JISE


  [ 1 ] [ 2 ] [ 3 ] [ 4 ] [ 5 ] [ 6 ] [ 7 ] [ 8 ] [ 9 ] [ 10 ] [ 11 ] [ 12 ] [ 13 ] [ 14 ]


Journal of Information Science and Engineering, Vol. 39 No. 2, pp. 269-289


Cost-Effective Smartphone-Camera-Based Scheme to Distinguish Drivers from Passengers for Texting-While-Driving 


SHIH-YU HUANG AND CHIA-HUI WANG+
Department of Computer Science and Information Engineering
Ming Chuan University
Taoyuan, 333 Taiwan
E-mail: {syhuang; wangch
+}@mail.mcu.edu.tw


The method proposed in this paper utilizes the front and rear cameras of a user’s smartphone to distinguish drivers from passengers to prevent texting-while-driving. Since texting behaviors of drivers differ from those of passengers, the images captured by the front and rear cameras on a smartphone have distinguishable characteristics. These features can be cost-effectively employed to detect whether the smartphone is being used by the driver or a passenger. Our experimental results show that the accuracy of the proposed scheme is over 92% among most of the testing cases, which makes the proposed system a cost-effective tool for automotive safety via smartphone cameras.


Keywords: smartphone cameras, texting-while-driving, pattern recognition, SIFT, SURF

  Retrieve PDF document (JISE_202302_04.pdf)