On the impurity of street-scene video footage
Craig Henderson, Saverio G. Blasi, Faranak Sobhani with Richard Beckley (Metropolitan Police, TBC)
AbstractThe Metropolitan Police in London have found that the opportunity to use computer vision technology in the analysis of real-world street-scene video is severely limited because of the practical constraints in the variety and poor quality of videos available to them. Consequently, in a large criminal investigation, police forces employ numerous officers and volunteers to watch many hours of camera footage to locate, identify and trace the movements of suspects, victims, witnesses, luggage and other inanimate objects. Their goal is to piece together a story of events leading up to an incident, and to determine what happened afterwards. In this tutorial and associated paper, we present the technical challenges facing researchers in developing computer vision technique to process from the wild street-scene videos. Video footage captured by surveillance CCTV cameras and hand-held devices such as mobile phones and body-mounted cameras worn by police officers pose particular difficulties. Video formats are varied and often non-Standards compliant which leads to apparent corruption when rendered using standard players. Footage is low-quality either in resolution or in sharpness caused by free movement of the camera, fast panning and zooming or weather conditions. We describe our experiences working with the Metropolitan Police in London to find a solution to these problems and enable computer vision techniques to be used in the forensic analysis of videos in criminal investigations.
Craig Henderson received a B.Sc. degree in Computing for Real Time Systems from the University of the West of England in Bristol, UK in 1995. From 1995 to 2014 he worked in a variety of organisations as a Software Engineer and Engineering Manager.
Since 2014, he is a PhD student in the Multimedia and Computer Vision and Laboratory at the School of Electronic Engineering and Computer Science, Queen Mary, University of London,
London, UK. His research interests include computer vision, machine learning and scalable systems.
Saverio G. Blasi obtained a PhD in Electronic Engineering from Queen Mary University of London in 2014. His PhD research mainly focused on developing novel prediction algorithms to increase the performance of video compression schemes under a variety of different conditions. He mainly worked with the Advanced Video Coding (AVC), VP8, and HEVC standards. Saverio's research spanned several areas of interest to picture coding, such as low complexity motion estimation algorithms, highly efficient inter and intra-prediction schemes, and novel methods for transform coding. During the course of his PhD, Saverio produced several top conference and journal papers, and one patent.
Faranak Sobhani is a first year PhD Research Student working on knowledge representation and semantic web. Her research interests centre around high-level data focusing on semantic web, knowledge management, knowledge representation, information retrieval, reasoning and inference in forensic domain. Her research is directed towards an infrastructure for handling both uncertainty and vagueness in the Rules and Logic of the semantic web, experimenting with fuzzy Ontology, inference in Ontology and integration with fuzzy Ontologies to represent knowledge in the forensic domain in which the concept to be represented has imperious definition.