Model-based robust and pecise tracking embedded in smart cameras-the PFAAM-CAM

Top down tracking approaches like particle filtering are known for their robustness since they can handle multimodal probability density functions. Active appearance models (AAMs), on the other hand, allow for precise, model-based tracking but suffer from limited robustness. The particle filter AAM...

Full description

Saved in:
Bibliographic Details
Published in2008 Second ACM/IEEE International Conference on Distributed Smart Cameras pp. 1 - 8
Main Authors Hoffmann, M.R., Swart, A., Hunter, K.M., Herbst, B.M., Flecky, S., Strasser, W.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2008
Subjects
active appearance models
Cameras
Fitting
Mathematical model
Noise
Particle filters
Probability density function
Shape
smart cameras
tracking
Online AccessGet full text

Cover

More Information
Summary:Top down tracking approaches like particle filtering are known for their robustness since they can handle multimodal probability density functions. Active appearance models (AAMs), on the other hand, allow for precise, model-based tracking but suffer from limited robustness. The particle filter AAM combination (PFAAM), exploits the best of both worlds. In this paper the PFAAM is embedded on a smart camera. We present the necessary changes to achieve faster performance for the limited resources available in this embedded environment. The proposed implementation of the PFAAM on the smart camera-the PFAAM cam-offers various benefits compared to a more traditional, centralised approach. All the processing is performed on the camera that allows it to run on the raw and thus artefact free video data. Also, only the resulting parameters of the AAM are transmitted; no video feed has thus to leave the camera that significantly reduces the necessary bandwidth.
ISBN:9781424426645
1424426642
DOI:10.1109/ICDSC.2008.4635676