Sound source positioning and human face detection-based human body positioning method and system

Abstract

The invention discloses a sound source positioning and human face detection-based human body positioning method and system. The method includes the following steps that: the distance between a sound source and the positioning system and an included angle beta between the connecting line of the sound source and the positioning system and the current positive direction of the positioning system are obtained; when the wide angle alpha of a color camera and the included angle beta satisfy a relational expression that beta<(alpha / 2-theta), wherein theta is a threshold value when the sound source is entirely located within the visual field of the color camera, and the holder of the positioning system keeps motionless; when the wide angle alpha of the color camera and the included angle beta satisfy a relational expression that beta>(alpha / 2-theta), the rotation angle of the holder of the positioning system is beta, so that the sound source is located at the center of the visual field of the color camera; the color camera acquires images; and whether faces exist in acquired images is analyzed, if faces exist in the acquired images, the sound source is determined as a man-made sound source, and the position information of a human body is determined according to the man-made sound source. With the method and system provided by the technical scheme of the invention adopted, the position information of a positioned person can be obtained fast and accurately, and operation is simple and convenient.

Description

technical field [0001] The invention relates to the technical field of smart home robots, in particular to a human body positioning method and system based on sound source positioning and face detection. Background technique [0002] In recent years, with the development of smart home technology and robotics, smart home robots have emerged. Among them, the detection of information such as the position of the human body in the home environment, as an important information processing technology in the field of smart home robots, has received increasing attention. [0003] At present, there are research and development attempts and applications of technologies related to human body target positioning in smart homes at home and abroad. Nevertheless, its positioning control method, programming software and technical performance still need to be further improved and verified. In a broad sense, human body positioning technology can be roughly divided into two categories: active a...

AI Technical Summary

Problems solved by technology

[0004] However, there are technical problems in the above-mentioned human body positioning methods. For example, the radio frequency positioning method requires the detected human body target to carry an electronic tag, and must ensure that the internal data of the electronic tag corresponds to the detected person one by one, which is not convenient in practical applications; passive infrared positioning The method is easily affected by non-human infrared sources, so that the error rate of detecting human bodies is high, and the price of infrared detection equipment is relatively expensive; although the positioning effect of array sound positioning technology is relatively accurate, it is easily affected by non-human sound sources, that is, it cannot Identify whether the sound source is generated by people in the home environment; based on face detection binocular vision positioning method can better identify the distance and angle information of the human body, but because the camera angle of view is small and it is impossible to know in advance where the person is located position, so it needs to be rotated to find the position of the face, that is, the blindness is greater

Images