It has been claimed that development of an invehicle early warning system is important to maximize collision avoidance capability. This study aims to provide a method that can predict the true ego-vehicle motion long enough so that early warning could be feasible, using a monocular forward-view camera. Based on an observation that severalsecond future position of a vehicle is probabilistic rather than deterministic, our approach utilizes a machine learning algorithm that can probabilistically model human driving behavior from data to predict multiple possible paths, such as going straight, turning left, and turning right. Experimental results on KITTI dataset suggest that our probabilistic learning approach could suffice for 4-second early warning, while an orthodox, deterministic learning approach and a simple motion extrapolation approach do not satisfy the requirement.
Learning-Based Multiple-Path Prediction for Early Warning
01.06.2018
5903783 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
LEARNING-BASED MULTIPLE-PATH PREDICTION FOR EARLY WARNING
British Library Conference Proceedings | 2018
|Europäisches Patentamt | 2024
|Lane departure warning system based on future driving path prediction
Online Contents | 2014
|