Human-like care is difficult to replicate. Due to the lack of a reliable vision-based fall detection AI, it is often more effective to assign a lot of manpower towards vision-based detections that have not been efficiently implemented.
Ms Inturi Anita Rani, Research Scholar in the Department of Computer Science Engineering, working with her supervisor, Dr V. M. Manikandan, has worked on a paper titled, “A Novel Vision-Based Fall Detection Scheme using Keypoints of Human-Skeleton with Long Short-term Memory Network” in the Arabian Journal for Science and Engineering published by Springer with an Impact Factor of 2.33.
Abstract of the research:
Humans are skilled at visually recognizing and classifying actions in videos, but it’s tough to automate this process. Human action detection in videos is useful in applications like automated surveillance, assisted living, human-computer interaction, content-based video retrieval, and video summarization. The ability to recognize atomic actions like “walking,” “bending,” and “falling” is critical for activity analysis when monitoring elderly people’s daily activities. Our paper presents a new promising solution for fall detection using vision-based approaches. In this approach, we analyse the human joint points which are the prime motion indicators. A set of keypoints of the subject are acquired by applying the AlphaPose pre-trained network. These keypoints are inferred to be the joint points of the subject. The acquired keypoints are processed through a framework of convolutional neural network (CNN) layers. Here, the spatial correlation of the keypoints is analysed. The long-term dependencies are then preserved with the help of long short-term memory (LSTM) architecture. Our system detects five types of falls and six types of daily living activities. We used the UP-FALL detection dataset for validating our fall detection system and achieved commendable results when compared to the state-of-the-art approaches. For comparison, we employed the OpenPose network for keypoint detection. It is inferred from the results that the AlphaPose network is more precise in keypoint detection.
About the research paper:
In this paper, the author proposes a vision-based system that is capable of detecting various types of falls accurately through video processing with the help of a machine learning approach.
Implementation of the research:
The proposed scheme can be used to monitor the activity of elderly people and if any unusual falls happen, the information can be shared with caretakers to ensure emergency services.
