Interaction area and interaction time period identification method, storage equipment and mobile terminal

Abstract

The invention discloses an interaction area and interaction time period identification method which is suitable for being executed in calculating equipment. The method comprises the following steps of receiving an input video signal, and carrying out frame disassembling processing on the input video signal so as to generate a single frame image; carrying out human shape detection on the acquired single frame image; carrying out total graph difference and recording differential data; determining whether the first N frames of image pixel difference data satisfy a human body interaction characteristic model and recording a triggered interaction area and a time breakpoint and a terminated interaction area and a time breakpoint; and recording a human body interaction area and a time period The invention also discloses storage equipment and a mobile terminal.

Description

technical field [0001] The invention belongs to the field of computer vision recognition, and in particular relates to a method for recognizing an interaction area and an interaction time period of difference pixels, and also relates to a storage device and a mobile terminal capable of realizing the above functions. Background technique [0002] With the development of science and technology and the wide application of modern video technology, image processing and pattern recognition methods based on machine vision are more and more used in the fields of pattern recognition, motion analysis, video surveillance and artificial intelligence. [0003] Most of the existing human-related algorithms are model-based detection algorithms, which need to use specific operators or models to perform matching calculations on the entire image, which greatly increases computing consumption and loses computing efficiency and real-time performance. At present, there are algorithms for generat...

AI Technical Summary

Problems solved by technology

[0003] Most of the existing human-related algorithms are model-based detection algorithms, which need to use specific operators or models to perform matching calculations on the entire image, which greatly increases computing consumption and loses computing efficiency and real-time performance.

At present, there are algorithms for generating a priori regions for human activity regions, most of which cannot take into account real-time and accuracy requirements. When determining regions, human body displacement activities (such as: walking, running, crawling, etc.) and interactive activities (displayed on the image It is an activity that changes between a dynamic state and a static state. The movement stops interacting with objects in a certain space, such as: standing up and sitting down, going out and entering the door, drinking water, etc.) There is no obvious distinction between these two human activity states, and there is no interaction type for the human body. Identification of the active area

Moreover, most of the existing algorithms only focus on the calibration in space, but do not record the time corresponding to the activity, and do not fully record the activity area of ​​​​a human body and the time of activity in this area.

Images