Abstract Many activities may be characterized by a sequence of key frames that are related to important changes in motion rather than dominant characteristics that persist over a long sequence of frames. To detect such changes, we define a transformation operator at every time instant, which relates the past to the future states. One of the useful quantities associated with numerical range of an operator is the eigenvalue. In the literature, eigenvalue-based approaches have been studied extensively for many modeling tasks. These rely on gross properties of the data and are not suitable to detect subtle changes. We propose an antieigenvalue – based measure to detect key frames. Antieigenvalues depend critically on the turning of the operator, whereas eigenvalues represent the amount of dilation along the eigenvector directions aligned with the direction of maximum variance. We demonstrate its application to activity modeling and recognition using two datasets: a motion capture dataset and the UCF human action dataset.
Key Frame-Based Activity Representation Using Antieigenvalues
Computer Vision – ACCV 2006 ; 6 ; 499-508
Lecture Notes in Computer Science ; 3852 , 6
2006-01-01
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Hide Markov Model , Dynamic Time Warping , Numerical Range , Transformation Operator , Parametric Hide Markov Model Computer Science , Image Processing and Computer Vision , Computer Imaging, Vision, Pattern Recognition and Graphics , Pattern Recognition , Artificial Intelligence (incl. Robotics) , Algorithm Analysis and Problem Complexity
Key Frame-Based Activity Representation Using Antieigenvalues
British Library Conference Proceedings | 2006
|Feature-based models and frame representation for part families formation
Kraftfahrwesen | 1991
|Activity representation with motion hierarchies
British Library Online Contents | 2014
|