Unlock instant, AI-driven research and patent intelligence for your innovation.

Human eye detection method

A human eye detection and human eye technology, applied in the field of computer vision, can solve problems such as inability to judge and reduce the accuracy of detection results, and achieve the effect of improving accuracy

Active Publication Date: 2018-12-07
STATE GRID ZHEJIANG ELECTRIC POWER
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This human eye detection method is easily affected by illumination, head posture, eye occlusion, etc., and thus cannot accurately determine whether it is a human eye based on the detection results, which reduces the accuracy of the detection results

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Human eye detection method
  • Human eye detection method
  • Human eye detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] In order to make the structure and advantages of the present invention clearer, the structure of the present invention will be further described below in conjunction with the accompanying drawings.

[0026] The present invention provides a human eye detection method, such as figure 1 As shown, including the following steps:

[0027] Step 1: Obtain several pairs of sample human eye images from the video image, send each pair of sample human eye images to the convolutional neural network for training, and obtain the sample depth feature value corresponding to each pair of sample human eye images. The obtained depth feature values ​​of all samples are constructed into a Gaussian mixture model;

[0028] Step 2: Detect the target human eye in the video image. If only the first target human eye can be detected in the video image, two sliding windows are opened at the position of the first target human eye;

[0029] Step 3: Make the two sliding windows at the current position move h...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a human eye detection method, and belongs to the field of computer vision. The method comprises that a sliding window is formed in an image in which only the first target eye can be detected, the sliding window is used to infer an inference image including the second target eye, the image of the first target eye and the inference image are sent to a convolutional neural network and then to a Gassian mixing model for matching, whether the reference image is the image of the second target eye is determined according to a matching result, if the matching result shows NO, the sliding window refers another reference image of the second target eye, the other reference image is sent to the convolutional neural network and then to the Gaussian mixing model for matching, andinference is not ended until the matching results shows that the inference image is the image of the second target eye. Thus, the accuracy of a detection result can be improved.

Description

Technical field [0001] The invention belongs to the field of computer vision, and particularly relates to a human eye detection method. Background technique [0002] With the development of the field of artificial intelligence, human eye detection has important applications in all aspects. Through the human eye detection technology, the human eye can be captured, and the human eye can be estimated to achieve a series of application purposes. Such as video surveillance, sentiment analysis, driver fatigue monitoring, etc. Therefore, the application of human eye detection has important significance. [0003] Due to the limitation of the prior art, the traditional human eye detection method is to detect the human eye by extracting the Haar-liKe feature of the human eye based on the face detection. The human eye detection method is susceptible to the effects of light, head posture, eye occlusion, etc., and thus cannot accurately determine whether it is a human eye based on the detect...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00
CPCG06V40/193G06V40/197
Inventor 梅峰戴波王彦波叶伟静王凌
Owner STATE GRID ZHEJIANG ELECTRIC POWER