Effective automatic intelligent video analysis of large-scale data from public spaces is an important tool in the fight against crime and for safeguarding public safety. Automatic video analytics capable of rapid processing (faster than real-time) of very large surveillance data is critically required in a global market including China and the UK. Whilst there are video analytics systems in the market, the challenge for domain-transferable video abnormal event detection with people and vehicle re-identification (search) in multi-source open data is still unsolved.
A bilateral funding scheme from Innovate UK and Jiangsu Science and Technology Department is supporting Vision Semantics Ltd, Queen Mary University of London, Sanleng Smart City & IOT System Co. Ltd and University of Science and Technology to jointly develop innovative and scalable systems for abnormal event detection with joint person and vehicle search in unconstrained public spaces.