Survey on data fusion approaches for fall-detection

Abstract

Human fall detection is a research area that aims to develop methods and systems that can automatically detect and recognize falls, especially among elderly people or people with disabilities. Falls are a major cause of injuries and deaths among these populations, and timely intervention can reduce the severity of the consequences. Therefore, human fall detection is an important application of computer vision, machine learning, and deep learning techniques. This article offers an extensive review of fall detection systems, emphasizing the utilization of state-of-the-art technologies like deep learning, sensor fusion, and machine learning. The research delves into the diverse methodologies and strategies utilized in fall detection systems, including the incorporation of wearable sensors, smartphones, and cameras. Through the examination of various fall detection techniques and their trial outcomes, the article underscores the efficacy of these systems in identifying and categorizing falls. The study also addresses the obstacles and limitations associated with fall detection systems, underscoring the necessity for further advancements in upcoming research. In essence, the research contributes to the progression of advanced fall detection systems, demonstrating their potential to enhance the quality of life for the elderly, alleviate healthcare challenges, and offer dependable solutions for fall detection and classification.