Shape Matching and Object Recognition Using Shape Contexts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Accurate road following and reconstruction by computer vision
IEEE Transactions on Intelligent Transportation Systems
Reliable method for driving events recognition
IEEE Transactions on Intelligent Transportation Systems
Hi-index | 0.00 |
This paper describes a novel driving pattern recognition and status monitoring system based on the orientation information. Two fixed cameras are used to capture the driver's image and the front-road image. The driver's sight line and the driving lane path are found from these 2 captured images and are mapped into a global coordinate. Two correlation coefficients among the driver's sight line, the driving lane path and the car heading direction are calculated in the global coordinate to monitor the driving status such as a safe driving status, a risky driving status and a dangerous driving status. The correlation coefficients between the lane path and car heading direction in a fixed period are analyzed and recognized as one of 4 driving patterns by HMM. Four driving patterns including the driving in a straight lane, the driving in a curve lane, the driving of changing lanes, and the driving of making a turn are able to be recognized so far.