A ttention d etection of the d river to ensure safe driving
semanticscholar(2018)
摘要
AbstractIn this paper, we have tried to detect the focus of attention of the driver from his/her head movement and orientation of pupil detection. If the driver changes his/her gaze, the corresponding coordinate of pupil also changes. The frontal view of the person is divided into three regions corresponding to three target objects and the gaze directions are detected based on in which region the coordinate of pupil is located in the eye area. In our technique we have used a camera to capture video frames of the target person. The frames are converted into grey image and processed pixel by pixel. A 3D head tracker is used to extract the facial regions from the image. From the facial regions face points and eye regions are detected. Using a Vector Field of Image Gradient (VFIG), the pupil of eye is detected. In our approach, we have used the face points to create a rectangle outside of the eyes to detect the gaze of driver by applying different techniques under different lighting conditions and different distances from the camera. For non-frontal face, sometimes situation arises when we cannot detect the pupils efficiently. In this case, we have used the head orientation for gaze detection. The head rectangle has been divided into three regions. We estimate the gaze based on which region the middle of the head falls with varying head rotation time. To ensure a safe driving we need to detect sustained as well as transient attention very carefully and efficiently. To detect the body movement, we have used the optical flow feature and verified this approach in controlled environment. Our result in controlled and real time experiments reveal that, we can efficiently track the focus of attention of the driver from the coordinate of the pupil of the eye combining with head position and consequently we can detect the sustained attention together with transients very effectively and control the attention by deploying an alarming system if inattention is detected. GSJ: VOLUME 6, ISSUE 6, June 2018 30 GSJ© 2018 www.globalscientificjournal.com
更多查看译文
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要