Real-time multi-target human body 2D attitude detection system and method

Abstract

The invention relates to a real-time multi-target human body 2D attitude detection system and method. The system comprises an image acquisition module used for acquiring image data, a real-time processing module used for inputting the image data to the neural network for learning and prediction and generating the human body attitude information according to a hot spot map of the acquired joint point position and a hot spot map of the direction vector field among joint points, and a visual display module used for presenting the predicted human body attitude information to users in a line connection mode. The system is advantaged in that the depth learning method is utilized to encode the joint position and the position and the direction of bones formed by joints through interconnection, accurate human body 2D attitude estimation of a single image is realized, for complex people gathering conditions, multiple human body attitudes of the scene can be accurately estimated, the users are facilitated to carry out further analysis processing and mining of the human body attitudes, and next behaviors are predicted.

Description

technical field [0001] The invention relates to the fields of computer vision and deep learning, in particular to a real-time detection system and detection method for multi-target human body 2D postures. Background technique [0002] With the development of computer vision technology and deep learning technology, human pose estimation is still an increasingly active research field of computer vision, and has broad application prospects, such as human-computer interaction, intelligent monitoring, athlete auxiliary training, video coding, etc. In recent years, driven by these applications, behavior analysis has become a research hotspot in computer vision, robotics, deep learning, machine learning, data mining and other related fields. The purpose of human behavior analysis is to describe, identify and understand human actions, interactions between people and between people and the environment. It has a wide range of application backgrounds in intelligent video surveillance, ...

AI Technical Summary

Problems solved by technology

The detection accuracy of existing methods in multi-target scenes is not ideal: First, each picture may contain an unknown number of people, and the location and range of these people are unknown

Secondly, the interaction between people may cause spatial interference. Since people are in contact with each other and joints overlap each other, the method of detecting the human body first may miss detection and be blocked in this case. , with incomplete information about the human body, resulting in imprecise estimates

Third, the time complexity will increase as the number of people in the picture increases, which is a huge challenge for the real-time performance of the system

Images