Indoor human body behavior recognition method

Abstract

The invention discloses an indoor human body behavior recognition method. The method comprises the following steps that: human body three-dimensional skeleton information is obtained based on Kinect equipment; three-dimensional skeleton features in each video set are extracted; the three-dimensional skeleton features are trained, and the features are described, and the training of the three-dimensional skeleton features further includes the following steps that: online dictionary learning is performed on the features, and then, sparse principal component analysis is performed on the features, and finally, a multi-task large margin nearest neighbor algorithm and a linear support vector machine are utilized to classify the features, so that a training feature set can be obtained; three-dimensional skeleton features of test videos are extracted; and the multi-task large margin nearest neighbor algorithm and the linear support vector machine are utilized to classify the features, so that feature descriptions can be obtained, and optimum judgment is performed on the training feature set and the test features with a scoring mechanism. The indoor human body behavior recognition method of the invention has a bright application prospect in intelligent video surveillance, patient monitoring systems, human-computer interaction, virtual reality, smart home, intelligent security and prevention and athlete assistant training, and has high feasibility and great social economic benefits.

Description

technical field [0001] The invention relates to the technical field of machine vision, in particular to a method for indoor human behavior recognition. Background technique [0002] As a specific field of optoelectronic technology application, machine vision has developed into a bright and dynamic industry with an average annual growth rate of more than 20%. Machine vision is widely used in many industries such as microelectronics, electronic products, automobiles, medical care, printing, packaging, scientific research, and military affairs. Consistent technology involved and obvious differences in application are the common characteristics of various machine vision application systems. Then, as a research on human behavior recognition in the field of machine vision, it is bound to be vigorously used. [0003] The application of human behavior recognition mainly focuses on intelligent video surveillance, patient monitoring system, human-computer interaction, virtual realit...

AI Technical Summary

Problems solved by technology

[0012] It can be seen from the existing human behavior technology that it has the following technical defects: (1) The environmental adaptability is not strong, and it is difficult to exclude light and non-human dynamic objects, which cause interference to recognition; The adaptability is not strong, and the recognition rate is not high; (3) when the sample is large and high-dimensional, the processing speed is slow; (4) for the multi-task large-boundary nearest neighbor algorithm, it has the disadvantage of slow search, for the selected weight , the dependence is too large, the weight is too small, and the number of neighbors obtained is too small, which will reduce the classification progress and amplify the interference of noisy data

Images