Child condition analysis methods and devices, vehicles, electronic devices, and storage media

摘要

The embodiments of the present application disclose child condition analysis methods and devices, vehicles, electronic devices, and storage media, wherein the method comprises performing facial feature extraction on at least one frame of an image in an acquired video stream. Based on facial features, we classify whether the person in the image is a child and at least one of the states of the person, and the first classification result of whether the person in the image is a child and at least one of the people. A step of obtaining a second classification result of a type of state, a step of outputting a first classification result and a second classification result, and / or a step of outputting presentation information based on the first classification result and the second classification result. And, including.