a smartphone application for real-time lane detection and rearend collision warning system for drivers on the road. The Android-based application uses image-processing algorithms coupled with the monoscopic camera on the smartphone as the main sensor to perform lane and vehicle detections. The novelty of this work lies in the use of the monocular vision of the camera to estimate the distance with the vehicle up ahead. The system is able to distinguish unintentional lane departure and if the driver is traveling too close to the vehicle ahead. An acoustic warning will notify the driver of a potential accident.
Original language | English |
---|---|
Title of host publication | Unknown Host Publication |
Publisher | IEEE |
Pages | 563-568 |
Number of pages | 698 |
ISBN (Electronic) | 978-1-4673-6564-2 |
DOIs | |
Publication status | Published (in print/issue) - 24 Sept 2015 |
Event | 2015 IEEE 39th Annual International Computers, Software & Applications Conference - Duration: 17 Apr 2015 → … |
Conference
Conference | 2015 IEEE 39th Annual International Computers, Software & Applications Conference |
---|---|
Period | 17/04/15 → … |
Keywords
- mobile application
- lane detection
- vehicle detection
- distance estimation
- real-time
Fingerprint
Dive into the research topics of 'Real-Time Lane Detection and Rear-End Collision Warning System on a Mobile Computing Platform'. Together they form a unique fingerprint.Press/Media
-
Beyond calls and games: Utilising the full potential of smartphones
19/08/14
1 item of Media coverage
Press/Media: Research
Profiles
-
Mark Ng
- School of Engineering - Senior Lecturer
- Faculty Of Computing, Eng. & Built Env. - Senior Lecturer
Person: Academic