Abstract
Human activity recognition is an active research topic in computer vision due to its applicability to wide range of application areas such as smart surveillance, robot learning, human computer interaction, health assessment. Identifying human activities from video sequences constitutes one of the most challenging tasks in the field of computer vision, especially due to the harsh nature of the real-world activity recognition scenarios and high volumes of data that need to be worked upon. The techniques available in the literature for activity recognition are broadly classified into two categories: single layered approaches aimed at recognition of much simpler activities, hierarchical approaches aimed at recognition of complex activities in terms of simpler ones. Deep learning is one of the hierarchical approaches for recognizing human activities capable of achieving outstanding results and outperforming other non-deep state-of-the-art methods by effectively utilizing the image structure in reducing the search space of the learning model. This paper aims at capturing a snapshot of current trends in activity recognition with deep learning models. We have also examined the merits, demerits, efficiency of pioneering deep learning models being used for activity recognition.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.