Multi-scale Gaussian-Markov random field model-based lower limb motion identification method

Abstract

The invention discloses a multi-scale Gaussian-Markov random field model-based lower limb motion identification method. The method comprises the steps of 1, collecting original data of C motion modesof human lower limbs, performing preprocessing on the original data, and constructing a data feature graph; 2, performing multi-scale decomposition and feature field modeling of a signal; 3, setting an iterative frequency Q, and iteratively updating a first-layer scale image observation field Gaussian model parameter {mu c, sigma c, pi c}; and 4, performing matching on a classification result anda standard set of each motion mode to judge mode attribution, and according to a voting rule, eliminating the problem of boundary fuzziness of a time sequence segmentation region of different motion modes. According to the method, a stable signal local feature can be extracted, and the signal noise influence caused by motion instability can be eliminated, so that the identification accuracy and the prediction reliability of the lower limb motion modes are improved, and the technical support is provided for stable control of an auxiliary motion system.

Description

technical field [0001] The invention relates to the field of pattern discrimination of human body motion parameter measurement signals, in particular to the prediction and recognition technology of human lower limb daily behavior motion intention. Background technique [0002] The automatic recognition of human lower limb motion mode is one of the key technologies to realize the active control and efficient human-computer interaction of intelligent prosthetics and assisting disabled exoskeleton robot systems. In complex daily behavioral sports scenes, how to keenly obtain various motion intentions of the human body, and realize the active assist control of the robot system according to the real-time motion intentions of the human body, so as to achieve the robot system to quickly and accurately adapt to the human body's response and realize natural motion mode, which becomes the difficulty to be solved by non-motion hysteresis control. The existing motion intention recognit...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the problems of poor reliability and low accuracy of the existing motion pattern recognition technology in the auxiliary motion system, the present invention proposes a lower limb motion recognition method based on a multi-scale Gauss-Markov random field model, in order to extract stable The local characteristics of the signal can overcome the influence of signal noise caused by motion instability, thereby improving the recognition accuracy and prediction reliability of the lower limb motion pattern, and providing technical support for the stable control of the auxiliary motion system

Images