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

A line-of-sight control system and method based on hierarchical stochastic forests

A technology of random forest and control system, which is applied in the field of information sensing, can solve the complicated and cumbersome calibration process, and achieve the effects of strong portability, simple operation, and application promotion

Active Publication Date: 2019-03-22
SHANGHAI UNIV
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the calibration process of these drop points is relatively complicated and cumbersome.

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
  • A line-of-sight control system and method based on hierarchical stochastic forests
  • A line-of-sight control system and method based on hierarchical stochastic forests
  • A line-of-sight control system and method based on hierarchical stochastic forests

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] specific implementation plan

[0047] The present invention is described in detail below in conjunction with accompanying drawing:

[0048] Such as figure 1 Shown: a kind of line-of-sight control system based on hierarchical random forest, including video acquisition module, feature extraction module, feature analysis module and display module; Described video acquisition module, feature extraction module module, feature analysis module and display module block depend on this connection; where:

[0049] The video collection module is used to collect face video streams;

[0050] The feature extraction module is used to extract each frame from the collected face video stream, extract the face position in each frame picture, and further extract the eye features in the face (see appendix figure 2 );

[0051] The feature analysis module is used to analyze the eye features in the above-mentioned feature extraction module to calculate the location of the line of sight on th...

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 sight control system and method based on hierarchical random forests, a hierarchical stochastic forest-based system to compute LOS is adopted, The human face video stream is obtained by using the camera in front of the computer screen, and the human face position in each frame is detected, and the eye feature information in the human face is further extracted. Finally, theeye feature information is sent into the hierarchical stochastic forest model to calculate the falling point area of the line of sight in the computer screen. The invention only needs a network camera to calculate the real-time falling point area of the line of sight on the computer screen, and does not need calibration and calibration before use, the detection method is simple and convenient, the hardware configuration required is small, and the implementation cost is low.

Description

technical field [0001] The invention relates to the field of information sensing, in particular to a random forest-based line-of-sight control system and method. Background technique [0002] Eye-tracking technology can be applied to human-computer interaction, product evaluation, assisted driving, interactive games, military combat, psychological testing and other fields. For different applications, there are two types of eye trackers: head-mounted and non-head-mounted. Among them, the mainstream head-mounted products on the market include ASL Model H6 series eye trackers, ASL Model Eye series, etc.; the mainstream non-head-mounted products on the market mainly include Tobii series eye trackers, Smart Eye series, etc. [0003] At present, there is no practical and feasible method that can only rely on the webcam for eye tracking. At present, in addition to relying on hardware devices to achieve eye tracking, there are also methods that rely on deep learning and neural net...

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): G06F3/01G06K9/00
CPCG06F3/013G06V40/171G06V40/193G06V40/197G06V40/172
Inventor 姚宇巍王江锋尹悦丁艳红隋秀娟张新鹏
Owner SHANGHAI UNIV