Related Experiment Video
Updated: Jul 2, 2025
06:37
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
Published on: December 15, 2023
3.8K
Deep Reinforcement Learning in Human Activity Recognition: A Survey and Outlook
IEEE Transactions on Neural Networks and Learning Systems
|February 19, 2024
Summary
This survey explores deep reinforcement learning (DRL) for human activity recognition (HAR). It categorizes DRL-based HAR methods and highlights future research challenges in this evolving computer vision field.
Area of Science:
- Computer Vision
- Artificial Intelligence
Background:
- Human Activity Recognition (HAR) is crucial for intelligent systems like surveillance and human-computer interaction.
- Deep Reinforcement Learning (DRL) is emerging as a powerful technique for HAR tasks.
- DRL-based HAR is a novel and challenging research area with significant potential.
Purpose of the Study:
- To provide a comprehensive survey of existing DRL-based HAR methods.
- To classify these methods based on their objectives and DRL framework integration.
- To identify key challenges and future research directions in DRL for HAR.
Main Methods:
- Systematic review and classification of DRL-based HAR literature.
- Analysis of how different HAR objectives are addressed using DRL.
- Identification of common themes and approaches in DRL for HAR.
Main Results:
- Categorization of DRL-based HAR methods by objective and DRL application.
- Overview of the current landscape of DRL in activity recognition.
- Identification of research gaps and opportunities.
Conclusions:
- DRL offers promising avenues for advancing HAR capabilities.
- Further research is needed to address current challenges in DRL-based HAR.
- This survey serves as a foundational resource for future work in this domain.
