Method and system for determining feature points based on multiple image acquisition devices

Abstract

The invention provides a method and a system for determining feature points based on multiple image acquisition devices. The method comprises the following steps: generating a dynamic image file of each image acquisition device according to acquired dynamic images; determining a respective neural network for each dynamic image file according to a preset configuration file, and performing data processing by using the respective neural network of each dynamic image file to obtain a thermal image set associated with each image acquisition device; performing data fusion on the plurality of thermal image sets to obtain the thermal image set subjected to data fusion of each image acquisition device, and further obtaining three-dimensional information including a host object; and performing image recognition on each dynamic image file to determine object information of a guest object involved in the three-dimensional information, determining a feature point repair type based on the object information of the guest object, and performing feature point repair on the three-dimensional information according to the feature point repair type to determine a plurality of feature points associated with the host object.

Description

technical field [0001] The present invention relates to the technical field of image recognition, and more particularly relates to a method and system for determining feature points based on multiple image acquisition devices, a computer-readable storage medium and electronic devices. Background technique [0002] At present, posture assessment technology in the field of computer vision has been widely used in fields such as sports events, clinical surgery simulation teaching, brain function development, and rehabilitation training. However, due to the symmetry of the human body's own structure and the complexity of the open scene, the existing pose assessment methods will produce key points or features in the case of local vision, special body positions, human-human interaction, and human-object interaction. The problem of point recognition failure. [0003] Taking rehabilitation training as an example, rehabilitation training will carry out active or passive exercises of ...

AI Technical Summary

Problems solved by technology

During use, due to the occlusion of some parts of the body by the auxiliary device, the recognition of key points or feature points will also fail.

[0006] At present, there is a lack of effective solutions to the problem of failure to identify key points or feature points in the prior art

Images