Motion normalization detection method and device based on time consistency contrast learning

Abstract

The invention relates to the field of intelligent video monitoring and deep learning, in particular to an action normalization detection method and device based on time consistency comparative learning, and the method comprises the steps: firstly constructing a data set for videos which are acquired through a camera and are marked by a first number and are not marked by a second number, and the first number is smaller than the second number; secondly, performing strong and weak data enhancement on an unlabeled video, extracting features, inputting the features into a time consistency behavior alignment network, outputting a feature map and a similar action starting and ending frame set between different samples, mapping sub-feature maps corresponding to the sets on the feature map, and constructing similar and different types of sub-feature map samples; sending to a comparative learning network to extract space-time discriminant features; the first number of labeled videos are sent to a pre-trained network for transfer learning, and behavior categories are output; and finally, the behavior normalization is judged according to the inter-frame behavior category change, and if the behavior normalization is not standard, early warning is given out.

Description

technical field [0001] The invention relates to the field of intelligent video monitoring and deep learning, in particular to a method and device for detecting action norms based on time consistency comparison learning. Background technique [0002] Medical staff have always been at the front line of the fight against the epidemic, protecting the lives of the broad masses of people. Protective equipment is an important protective barrier for medical staff, which can reduce the high infection rate caused by exposure. Medical staff put on and take off protective clothing in a standardized manner is an important measure to prevent infection. If the protective clothing is not put on and taken off according to the regulations, there is a high risk of infection. Therefore, standardizing the donning and doffing process can effectively avoid the problem of isolation of the entire team due to the infection of individual personnel, thereby reducing non-combat attrition. [0003] Not ...

AI Technical Summary

Problems solved by technology

However, when this assumption is applied to the uncut video classification task, there is a big problem. When the video clip spans two or more actions, it will make it difficult for the algorithm to learn distinguishing features, which will affect the recognition in downstream tasks. precision

Images