Human body key point recognition method and device and electronic equipment

Abstract

The embodiment of the invention provides a human body key point recognition method and device and electronic equipment, and relates to the field of image processing. The method comprises the steps ofobtaining a target image of a to-be-recognized human body key point; inputting the target image into a pre-trained neural network model to obtain a heat map and a displacement map of each human body key point in the target image; determining coordinates of each human body key point in the target image based on the heat map and the displacement map of each human body key point in the target image according to a predetermined recognition rule; and based on the coordinate of each human body key point in the target image, determining the coordinate of each human body key point in the image. By means of the scheme, the purpose of guaranteeing the recognition accuracy of human body key point recognition under the condition of low model complexity can be achieved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a human body key point recognition method, device and electronic equipment. Background technique [0002] Human key point recognition is the basis for action recognition, abnormal behavior detection, security, etc. It is mainly used to locate key parts of the human body from a given image, such as the head, neck, shoulders, hands and other parts. [0003] In the prior art, when identifying the key points of the human body, the target image of the key points of the human body to be identified is obtained, and a single heat map of each key point of the human body in the target image is generated through the pre-trained neural network model, and then , based on a single heat map of each key point of the human body, determine the coordinates of each key point of the human body. Wherein, the heat map of any key point of the human body is a probability distribution ma...

AI Technical Summary

Problems solved by technology

[0005] The recognition accuracy and model complexity of the key points of the human body cannot be guaranteed at the same time, which is specifically reflected in: if the recognition accuracy of the key points is high, then the size of the heat map needs to be Larger, which leads to a higher complexity of the neural network model used

Images