This work developed two different learning methods applied to the task of driver activity monitoring. The goal of the methods is to detect periods of driver activity that are not safe, such as talking on a cellular telephone, eating, or adjusting the dashboard stereo system. The system proposed uses a side-mounted camera looking at a driver's profile and utilizes
the silhouette appearance obtained from skin-color segmentation for detecting the activities. The unsupervised method uses agglomerative clustering to succinctly represent driver activities throughout a sequence, while the supervised learning method uses a Bayesian eigenimage classifier to distinguish between activities. The results of the two learning methods applied to driving sequences on three different subjects are very promising. This work has the potential to reduce deaths on our highways.
- Project number: 2004059
- Start date: 01/2004
- Project status: Completed
- Research area: Transportation Safety and Traffic Flow