DRIVE NOW TEXT LATER, DETECTION OF CAB DRIVER ILLIGAL ACTIVITY WHILE DRIVING
Keywords:
Cascade Classifier, Object Detection, neural network, cascade object detector, mobile phone usage detection of driverAbstract
Texting-while-driving (TD) is one of the top dangerous behaviors for drivers. Many interesting systems and
mobile phone applications have been designed to help to detect or combat TD. However, for a TD detection system to be
practical, a key property is its capability to distinguish driver’s mobile phone from passengers. Existing solutions to this
problem generally rely on user’s manual input, or utilize specific localization devices to determine whether a mobile
phone is at drivers’ location. In this paper, we propose a method which is able to detect TD automatically without using
Any extra devices. The main idea of our proposed system very straight forward: when a user is composing messages, the
smartphone embedded sensors (i.e. gyroscopes, accelerometers, and GPS) collect the associated information such as
touch strokes, holding orientation and vehicle speed. This information will then be analyzed to see whether there exist
some specific TD patterns. This type of experiments have been conducted by different persons and in different driving
cases. The results show that our goal can achieve a good detection and accuracy with low Negative rate. Besides being
infrastructure free and with high accuracy, this method does not access any content of messages and therefore is
privacy-preserving.
