A head motion tracking method and system

Abstract

The invention provides a head movement tracking method and system. The method comprises the following steps: acquiring actually measured angular velocity and acceleration information of head movement;detecting face information, and obtaining actually measured posture and position information of the head according to the face information; and fusing the actually measured angular velocity and acceleration information of the head with the actually measured attitude and position information to obtain optimized head attitude and position information. According to the method, auxiliary correction of actually-measured attitude and position information by actually-measured angular velocity and acceleration information can be realized; therefore, optimized head posture and position information areobtained; compared with the actual measurement attitude and position information of the head, the optimized attitude and position information can obtain a higher frame rate, and inherent high-frequency noise of the actual measurement attitude and position information is filtered out, so that the phenomena of scene lag, jumping and the like of head motion tracking are avoided, and the accuracy andstability of head motion tracking are improved.

Description

technical field [0001] The present invention relates to the technical field of head motion detection, in particular to a head motion tracking method and system. Background technique [0002] Face detection technology is an effective method to calculate the head pose by detecting the feature points of the face, and it is widely used in many fields such as human-computer interaction. Due to the complex calculation process and other factors, the frequency of face detection technology is relatively low. Moreover, it is difficult to improve the accuracy of face detection, and the equipment requirements are high, and the obtained head pose has high-frequency noise. Without the aid of any external equipment, the pose prediction value often deviates from the actual head pose by a large amount, causing scenes to lag and jump, making the head pose detection not accurate and stable enough. [0003] IMU (Inertial measurement unit, inertial measurement unit) usually includes an angular...

AI Technical Summary

Problems solved by technology

However, the long-term integral drift of the IMU will affect the accuracy and stability of head posture and position detection

Images