Classroom number detection method and system based on machine vision and binocular collaboration technology
A machine vision and people detection technology, applied in the field of image processing, to achieve the effect of high accuracy and robustness, and broad application prospects
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0061] Such as figure 1 As shown, the classroom population detection method based on machine vision and binocular coordination technology of the present invention is mainly composed of an image and video acquisition module, an image preprocessing module, a left and right classroom human detection module, a binocular coordination module, and a number output module.
[0062] figure 2 for figure 1 Shown is a block diagram of the specific composition of each part of the method for detecting the number of people in a classroom based on machine vision and binocular collaborative technology, which includes the following steps:
[0063] S1 installs a camera on the left and right sides of the back of the classroom to collect videos from different perspectives on the left and right sides of the classroom;
[0064] S2 selects the video data on the left and right sides of the classroom, and performs grayscale processing on the image frames in the video data on the left and right sides ...
Embodiment 2
[0102] This embodiment is based on machine vision and binocular collaboration technology classroom population detection system, including: image video acquisition module, image preprocessing module, left and right classroom human body detection module, binocular coordination module, number output module;
[0103] The image and video acquisition module is used to obtain video image data of different viewing angles on the left and right sides of the classroom;
[0104]The image preprocessing module is used to grayscale the image frames in the video image data to compress the amount of original data; use the 3*3 Gaussian filter mask template to convolve with the grayscale image and perform smoothing filtering to achieve Suppress the noise and weaken the background information, enhance the effect of the figure outline; perform two super-resolution reconstructions on the filtered image, in which the original image size is 1280*720, and perform 2*2 and 4*4 super-resolution reconstruc...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More