The detection and recognition of human actions from real-time CCTV video data streams is a popular challenge, with the potential to aid in video surveillance and anomaly detection of, for example, potentially hazardous scenarios in factories. This project aims to efficiently and effectively address this challenge by developing a generalised framework for interpreting human actions, employing cutting-edge deep learning technologies. The expected outcome is a high-performance, real-time human action recognition and detection system.
The underpinning challenges of the project are:
• Efficient and effective representation of streamed body pose data which can be used generically for understanding and analysing the actions of the body. • Efficient and robust ways to combine path signatures with cutting-edge deep learning models to produce state-of-the-art results in action classification. • Incorporating path signatures into deep learning models is expected to extract rich prior knowledge and further boost system performance.
The overall proposed framework will be extended for visual surveillance application, which will be capable to overcome the shortcoming of depending on the human resource to stay monitoring, observing the normal and suspect event all the time without any absent mind and to facilitate the control of huge surveillance system network.
Students having background in image processing/computer vision with expertise in any of the programming languages (Matlab, Python, C, C++, C#) are welcome. The domain of this project can be adjusted as per the qualification and interests of students.