# Show Reference: "Audio Visual Person Tracking: A Practical Approach (Communications and Signal Processing)"

Audio Visual Person Tracking: A Practical Approach (Communications and Signal Processing) (23 December 2011) by Fotios Talantzis, Aristodemos Pnevmatikakis, Anthony G. Constantinides
@book{talantzis-et-al-2011,
author = {Talantzis, Fotios and Pnevmatikakis, Aristodemos and Constantinides, Anthony G.},
day = {23},
edition = {1},
howpublished = {Hardcover},
isbn = {1848165811},
keywords = {auditory, cue-combination, math, multi-modality, person-tracking, visual},
month = dec,
posted-at = {2013-02-12 09:19:35},
priority = {2},
publisher = {Imperial College Press},
title = {Audio Visual Person Tracking: A Practical Approach (Communications and Signal Processing)},
url = {http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20\&path=ASIN/1848165811},
year = {2011}
}


Many visual person detection methods use one feature to detect people, create a histogram for the strength of that feature across the image. They then compute a likelihood for a pixel or region by assuming a Gaussian distribution of distances of pixels or histograms belonging to a face. This distribution has been validated in practise (for certain cases).

Person tracking can combine cues from single modalities (like motion and color cues), or from different modalities (like auditory and visual cues).

The Kalman filter assumes linear dynamics (state update) and Gaussian noise.

The extended Kalman filter results from local linearlization of update dynamics.

Particle filters are a numeric Monte-Carlo solution to recursive Bayesian filtering which address problems with non-Gaussian posteriors.

Kalman filters and particle filters have been used in uni- and multi-sensory person tracking.