A human posture regression method and system based on point cloud semantic enhancement

Abstract

A method and system for human posture regression based on semantic enhancement of point cloud is provided in that embodiment of the present invention. The method comprises steps extracting the point cloud features of the hand point cloud data, and classifying them point by point, obtaining semantic segmentation information of hand point cloud data, Hand-point cloud data being semantically enhancebased on semantic segmentation information, based on the hand point cloud data after semantic enhancement, and geometrically transforming the hand posture prediction result, so that that regression result of the hand posture are obtained. The method of geometric transformation of input data and output data by network learning makes the method of human pose estimation more robust to the geometric transformation of input data. The semantic information of input point cloud classification sub-network and attitude regression sub-network are fused effectively, and the performance of human pose estimation is further improved.

Description

technical field [0001] The present invention relates to the field of computer technology, more specifically, to a method and system for hand gesture regression based on point cloud semantic enhancement. Background technique [0002] In vision-based human-computer interaction, hand pose estimation refers to accurately predicting the three-dimensional coordinate position of the skeleton nodes of the human hand, which has broad application prospects in the fields of virtual reality, augmented reality, and human-computer interaction. The problem of hand pose estimation has been a hot research point in the field of computer vision in the past ten years. [0003] Vision-based hand pose estimation methods can be divided into two categories: one is the appearance-based method; the machine learning is used to establish a mapping from the two-dimensional image feature space to the three-dimensional hand pose space to estimate the state of the hand, and the advantages of the appearance...

AI Technical Summary

Problems solved by technology

However, 3D voxels need to quantify the continuous coordinate information, which introduces quantization errors, which is not good for accurate hand pose estimation.

At the same time, the 3D CNN method takes up a lot of memory, especially when the 3D voxel resolution is high; the trained network is not robust to the input geometric transformation, and the accuracy is limited. In addition, most of the existing methods Based on heat map prediction or direct regression, the performance of attitude regression is low

Images