ACASVA is a joint research venture bringing together interdisciplinary scientific and engineering expertise at the Centre for Vision, Speech and Signal Processing (CVSSP) and the Department of Psychology (DoP) at the University of Surrey, and the School of Computing Sciences (CMP) at the University of East Anglia. This project will address the challenging problem of autonomous cognition at the interface of vision and language.
Practical aim is to generalize an existing video annotation system, VAMPIRE (Visual Active Memory Processes and Interactive REtrieval). Images below, represent the key features that are pre computed in the VAMPIRE project. This data will be used to proceed with the Project Goals.
Ball Tracker Demo
ACASVA Annotation Tool Demo
Tennis Court with Player Positions Ball Trajectory with Player Contours