A multi-student sit-up detection method based on optical flow and k-means clustering

Abstract

The invention discloses a student sitting detection method based on optical flow and k-means clustering, which collects the image information of the student area; detects the moving target area of ​​the student area, and detects the moving area in the image by using the inter-frame difference method , use the connected domain marking algorithm to mark the moving target area template; superimpose the moving target area template with the original image, and perform optical flow calculation on the moving target area to obtain the motion vector of the feature points; divide the optical flow into an upward group A and a group of B downwards are clustered; if the same central point appears continuously for a certain number of times, it is considered that the target has a sitting action, so far, the detection is over. Compared with the prior art, the present invention can detect students' sitting-ups with only one camera, and the equipment is simple and easy to install; it can be applied to various environments; the present invention has high detection accuracy and good real-time performance, and can reach class Requirements; it can detect multiple students standing up at the same time, which is more practical.

Description

technical field [0001] The invention relates to the technical field of information-based teaching, in particular to a method for detecting students sitting up in an intelligent teaching recording and broadcasting system. Background technique [0002] The related background technology of the present invention mainly contains: [0003] 1. By installing a sensor device or an infrared projection sensing device to detect students' sitting ups. This approach typically requires retrofitting student seating or installing a large number of sensors on classroom walls, which is expensive and difficult to maintain. [0004] 2. The method of judging students' sitting-ups by image processing on the pictures taken by cameras is generally to use multiple cameras (usually at least two cameras) to analyze and judge simultaneously. [0005] For example, according to the records of Chinese patent 201110032341.3 "A Method for Detecting Students Standing Up in a Teaching Intelligent Recording a...

AI Technical Summary

Problems solved by technology

Although this can finally achieve the purpose of detection, but the cost is high, the installation and wiring are complicated, and the camera needs to be installed on one side of the classroom, which is close to the height of the students standing up, which is not beautiful and is easily damaged by students

And these methods are mostly aimed at the situation of a student standing up, when there are many students sitting up, it will not be able to judge well

Images