Second-level sight line tracing method based on face orientation constraint
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A face orientation and gaze tracking technology, applied in the field of human-computer interaction, can solve problems such as shaking the user's head
Active Publication Date: 2017-09-22
SOUTH CHINA NORMAL UNIVERSITY
View PDF7 Cites 54 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0008] The purpose of the present invention is to propose a two-level line of sight tracking method based on face orientation
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0053] Such as figure 1 As shown, a two-level gaze tracking method based on face orientation constraints includes the following steps:
[0054] (1) Acquiring an image sequence through a non-invasive image acquisition unit;
[0055] Described step (1) comprises the following steps:
[0056] (1.1) Collect images used by users in real time through the camera and convert them into 256-level grayscale images.
[0057] (1.2) The color space reduction strategy is adopted, the color space is reduced to one thousandth of the original, and the calculation redundancy is reduced.
[0058] (1.3) Use a bilateral filter to preserve and denoise the image.
[0060] The human face and eye image acquisition unit is a camera installed near the monitoring screen observed by the user, which is used to photograph the user's face area and obtain images of the user's binocular area. At the same time, the user does not need to wear any ...
Embodiment 2
[0098] What differs from embodiment 1 is that described step (6) comprises following sub-steps:
[0099] (6.1) Based on the method of machine learning, in the face area, detect the eye area falling in the constrained field of view;
[0100] (6.2) Obtain the iris position through the gray scale integral function, then segment the pupil edge in the human eye area based on the Snake model, and locate the pupil center;
[0101] (6.3) Based on the relative position between the pupil center and the eye corner, construct the pupil center-inner corner eye movement vector (Δx, Δy);
[0102] (6.4) Implemented by a classification method: divide the constrained field of view into small intervals and encode them. The system loads the pre-trained artificial neural network, inputs the user's current eye movement information and head posture, and then outputs the current user's gaze hot spot.
[0103] If the method of classification is adopted, further, the constrained field of view is even...
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
Login to view more
Abstract
The invention discloses a second-level sight line tracing method based on face orientation constraint. The method comprises the following steps that: obtaining an image sequence; detecting face area and eye area image information; solving a face orientation, taking the face orientation as a ray direction, and defining the ray direction as a standard watching direction; intersecting the ray of the standard watching direction with an equipment screen to obtain a point of intersection, and taking the point of intersection as a standard watching point; taking a screen area delimited by taking the standard watching point as a center as a constraint field of view; and analyzing the eye area image information to obtain the watching area of the user on the constraint field of view. By use of the method, according to the physiologic habits of human eye for observing objects, head shaking is taken as effective sight line tracing information, and a head gesture is preferably considered. By use of the method, a calibration step is omitted, head movement compensation is not required, and true no-constraint sight line tracing can be realized.
Description
technical field [0001] The invention belongs to the technical field of human-computer interaction, and in particular relates to a two-level gaze tracking method based on face orientation constraints. Background technique [0002] Eye movement interaction is an emerging human-computer interaction method in recent years. It uses auxiliary input devices such as eye trackers to use the user's eye movements such as gaze, saccade, and blink as the input of the interactive system, effectively replacing the mouse and keyboard. Eye movement interaction is the most direct and natural way of interaction between humans and machines. Gaze tracking technology is the key and core function to realize human-computer eye movement interaction. The current mainstream implementation methods can be divided into two categories according to whether the user wears a specific optoelectronic device: invasive methods and non-invasive methods. Intrusive methods mainly rely on special optical, electric...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more