Human Behavior Analysis: A Survey on Action Recognition
Open Access
- 8 September 2021
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 11 (18) , 8324
Abstract
The visual recognition and understanding of human actions remain an active research domain of computer vision, being the scope of various research works over the last two decades. The problem is challenging due to its many interpersonal variations in appearance and motion dynamics between humans, without forgetting the environmental heterogeneity between different video images. This complexity splits the problem into two major categories: action classification, recognising the action being performed in the scene, and spatiotemporal action localisation, concerning recognising multiple localised human actions present in the scene. Previous surveys mainly focus on the evolution of this field, from handcrafted features to deep learning architectures. However, this survey presents an overview of both categories and respective evolution within each one, the guidelines that should be followed and the current benchmarks employed for performance comparison between the state-of-the-art methods.Keywords
Funding Information
- Fundação para a Ciência e a Tecnologia (UIDB/50008/2020, UI/BD/150765/2020)
- European Regional Development Fund (Centro-01-0145-FEDER-000019)
This publication has 73 references indexed in Scilit:
- Deep learningNature, 2015
- Deep learning in neural networks: An overviewNeural Networks, 2015
- Up next2014
- Large-Scale Video Classification with Convolutional Neural Networks2014
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Towards Understanding Action Recognition2013
- Action Recognition with Improved Trajectories2013
- A survey on vision-based human action recognitionImage and Vision Computing, 2010
- A survey of advances in vision-based human motion capture and analysisComputer Vision and Image Understanding, 2006
- Long Short-Term MemoryNeural Computation, 1997