Search method for human motion based on data drive and decision tree analysis

Abstract

The invention opens a retrieval method of human motion data based on data-driven and the decision tree analysis. This method extracts a method of three-dimensional space-time characteristics based on the transformation rule of three-dimensional space, from various key points of the human body among data of movement capture, and introduces a key space-time concept based on the continuity of movement in time and space. Because the three-dimensional space-time characteristics to avoid dealing directly with data of high-dimensional primitive movement of human body, thereby reducing dimension of the characteristic level, avoiding a dimension disaster, to achieve lower cost, and aiming on that characteristics of the key points in time and space relative to maintain an independent identity, through the study method of data-driven decision tree to analyse the different effects On learning key points of similar campaigns, making retrieval process complete the matching calculation from an important key points to the minor key points in turn, thereby excluding a large number of unnecessary similarity computing of minor key points, and ultimately achieve an efficient campaign retrieval system.

Description

technical field [0001] The invention relates to the field of multimedia human body three-dimensional animation, in particular to a human body movement retrieval method based on data drive and decision tree analysis. Background technique [0002] In recent years, due to the advancement of equipment technology, a large amount of 3D human motion capture data has been generated, which has been widely used in computer animation, games, medical simulation and other fields. In order to make more effective use of the motion data contained in the large-scale 3D motion library, it is necessary to study an efficient motion data retrieval technology to support the processing of motion editing, deformation and synthesis. When processing and retrieving 3D motion data, the challenges of the problem are: [0003] 1. Motion is a harmonious combination of the signals of each joint point. A reasonable motion feature description mechanism is required in the retrieval process. Therefore, what k...

AI Technical Summary

Problems solved by technology

[0003] 1. Motion is a harmonious combination of the signals of each joint point. A reasonable motion feature description mechanism is required in the retrieval process. Therefore, what kind of motion features to extract and what kind of expression to express the motion features will have an effect on motion processing. and efficiency can have a huge impact on

[0004] 2. The feature dimensions extracted from motion data are usually very high, and the distance between each data will become almost the same due to the central limit law, which cannot be distinguished from each other, resulting in a high-dimensional disaster (Curse of Dimensionality) problem

[0005] 3. It is very difficult to measure the similarity between motion timing signals

Images