Classroom desk detection method based on machine learning

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 ...

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

Images