Tumble pre-judgment method based on human body key point behavior recognition and LSTM

Abstract

The present invention provides a tumble pre-judgment method based on human body key point behavior recognition and LSTM. According to the tumble pre-judgment method based on human body key point behavior recognition and LSTM, the human body is further divided into a head area, a trunk area and a leg area for behavior recognition, the calculation amount is greatly reduced, and therefore the detection efficiency is improved; and on the basis, the memory function of the acquired video is realized by adopting an LSTM (Long Short Term Memory), namely a long-term and short-term memory neural networkmechanism, so that the functions of analyzing and identifying the behavior change of the human body are realized, and finally, the identification results are classified into three types, namely tumble, non-tumble and others. According to the method, the calculation power consumption is reduced, and the fall detection time is saved, so that the functions of real-time detection and fall detection pre-judgment are realized.

Description

technical field [0001] The invention belongs to the field of medical care under the guidance of artificial intelligence AI, and specifically relates to a fall prediction method based on human key point behavior recognition and LSTM. Background technique [0002] At present, there are many discussions on fall detection methods based on computer vision at home and abroad. According to the different algorithms and implementation methods, they can be divided into four categories: (1) Body shape analysis: this method uses the background elimination modeling The contour is extracted from the image, and then the human body is framed as a region of interest with a rectangle, and the aspect ratio is used to determine whether a fall has occurred. This method is easily affected by illumination changes and background moving objects, has a high misjudgment rate, and cannot realize the fall prediction function. (2) Inactive state detection: This method distinguishes falls from similar ac...

AI Technical Summary

Problems solved by technology

However, using CNN to train the model requires a large amount of calculation, resulting in low algorithm efficiency, and does not realize the predictive function of falls

[0003] Combined with the current research status in the world analyzed above, it can be found that the current fall detection methods are facing the following problems: (1) The algorithm has a large amount of calculation, which leads to low operating efficiency and cannot achieve real-time detection; (2) Lack of an effective fall prediction algorithm

Images