Stationary processes for object detection and non-rigid structure-from-motion
Data(s) |
2016
|
---|---|
Resumo |
Stationary processes are random variables whose value is a signal and whose distribution is invariant to translation in the domain of the signal. They are intimately connected to convolution, and therefore to the Fourier transform, since the covariance matrix of a stationary process is a Toeplitz matrix, and Toeplitz matrices are the expression of convolution as a linear operator. This thesis utilises this connection in the study of i) efficient training algorithms for object detection and ii) trajectory-based non-rigid structure-from-motion. |
Formato |
application/pdf |
Identificador | |
Publicador |
Queensland University of Technology |
Relação |
http://eprints.qut.edu.au/94745/1/Jack_Valmadre_Thesis.pdf Valmadre, Jack L. (2016) Stationary processes for object detection and non-rigid structure-from-motion. PhD thesis, Queensland University of Technology. |
Fonte |
Institute for Future Environments |
Palavras-Chave | #computer vision #object detection #structure from motion #stationary process #toeplitz #circulant #fourier #signal processing |
Tipo |
Thesis |