Moving body posture estimating method

Abstract

The invention discloses a moving body posture estimating method which can accurately position body framework points and effectively obtain the features with more expressive power in a three-dimensional moving body and is more effective and simpler in structure. The method includes the steps of firstly, preprocessing depth image data through a median filter method, and conducting part calibrating on body pixels through a Dijkstra algorithm based on geodesic distance; secondly, determining that the number of clusters of each type is three on the basis of a regional feature point extracting algorithm of a K-mean value clustering algorithm, and extracting 32 posture features to express different body postures; thirdly, obtaining position calibrating information of the framework points through PoserPro2012 software in the training stage, synthesizing 300 frames to simulate posture features of a human body, calibrating standard framework points, and calculating a linear regression model of the posture features and the framework points through the posture feature points and the standard framework points of a training sample so that the mapping relation between the posture features and the standard framework points can be obtained.

Description

technical field [0001] The invention belongs to the technical field of computer vision and pattern recognition, and in particular relates to a method for gesture estimation of a moving human body. Background technique [0002] Human pose estimation is an important research direction in the field of computer vision. In the past ten years, the problem of automatically recognizing human poses in image and video sequences has been a research hotspot in the field of computer vision. The main reason for human body pose estimation to become the focus of research is the rapid development of electronic equipment and the huge application market generated by it. Effective processing and understanding of human activities in data will have a profound impact on the development of human society. The purpose of sports human behavior analysis is to describe, recognize and understand human actions, human-human and human-environment interactions, which can be used in intelligent video survei...

AI Technical Summary

Problems solved by technology

Two-dimensional human body posture refers to a description of the distribution of human body joints on the two-dimensional plane of the image. The human body posture estimation of traditional two-dimensional images is greatly affected by surrounding environmental factors (clothes color, light) and occlusion. At the same time, there is a lack of pixel Spatial location information

Human body pose estimation based on deep convolutional neural network has obvious defects: it is only for RGB images, no depth data is used, and the network structure used by this method is very complicated (such as figure 2 ), the training efficiency is low

One is a method based on geodesic distance and optical flow represented by the method proposed by Loren Arthur Schwarz et al. The defect of this type of algorithm is that it is for the secondary skeleton points (elbow, knee, neck, shoulder, crotch) The positioning method is based on the proportional positioning method, so the effect is not ideal for people of different body types. At the same time, the application of optical flow requires a large amount of calculation and it is difficult to meet the occasions with high real-time requirements.

Images