Human body posture estimation method based on fusion model

Abstract

The invention discloses a human body posture estimation method based on a fusion model, being able to fully utilize the image feature information, being able to fuse the HOG feature information of the image and the form feature information, and being able to improve the accuracy for human body posture identification of a traditional image model structure. The human body posture estimation method includes the steps: 1) taking the two dimension static state image during the moving process of a human body as the input data, and acquiring the candidate posture based on the image model; and 2) utilizing a belief function D-S fusion model to fuse the feature information in the image, and calculating the position, of the highest reliability value, corresponding to each part and taking the position as the optimal position so as to acquire the optimal result of human body posture.

Description

technical field [0001] The invention belongs to the technical field of computer vision and pattern recognition, and in particular relates to a human body pose estimation method based on a fusion model. Background technique [0002] Human pose estimation is the process of automatically determining the position, direction and scale of human body parts in the image by analyzing various features in the image. It is a popular research direction in recent years. In computer vision, the computer can only process the underlying information of the image, and then infer the information it contains to get the final result. However, humans do not follow this process in the process of cognition, but rely on probability, language and personal experience. Therefore, how to cross the domain semantic gap has always been the focus of computer vision research. The research on human pose estimation has important theoretical significance and involves many aspects of computer vision. The main ...

AI Technical Summary

Problems solved by technology

In 2009, SamJohnson et al. overlapped the likelihood results of appearance models based on HOG and color features as a new appearance model, but the fusion method of image features when using multiple features is too simple to achieve efficient fusion

In 2011, Yang et al. proposed a human pose estimation method based on a tree structure and using HOG as the feature vector of the image. This method did not make full use of the information in the image, so that the detection accuracy of the arm and other parts was not high.

Images