Background subtraction: methods based on eigen features

Performance map

BenchmarkEigen

Eigenbackground / SL-PCA of Oliver et al (2000) paper link

{youtube}4c1lLY3ta08{/youtube}

We describe a real-time computer vision and machine learning system for modeling and recognizing human behaviors in a visual surveillance task [1]. The system is particularly concerned with detecting when interactions between people occur and classifying the type of interaction. Examples of interesting interaction behaviors include following another person, altering one’s path to meet another, and so forth. Our system combines top-down with bottom-up information in a closed feedback loop, with both components employing a statistical Bayesian approach [2]. We propose and compare two different state-based learning architectures, namely, HMMs and CHMMs for modeling behaviors and interactions. The CHMM model is shown to work much more efficiently and accurately. Finally, to deal with the problem of limited training data, a synthetic ™Alife-style∫ training system is used to develop flexible prior models for recognizing human interactions. We demonstrate the ability to use these a priori models to accurately classify real human behaviors and interactions with no additional tuning or training

{gallery}DPEigenbackgroundBGS{/gallery}

These algorithms are contained in the bgslibrary by Andrews Sobral, that includes over 30 background subtraction algorithms, a common C++ framework for comparing them, and an handy C++/MFC or Java app to see them running on video files or live feed from a webcam.

Return to the list of background subtraction algorithms

Leave a Reply

Your email address will not be published.