A Real-Time Implementation of Face and Eye Tracking on OMAP Processor
The real-time implementation of embedded image processing applications needs a fast processor. Eye recognition is an important part of image processing systems such as driver fatigue detection system and eye gaze detection system. In these systems, a fast
- PDF / 197,542 Bytes
- 8 Pages / 439.37 x 666.142 pts Page_size
- 67 Downloads / 151 Views
Abstract The real-time implementation of embedded image processing applications needs a fast processor. Eye recognition is an important part of image processing systems such as driver fatigue detection system and eye gaze detection system. In these systems, a fast and accurate real-time implementation of face and eye tracking is required. Hence, a new approach to determine and track face and eye on live images is proposed in this paper. This proposed method is implemented and successfully tested in laboratory for various real-time images with and without glasses captured through Logitech USB Camera of 1600 × 1200 pixels @ 30 fps. The method is developed on 1 GHz open multimedia applications platform (OMAP) processor and the algorithm is developed using OpenCV libraries. The success rate of the proposed algorithm shows that the hardware has sufficient speed and accuracy, which can be used in real time. Keywords DM3730
Eye Face Logitech OpenCV
1 Introduction Wierwille et al. [1] proposed monitoring changes in physiological characteristics like ECG, EEG, skin temperature, and head movement to estimate driver fatigue. The drawback of this approach is that it causes distraction, nonrealistic, and disturbance to the driver. Artaud et al. [2] and Mabbott et al. [2] proposed a method of sensing driver response by placing sensors on steering wheel and back of the seat. The drawback of this approach is that it fails if driver wears gloves and performance of sensors placed on back seat reduces with time. Boyraz et al. [3] proposed a V. Biradar (&) Vignan Institute of Technology and Science, Hyderabad, Deshmukhi, India e-mail: [email protected] D. Elizabath Rani Gitam Institute of Technology, GITAM University, Visakhapatnam, India © Springer Science+Business Media Singapore 2016 H.S. Saini et al. (eds.), Innovations in Computer Science and Engineering, Advances in Intelligent Systems and Computing 413, DOI 10.1007/978-981-10-0419-3_29
241
242
V. Biradar and D. Elizabath Rani
method of sensing vehicle response to measure uncertainty in steering wheel. The drawback of this approach is that it is limited to vehicle type and driver condition. Mabbottt et al. [2] proposed a method where driver response is monitored requesting the driver to send feedback continuously. The drawback of this approach is that driver gets tiresome and feels annoying. All the above-discussed approaches are intrusive system of driver fatigue detection system. Few limitations of intrusive methods are as follows: system is complex, cannot be placed easily, causes disturbance, poor performance, non-reliable, and produces noise. The solution is nonintrusive system. The basic approach in nonintrusive system is analysis of face. The first symptom of fatigue appears in eye and than in mouth. Lot of research has been done to analyze the facial features to estimate driver fatigue based on eye blink rate and yawning. Parmar [4] proposed driver drowsiness detection system based on eye blink rate, the success rate is 80 %. The drawbacks of the system a
Data Loading...
