Classroom desk detection method based on machine learning

A machine learning and detection method technology, applied in the field of artificial intelligence, can solve problems such as time-consuming, labor-intensive, errors, etc., to achieve the effect of fast execution, strong adaptability, and improved class quality

Active Publication Date: 2021-04-20
南京览众智能科技有限公司
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, relying on manpower is not only time-consuming and labor-intensive, but also has a greater possibility of error. If machine learning and deep learning computer vision methods can be used to solve the problem of automatically detecting the position of classroom desks in educational scenarios, a certain degree of automation and intelligent analysis can be achieved. classroom situations that would be very helpful

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
  • Classroom desk detection method based on machine learning
  • Classroom desk detection method based on machine learning
  • Classroom desk detection method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The present invention will be described in detail below with reference to the drawings and embodiments.

[0053] figure 1 The flowchart of the present embodiment includes the following steps:

[0054] Step 1: Train the deep learning target detection model for detecting desks, and detect the input image I input The bounding box of each desk in , record the set of bounding boxes of all desks as B input ; the image I input It is a classroom scene with many rows of desks, in the present embodiment, image I input For the smart classroom scene.

[0055] Step 2: Use the line detection algorithm to detect the image I input All straight lines in .

[0056] Step 3: For the detected straight line, use the clustering algorithm to calculate the main direction of the classroom. The main direction of the classroom is defined as the direction in which the desks are arranged horizontally, such as Figure 4 Shown is the obtained effect of the main direction of the classroom, and s...

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 classroom desk detection method based on machine learning. The classroom desk detection method comprises the following steps: step 1, detecting a bounding box of a desk in an image; 2, detecting all straight lines of the classroom desk; and 3, calculating the main direction of the classroom by using a straight line. 4, performing affine transformation on the bounding box in the main direction; 5, performing affine transformation on the original image by utilizing the main direction; step 6, executing a clustering algorithm on the bounding box; 7, calculating a clustering center difference value and a threshold value, and combining specific clusters; 8, taking the bounding boxes of the continuous multiple rows of desks out; 9, calculating a regional bounding box; step 10, drawing the regional bounding box on the image; and step 11, performing inverse affine transformation on the image. The classroom desk position can be automatically and intelligently positioned to a certain extent, and subsequent classroom condition analysis, such as statistics of the student seating rate, analysis of the interest degree of students in a classroom and improvement of the teaching method, is facilitated.

Description

technical field [0001] The invention belongs to the field of artificial intelligence and relates to a method for detecting classroom desks based on machine learning. Background technique [0002] With the development of machine learning, especially the development of deep learning, some problems that cannot be solved by traditional computer vision have been solved, and some aspects of traditional visual effects that are not enough have also been greatly improved. At present, most classroom data rely on manpower to calculate statistics, such as classroom occupancy rate, students skipping classes, students' interest in courses, etc. According to these classroom data, teaching quality can be improved and teachers and parents can better improve student learning. However, relying on manpower is not only time-consuming and labor-intensive, but also has a greater possibility of error. If machine learning and deep learning computer vision methods can be used to solve the problem of ...

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): G06K9/00G06K9/62G06N3/04G06N3/08
Inventor 张锐盛谦孟祥祥胡锦鑫潘飞蒋斌郭延文
Owner 南京览众智能科技有限公司
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