Method for controlling intelligent mobile service robot based on head posture recognition

Abstract

The invention provides a method for controlling an intelligent mobile service robot based on head posture recognition. Facial feature points are detected by utilizing a constraint local model algorithm; the current head posture is estimated by utilizing the geometrical relationship of the facial feature points; and thus, a patient can control motion of the intelligent mobile service robot by using the head. The method specifically comprises the following steps: training a head posture sample to obtain a facial feature point shape template and a local template of feature points; acquiring a head image by using Kinect and finding out the position of the face; detecting the facial feature points by using the constraint local model algorithm; estimating the current head posture by utilizing the detected feature points; and giving different control commands to the mobile service robot according to different head posture parameters. By means of the method disclosed by the invention, handicapped persons can also stably control the intelligent mobile service robot by using heads; and thus, the handicapped persons are convenient to go out.

Description

technical field [0001] The invention relates to the field of machine vision control, in particular to a control method for an intelligent mobile service robot based on head posture recognition, which is applied to an interactive system of an intelligent mobile service robot and is suitable for realizing a model based on local constraints on the interactive system of an intelligent mobile service robot (CLM) head pose real-time estimation and based on this to realize the control of the intelligent mobile service robot. Background technique [0002] With the development of society, the problem of population aging has become a common challenge faced by developed countries and some developing countries. The forecast shows that in the 20 years from 2015 to 2035, the proportion of China's elderly population will double to 20. %, many of them are old people with inconvenient activities due to diseases, and the number of disabled people with various disabilities caused by various di...

AI Technical Summary

Problems solved by technology

[0004] 1. The method of wearing a motion sensor. This method installs an accelerometer and a gyroscope sensor on the head of the test subject, and judges the head posture by receiving the sensor motion data. This method has high precision, but requires wearing a device, and the user experience is poor

[0005] 2. The LED calibration method, by wearing a headgear with a certain number of LEDs, using the camera to capture the image of the headgear, and then judging the current position according to the position of the LEDs, similarly, this method has high precision, but still needs to wear a device

[0006] 3. The machine vision method, which collects head images through the camera and judges the head posture through algorithms, is the current mainstream method, with zero contact with the test object and a better user experience. Estimating head pose (machine vision method), such as traditional template matching algorithm, mainstream random forest classifier, geometric relationship method of facial feature points, etc. The traditional CLM algorithm simply uses two-dimensional images, which has the problem of interference with different lighting conditions

Images