Three-dimensional human body motion tracking method based on quantum immune clone algorithm

Abstract

The invention discloses a three-dimensional human body motion tracking method based on quantum immune clone algorithm. The tracking process comprises: detecting articulation points of the human body in a two dimension picture in a unary picture sequence with human body gesture existing, using a kalman filter to predict the articulation points not detected, and simultaneously establishing a three-dimensional human body model; applying quantum immune clone algorithm in human body tracking, initializing species group, setting initial parameters of human body motion, then carrying out clone operation, performing operation of immunizing genes and immunoselection to generate a new species group; substituting the state parameters of the new species group in the three-dimensional human body model, using likelihood function to calculate the distance affinity, retaining the optimal solution, performing multiple times of substitution and calculation to obtain the ideal human body motion parameters to restore the three-dimensional human body gesture. The invention has the advantages of lower calculation cost and capable of obtaining three-dimensional human body gesture quickly, and is applicable to tracking of human body motion gesture in scene monitoring, motion analysis and health assessment.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a human body tracking method, which can be used to track human body movements in images or image sequences, and realize scene monitoring, virtual reality, game production, sports analysis and health evaluation. Background technique [0002] On the basis of image processing, in order to enable computers to understand images, people usually introduce computer vision. The camera performs visual navigation, scene monitoring, and extracts various types of objects, human and animal structure or motion characteristics, etc. However, it is very difficult to make a computer have human visual ability, because human beings live in a three-dimensional geometric space, and the visual sensor can only obtain the projection information of the three-dimensional world, that is, two-dimensional images. This process leads to a large amount of information loss. Computer vision tasks are furth...

AI Technical Summary

Problems solved by technology

The dimensionality of human body tracking is high and the fitness surface is complex, the optimization problem becomes extremely difficult, and many traditional optimization methods are incompetent

However, the evolutionary algorithm can solve these problems better, mainly because it basically does not require domain knowledge of the problem, and there is no restriction on the type of function and the shape of the search space, but the main problem that plagues the evolutionary algorithm is that the algorithm may fall into local extremes. value point, the dimensionality of human body tracking is high and the fitness surface is complex. Once it falls into a local extreme point, it cannot restore the human body posture very well.

Images