Human Activity Recognition with Videos Using Deep Learning
Ayush Jain, Kaveen Gandhi, Dhruv Kumar Ginoria, Periyasami Karthikeyan · 2021
Human activity recognition is a fascinating problem that can be addressed in ample ways. This review is centered around acknowledging actual human exercises dependent on the understanding of sensor information which likewise incorporates one-dimensional time-series information. Different methods have been implemented during the past years. Various ways are offered to recognize various types of activities, such as whether the individual is running, walking, dancing, jogging, or falling, to list a few. For each technique, multiple methodologies and datasets are employed, with data obtained in various ways such as sensors, accelerometers, gyroscopes, pictures, and so on. The desired outcomes by each approach and dataset type are then compared. To categorize, machine learning techniques such as K-nearest neighbors (KNN), support vector machines (SVM), decision trees, hidden Markov models, and other Deep Learning architectures are used.