A computer vision-based student tracking method and device

A computer vision and student technology, applied in the field of computer vision, can solve problems such as inaccurate target outlines, and achieve the effect of low difficulty and low time complexity

Active Publication Date: 2020-02-07
GUANGZHOU BAOLUN ELECTRONICS CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that it can only be analyzed in a static background, and the outline of the detected target is not accurate

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 computer vision-based student tracking method and device
  • A computer vision-based student tracking method and device
  • A computer vision-based student tracking method and device

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0072] S5: After the matching process is completed, the motion direction is calculated on the HMI image for all tracking target ROI areas. The specific implementation is as follows:

[0073] Sub-step (1): Calculate the motion speed in the x direction, scan the HMI image line by line according to the direction from left to right, when a non-zero point is found, record the point coordinates as startX, and the HMI value is lastV;

[0074] Sub-step (2): Continue to scan to the right until the HMI value is not equal to lastV, the coordinate of this point is k, and the value is currV, and the movement speed of the pixel at the current position is calculated as:

[0075] Vn=(k-startX) / (currV-lastV);

[0076] Update startX to k, lastV to currV, repeat substep (2);

[0077] Sub-step (3): according to the motion speed of all pixels, calculate the average speed Vx of the x direction of this ROI area;

[0078] In particular, for the speed calculation in the y direction, it is the same ...

Embodiment approach

[0088] In order to ensure the validity of the judgment of standing up and sitting down, it is necessary to verify the result of step S6. This method proposes to use a circular linked list to save the historical image as the background, and calculate the difference between the current frame and the background of the target area to determine the difference between the standing up and the standing up. To verify with the sit down action, the implementation of the circular linked list is as follows:

[0089] Sub-step (1): create a circular linked list that includes k images, initialize all pixel values ​​to 0, set a variable count of the number of statistical frames, initialize to 0, and k is an experience value, k=15 in the present embodiment;

[0090] Sub-step (2): Each time the algorithm receives a frame, the count is accumulated by 1. When the count is a multiple of a, the current image is added to the first position of the circular linked list; where a is determined according t...

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 student tracking method based on computer vision. The student tracking method includes the following steps of S1, calculating a differential image; S2, updating HMI and Mask images; S3,conducting contour tracking of the Mask in the step S2; S4,screening and matching candidate targets; S5, calculating a motion direction of each tracking target ROI in the HMI image; S6,conducting an action analysis of the targets; S7, verifying results of the analysis in the step S6;and S8,returningthe state and coordinate of the tracking target, and returning the coordinates and states of all the targets. The invention further discloses a student tracking device based on computer vision. The algorithm of the invention is low in implementation complexity, with no dependence on other computer vision processing libraries and can be easily ported to various platforms. As the time complexity of the algorithm of the invention is low, a target tracking product with a high requirement of real-time performance can be processed in embedded systems.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a computer vision-based student tracking method and device. Background technique [0002] The research of computer vision originated in the 1960s. In recent years, computer vision technology has been gradually applied to intelligent recording and broadcasting systems. Through edge detection, target detection and other pattern recognition methods to understand images, the recording and broadcasting system automatically locates the interested Goal, the assistant guide screen automatically switches. Commonly used moving target detection algorithms include frame difference method, background difference method, optical flow method and so on. The inter-frame difference method is a method to obtain the contour of a moving target by performing a difference operation on two adjacent frames in a video image sequence. The principle of this method is simple, easy to implement, and because th...

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 Patents(China)
IPC IPC(8): G06T7/215G06T7/246
CPCG06T2207/10016
Inventor 李昌绿
Owner GUANGZHOU BAOLUN ELECTRONICS CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap