Blink Frequency and Gaze Estimation Method Based on Eye Region Generative Network

Abstract

The invention discloses a blinking frequency and line-of-sight prediction method based on eye area generation network, which can be used for driver fatigue driving warning. The specific steps are as follows: Firstly, machine deep learning is used to extract the characteristic area of ​​the driver's eye captured by the camera, and the driver's eye is simulated by ellipse fitting on the feature area, and the blink frequency and The pupil position estimation method gives the blink frequency and the driver's gaze direction, which provides supporting data for the driver fatigue monitoring system and driver dynamic behavior analysis.

Description

technical field [0001] The invention belongs to the field of automobile safety and relates to a method for estimating the driver's blinking frequency and line of sight, and the method can be used for early warning of driver's fatigue driving. Background technique [0002] At present, traffic accidents caused by fatigue driving still occupy the main component. Therefore, the successful early warning of drivers under driving fatigue has become a problem that people pay more and more attention to. This has also led most researchers to propose many effective auxiliary measures for this problem. The development of image processing technology and the extraction of facial features have provided a theoretical basis for the research on driver fatigue warning methods, but they are still immature. period. For example: [0003] Since the target may appear anywhere in the image, and the size and aspect ratio of the target are also uncertain. In the process of traditional target detect...

AI Technical Summary

Problems solved by technology

In the process of traditional target detection, the sliding window strategy is used to traverse the entire image, and different scales and different lengths and widths need to be set, which makes the complexity too high, produces too many redundant windows, and takes a long time

This seriously affects subsequent feature extraction

In the deep learning target detection algorithm of Region Proposal (candidate area), the extraction of candidate areas has been greatly improved, but it is still not close to the real range of the target. The R-CNN training under development is divided into multiple stages. It is cumbersome, time-consuming to train, and takes up a lot of disk space. It takes 47s to process an image using the GPU, VGG16 model, and the processing speed is slow. However, the improved versions of SPP-NET, Fast R-CNN, and Faster R-CNN, although in terms of processing speed and The processing steps are simplified, but the extraction of candidate regions takes a lot of time and cannot meet the real-time requirements

Images