Fall recognition method, device and equipment based on multiple features of human body and storage medium

• Main Authors: MAO MENGLIN, CHEN WEIJIE, ZHANG YUXING, CHEN YANRONG, SHEN WENZENG
• Format: Patent
• Language: Chinese; English
• Published: 22.07.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; PHYSICS

The invention relates to a fall identification method and device based on multiple features of a human body, equipment and a storage medium. The method comprises the following steps: acquiring a to-be-recognized video, and inputting the to-be-recognized video into a preset video recognition model; wherein the to-be-recognized video comprises a target person; acquiring position data of skeleton key points of the target person based on the video recognition model; and judging whether the target task is in a falling state or not based on the position data of the skeleton key points. According to the embodiment of the invention, the difference value between the skeleton key points between the different frame images in the to-be-recognized video is determined through the preset model, whether the target person is in the falling state or not is determined, two different states of lying down and falling down can be effectively distinguished, and the recognition accuracy is improved. 本申请涉及一种基于人体多特征的摔倒识别方法、装置、设备及存储介质。