F2010D034
A Rear-End Collision Warning System with Online One-Class Support Vector Machine
The paper proposes a rear-end collision warning system for drivers, where how to evaluate the risk of collision is critical. In the proposed system, the time-to-collision assuming a constant relative acceleration is employed as a subjective index of risk, which is justified from both the mechanical and psychological viewpoints. This is referred to as the TTC 2nd since Newtonian mechanics in a constant acceleration leads to a quadratic equation.
In our studies based on the originally collected data in an unconstrained drive, it is found that a driver uses the brake pedal of the vehicle before the index of risk reaches a threshold. In other words, when the index exceeds the threshold, the situation is dangerous and hence the system should produce an alert.
In fact, however, the threshold varies from driver to driver and from situation to situation. Moreover, the value slightly depends on other factors such as the velocity of the vehicle and the relative distance from the preceding one.
Hence, the system has to adapt the threshold to the driver's characteristics, that is, it detects anomaly of the TTC 2nd as well as learns the threshold from the data. One method to realize it is the one-class support vector machine, or OCSVM, that produces a small support of density function for a given probability. Since the OCSVM learns data in batch mode, we combine it with an online learning technique, so that the system continuously adapts to any driver and/or any situation.
To confirm the effectiveness of our system, we carried out some computer simulations to compare the performances of the OCSVMs with one or two explanatory variables. The results show that the system works well but the performance of any anomaly-detector strongly depends on the metric that affects the distance of data from the separating hyperplane.
This abstract is supplemented by a PDF, which can be viewed here.
Session: Active Safety Issues