Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Pupil detection method and device based on double cameras

A dual-camera and depth-camera technology, applied in the field of pupil detection, can solve the problems of pupil coordinate deviation, driver's line of sight occlusion, uneven light distribution, etc., and achieve the effect of improving coordinate deviation, improving accuracy, and large recognition range

Active Publication Date: 2020-10-02
宁波均联智行科技股份有限公司
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing solutions have the following defects: on the one hand, the head-mounted eye tracker will block the driver's line of sight and cannot be directly applied to the cockpit environment; on the other hand, due to the complex background environment of the cockpit, images collected by a single camera are prone to pupil One or more of coordinate offset, eyelash / eyelid occlusion, spectacle lens light reflection / glass edge occlusion, low light intensity or uneven light distribution, image blur
[0004] In summary, the pupil detection technology in the prior art is not suitable for the cockpit environment, and there is a technical problem of inaccurate pupil 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
  • Pupil detection method and device based on double cameras
  • Pupil detection method and device based on double cameras
  • Pupil detection method and device based on double cameras

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] see figure 1 with Image 6 , this embodiment provides a pupil detection method based on dual cameras, including:

[0057] Construct a dual-camera pupil detection environment, and obtain the detection frame pictures including face images captured by each camera at the same time; extract the face images in each detection frame picture generated at the same time respectively, and realize the detection of the face area Pre-positioning; based on the ElSe algorithm, the pupil edge information in the face image is identified, and the pupil edge information includes a plurality of pupil feature point coordinates; according to the pupil feature point coordinates of the two eyes in each face image, the average value is calculated and output Radius results for each pupil.

[0058] In the pupil detection method based on dual cameras provided in this embodiment, by constructing a pupil detection environment of dual cameras, each camera can capture detection frame pictures includin...

Embodiment 2

[0091] This embodiment provides a pupil detection device based on dual cameras, including:

[0092] The environment layout unit is used to construct the pupil detection environment of the dual cameras, and obtain the detection frame pictures including facial images captured by each camera at the same time;

[0093] The face positioning unit is used to extract the face images in each detection frame picture generated at the same time respectively, so as to realize the pre-positioning of the face area;

[0094] A pupil detection unit, configured to identify pupil edge information in the face image based on the ElSe algorithm, where the pupil edge information includes a plurality of pupil feature point coordinates;

[0095] The calculation output unit is used to output the radius result of each pupil after calculating the mean value according to the pupil feature point coordinates of the two eyes in each facial image.

[0096] Compared with the prior art, the beneficial effect o...

Embodiment 3

[0098] This embodiment provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is run by a processor, the above-mentioned steps of the pupil detection method based on dual cameras are executed.

[0099] Compared with the prior art, the beneficial effect of the computer-readable storage medium provided by this embodiment is the same as the beneficial effect of the dual-camera-based pupil detection method provided by the above technical solution, and details are not repeated here.

[0100] Those of ordinary skill in the art can understand that all or part of the steps in the above-mentioned inventive method can be completed by instructing related hardware through a program. The above-mentioned program can be stored in a computer-readable storage medium. When the program is executed, it includes: For each step of the method in the above embodiments, the storage medium may be: ROM / RAM, magnetic dis...

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 discloses a pupil detection method and device based on double cameras, relates to the technical field of pupil detection, and can improve the accuracy of a pupil detection result by adopting a pupil detection scheme of the double cameras. The method comprises the following steps: constructing a pupil detection environment of double cameras, and acquiring a detection frame picture which is shot by each camera at the same time and comprises a face image; respectively extracting a face image in each detection frame picture generated at the same moment to realize pre-positioning of aface region; identifying pupil edge information in the face image based on an ElSe algorithm, wherein the pupil edge information comprises a plurality of pupil feature point coordinates; and according to the pupil feature point coordinates of the two eyes in each face image, outputting a radius result of each pupil through mean value calculation. The device applies the method provided by the scheme.

Description

technical field [0001] The present invention relates to the technical field of pupil detection, in particular to a pupil detection method and device based on dual cameras. Background technique [0002] The DMS pupil detection system can detect physiological information such as the driver's stress response, fatigue, and eye light conditions, and then take corresponding actions. [0003] At present, the mainstream laboratory pupil detection technology mostly uses head-mounted eye trackers to collect eye images, collects images of each eye through a single camera, and then detects and analyzes the pupils in the images. The existing solutions have the following defects: on the one hand, the head-mounted eye tracker will block the driver's line of sight and cannot be directly applied to the cockpit environment; on the other hand, due to the complex background environment of the cockpit, images collected by a single camera are prone to pupil One or more of coordinate deviation, e...

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
IPC IPC(8): G06K9/00
CPCG06V40/161G06V40/197G06V40/193G06V20/597
Inventor 樊潇胡爽
Owner 宁波均联智行科技股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products