Eye recognition and tracking method applied to personnel monitoring

Abstract

The invention relates to a method and a device for eye identification tracing for monitoring personnel. The method comprises the following: a step of capturing image; a step of image sequence; a step of searching a candidate area; a step of analyzing the candidate area; a step of tracing an eye area; and a step of judging the tracing. The device comprises an infrared light projector, a video camera and a processing unit, wherein the infrared light projector is used for providing infrared light source; the video camera is provided with a filter disc, which is connected with the processing unit and is used for capturing an infrared image for the processing unit to perform identification and tracing so as to achieve the efficacies of eye tracing and the improving the accuracy. The method and the device can be used in all weathers, avoid the influences caused by eyeglasses and sunglasses wore by a user, save hardware resources, and increase the processing speed, wherein a tracing mode process can skip over a sensing mode process when the tracing is successful, which is advantageous to process by the processing unit.

Description

technical field [0001] The invention relates to an eye recognition and tracking method applied to personnel monitoring. Background technique [0002] Use the processing unit to analyze and compare the characteristics and details of a continuous image, and then obtain the required data from the image through the preset process and analysis method, so as to be used as a part of the automatic control process, among which The processing and judgment of human facial images has become a popular and important technology due to its wide application scope; the processing and judgment of human facial images can be mainly used in driver's eye tracking and warnings to prevent fatigue driving The harm caused is of course not limited to this. The monitoring and warning of other types of personnel can also be automated with this technology. From this we can see the importance and practicability of image tracking. [0003] Prior art such as China Taiwan Patent Publication No. 436436, "Meth...

AI Technical Summary

Problems solved by technology

[0008] It can be seen from the various solutions of the above-mentioned prior art that for human faces, the eyes seem to be the most important identification target. However, the identification methods of the various solutions in the prior art are still cumbersome, and it may be necessary to capture the face Images, iris information, etc., may need to cooperate with YCbCr technology, etc., and all existing technologies have failed to provide a simple and fast eye tracking method. In this way, not only relatively expensive hardware equipment is required to cooperate with the existing technology, but also need to first It can only be used by capturing the user's own image. Relatively speaking, its convenience and applicability are not good

[0009] In addition, the way of tracking eyes in the existing technology is easily limited by the climate, ambient brightness and the wearables of the user (such as glasses, sunglasses, etc.), and it is difficult to effectively achieve the effectiveness and accuracy of tracking. Therefore, overall , its practicability is poor, there is still a need to improve

Images