Child behavior track positioning method and system

Abstract

The invention discloses a child behavior track positioning method and system, and the method comprises the steps: constructing a model library, and carrying out the feature extraction of an image in the model library, and obtaining a first feature library; performing face detection and human body detection on the collected video to generate a face detection frame and a human body detection frame; performing first matching on the human face detection frame and the first feature library, performing feature extraction on the human face detection frame based on a first matching result to obtain a second feature library, performing human face tracking matching on the to-be-recognized object successfully matched for the first time, and performing second matching based on the second feature library based on a human face tracking matching result; recording a coordinate position of successful first matching or successful face tracking matching or successful second matching in the image sequence so as to generate a track; through comprehensive face and human body information recognition, the problems of face shielding and back-to-back camera of the body are solved, and the behavior track of the child in the classroom is accurately tracked.

Description

technical field [0001] The present invention relates to the technical field of educational information intelligence, and more particularly, to a method and system for locating children's behavior tracks. Background technique [0002] The preschool education institutions for children aged 1-6 mainly focus on nurseries and kindergartens. On the one hand, the forms of children’s classes at this stage are varied and relatively unstable, and the children’s range of activities in the classroom will be relatively large, because there will be more occlusions On the other hand, the current general face recognition algorithm is mainly for adults, resulting in a low recognition rate for children. The accurate tracking and positioning of the activity distribution of each child in the classroom can facilitate the teacher to analyze the children's stay time in different areas of the classroom, so as to infer the child's point of interest, and assist the teacher to accurately and objective...

AI Technical Summary

Problems solved by technology

The existing analysis technology for fixed classes mainly relies on face recognition technology, the recognition accuracy cannot meet the requirements, and the children in the class scene are fixed, and accurate tracking and positioning of each child is a long-term identification process

Existing application scenarios with large personnel changes, such as shopping malls, are not suitable for the application of children's tracking and positioning in classrooms

Images