Fall Detection and Direction Judgment Based on Posture Estimation

Abstract

For the problem of elderly people falling easily, it is very necessary to correctly detect the occurrence of falls and provide early warning, which can greatly reduce the injury caused by falls. Most of the existing fall detection algorithms require the monitored persons to carry wearable devices, which will bring inconvenience to their lives and few algorithms pay attention to the direction of the fall. Therefore, we propose a video-based fall detection and direction judgment method based on human posture estimation for the first time. We predict the joint point coordinates of each human body through the posture estimation network, and then use the SVM classifier to detect falls. Next, we will use the three-dimensional human posture information to judge the direction of the fall. Compared to the existing methods, our method has a great improvement in sensitivity, specificity, and accuracy which reaches 95.86, 99.5, and 97.52 on the Le2i fall dataset, respectively, whereas on the UR fall dataset, they are 95.45, 100, and 97.43, respectively.

An Elderly Fall Detection System Using Enhanced Random Forest in Machine Learning

“…Using the Random Forest method, we achieved an accuracy level of 65.43% on both the training and testing sets. Every one of these outcomes demonstrates how various algorithms perform in that particular context [13].…”

Fall Direction Detection in Motion State Based on the FMCW Radar

“…Sensor Type Model Accuracy [16] Three-dimensional accelerometer SVM 94.54% [17] Three-dimensional accelerometer and gyroscope XGB-CNN 90.02% [18] Accelerometer SVM 98.3% [19] IMU sensor SVM 90.4% [24] Camera SVM 97.52%…”

“…The model achieved a detection accuracy of 98.89%. In [24], the researchers utilized a camera device to detect fall events. They employed the pose estimation method to acquire human joint information and used SVM for classification.…”

Lightweight 3D DenseNet with improved attention mechanism

“…At present, behavior recognition has become a hot spot in the field of computer vision, and human behavior recognition technology has been widely applied in the fields of public safety [1], intelligent transportation [2], medical monitoring [3], and safety production [4]. Today, with the massive growth of information, the number of sports videos is increasing rapidly.…”