Efficient Resource-constrained Retrospective Analysis of Long Video Sequences

Introduction: New technology is creating large stores of digital video. Real time processing of these huge data sets is extremely challenging; retrospective or forensic analysis creates even greater problems when one must rapidly examine hours or days of video from thousands of cameras. We develop a new method for controlling processing, so that available resources are directed at the most relevant portions of the video. In our approach, we initially perform some inexpensive processing of a video by applying a cheap but less accurate algorithm combined with sparse application of a more expensive and accurate algorithm. We then use a new probabilistic inference algorithm to determine to which frames we should apply further expensive processing.