Active Search for Real-Time Vision

In most cases when information is to be extracted from an image, there are priors available on the state of the world and therefore on the detailed measurements which will be obtained. While such priors are commonly combined with the actual measurements via Bayes' rule to calculate posterior probability distributions on model parameters, their additional value in guiding efficient image processing has almost always been overlooked. Priors tell us where to look for information in an image, how much computational effort we can expect to expend to extract it, and of how much utility to the task in hand it is likely to be. Such considerations are of importance in all practical real-time vision systems, where the processing resources available at each frame in a sequence are strictly limited -- and it is exactly in high frame-rate real-time systems such as trackers where strong priors are most likely to be available. In this paper, we use Shannon information theory to analyse the fund...

• Type: Conference
• Year: 2005
• Where: ICCV
• Authors: Andrew J. Davison
• Keywords: Computer Vision, Efficient Guided Image, Efficient Image Processing, Gaussian Probability Distributions, ICCV 2005, Posterior Probability Distributions, Strong Priors