Content and task-based view selection from multiple video streams Fahad Daniyal · Murtaza Taj · Andrea Cavallaro Received: date / Accepted: date Abstract We present a content-aware multi-camera selection technique that uses object- and frame-level features. First objects are detected using a color-based change detector. Next trajectory information for each object is generated using multi-frame graph matching. Finally, multiple features including size and location are used to generate an object score. At frame-level, we consider total activity, event score, number of objects and cumulative object score. These features are used to generate score information using a multivariate Gaussian distribution. The algorithm. The best view is selected using a Dynamic Bayesian Network (DBN), which utilizes camera network information. DBN employs previous view information to select the current view thus increasing resilience to frequent switching. The performance of the proposed approach is demonstrated on three multi-camera setups with semi-overlapping fields of view: a basketball game, an indoor airport surveillance scenario and a synthetic outdoor pedestrian dataset. We compare the proposed view selection ap- proach with a maximum score based camera selection criterion and demonstrate a significant decrease in camera flickering. The performance of the proposed approach is also validated through subjective testing. Keywords Content scoring · information ranking · feature analysis · camera selection · content analysis · autonomous video production 1 Introduction Multi-camera settings are becoming increasingly common in scenarios ranging from sports to surveillance and smart meeting rooms. An important task is the quantification of view quality to help select a single camera or a subset of cameras for optimal observability. The F. Daniyal Multimedia and Vision Group - Queen Mary University of London, United Kingdom, E1 4NS, UK Tel.: +44-20-7882-5259 E-mail: fahad.daniyal@elec.qmul.ac.uk M. Taj E-mail: murtaza.taj@elec.qmul.ac.uk A. Cavallaro E-mail: andrea.cavallaro@elec.qmul.ac.uk MULTIMEDIA TOOLS AND APPLICATIONS, ARTICLE ID 5872291, SEPTEMBER 2009