A Face & Eye Detection Model for Driving an Automobile



This paper proposes an inexpensive vision-based system to exactly identify Eyes Off target (EOR). The device has three primary components: 1) robust facial feature monitoring 2) mind pose and gaze estimation and 3) 3-D geometric reasoning to recognize EOR. Within the video stream from the camera put on the controls column, our physiques tracks facial features within the driver’s face. While using the supervised landmarks plus a 3-D face model, the device computes mind pose and gaze direction. Distracted driving is probably the primary causes of vehicle collisions within the United States. States. Passively monitoring a driver’s activities comprises the building blocks from the automobile safety system that could potentially reduce the quantity of accidents by estimating the driver’s focus of attention. Your brain pose estimation formula is robust to no rigid face deformations due to modifications in expressions. Finally, employing a 3-D geometric analysis, the device reliably detects EOR. The recommended system does not need any driver-dependent calibration or manual initialization and works instantly (25 FPS), during the day and night. Our physiques accomplished above 90% EOR precision for individuals examined situations. To validate the performance in the system in the real vehicle atmosphere, we transported out a comprehensive experimental evaluation under all types illumination conditions, facial expressions, and individuals.

Full Text:


Copyright (c) 2016 Edupedia Publications Pvt Ltd

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.


All published Articles are Open Access at  https://journals.pen2print.org/index.php/ijr/ 

Paper submission: ijr@pen2print.org