Human fall detection and activity monitoring: a comparative analysis of vision-based methods for classification and detection techniques

Fall detection (FD) system tends to monitor the fall events with restricted movement patterns and provides alerts to detect actions and corresponds to human falls. Based on high-level features, the resultant information often requires well-detected results like activity monitoring, detection, and classification. The objective of the study focuses on the vision-based FD and activity monitoring (AM) methods using different types of cameras and determines the finest method for different backgrounds and complex surroundings in outdoor and indoor scenes. Several works of literature provide various detection algorithms which cannot differentiate the fall from other actions. So, there is a need for efficient detection techniques which can efficiently work on all sorts of fall event images. Also, the AM algorithm lies in different classification techniques but it is not robust to classify the actions being the same speed with the fall such as jumping, bending, etc. In this paper, we view the comparative study of vision-based FD and monitoring techniques such as Inactivity/Body shape change based, Posture based, 3D head motion-based, Spatial-temporal based, Gait based and skeleton tracking techniques based on the source of their techniques, types, description, advantages, and disadvantages. In addition, several performance metrics were used to evaluate the results and compare the resulting study with the previous comparative evaluations. This comparative analysis leads to a deeper understanding of different FD and AM techniques and suggests the possible direction for the researchers to identify a suitable method for their needs.