Training method for vehicle detection
Authors:
Open Access
- 26 November 2016
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 105-109
Abstract
Recently, vehicle detection methods have been popularly used in the field of intelligent vehicles. The performance and processing time of vehicle detection is very important because it is associated with the life of a driver. However, all vehicle detection methods generate missing detections and false detections because of different vehicle appearances. However, in a general road environment, the appearance of most of these vehicles has a front and a rear. In this paper, we propose a training method to detect the front and rear of the vehicle. Our vehicle detection integrates state-of-the-art feature-based detection.Keywords
Funding Information
- Ministry of Science, ICT and Future Planning (2016DG0002)
This publication has 4 references indexed in Scilit:
- Are we ready for autonomous driving? The KITTI vision benchmark suite2012
- Model based vehicle detection and tracking for autonomous urban drivingAutonomous Robots, 2009
- Integral Channel Features2009
- On-road vehicle detection: a reviewIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006