A Survey on Vision Based Activity Recognition, its Applications and Challenges
Ashwin Geet d'Sa, Bhanu Prasad · 2019 Second International Conference on Advanced Computational and Communication Paradigms (ICACCP) · 2019
Tracking objects is gaining momentum in the field of research due to its widespread applications. Such systems can be enhanced or made more meaningful by allowing the activities of those objects to be recognized. Activity recognition is the ability to identify and recognize the action or goals of the agent. The agent can be any object or entity that performs action, which has end goals. The agents can be a single agent performing the action or group of agents performing the actions or having some interaction. Human activity recognition has gained popularity due to its demands in many practical applications such as entertainment, healthcare, simulations and surveillance systems. Vision based activity recognition is gaining advantage as it does not require any human intervention or physical contact with humans. Moreover, there are networked set of cameras, which makes it both easier to track and recognize the activities. Through this work, approaches involved in activity recognition, advantages and challenges involved in activity recognition are discussed.