2009 # A Multi-scale Feature Based Optic Flow Method for 3D Cardiac Motion Estimation

Help me understand this report

Search citation statements

Paper Sections

Select...

2

2

1

Citation Types

0

7

0

Year Published

2011

2020

Publication Types

Select...

5

2

1

Relationship

1

7

Authors

Journals

(7 citation statements)

0

7

0

“…Hence,
$\mathrm{boldV}\left(t\right)=\left(\begin{array}{c}u\left(t\right)\\ v\left(t\right)\\ w\left(t\right)\end{array}\right)=-H{\left(\mathrm{boldx}\left(t\right),s,t\right)}^{-1}\frac{\partial \left(\nabla L{\left(\mathrm{boldx}\left(t\right),s,t\right)}^{T}\right)}{\partial t},$
where H represents the spatial Hessian matrix of image L . In the literature, similar optic flow approaches that calculate velocity estimation at feature point location using the Hessian matrix are discussed in [9, 10, 43, 45]. …”

confidence: 99%

“…Hence,
$\mathrm{boldV}\left(t\right)=\left(\begin{array}{c}u\left(t\right)\\ v\left(t\right)\\ w\left(t\right)\end{array}\right)=-H{\left(\mathrm{boldx}\left(t\right),s,t\right)}^{-1}\frac{\partial \left(\nabla L{\left(\mathrm{boldx}\left(t\right),s,t\right)}^{T}\right)}{\partial t},$
where H represents the spatial Hessian matrix of image L . In the literature, similar optic flow approaches that calculate velocity estimation at feature point location using the Hessian matrix are discussed in [9, 10, 43, 45]. …”

confidence: 99%

“…This optic flow technique is not based on brightness conservation; therefore, it can be robustly applied directly on tagged MRI. In [ 43 ], a similar 3D motion estimation procedure has been presented. In this case, the critical points have been extracted by a methodology based on zerocrossings.…”

confidence: 99%

“…On the data set, proposed algorithm showed 100% and 83% of accuracy in recognizing anomalous events at two different locations. Alessandro Becciu, Luc Florack, Hans van Assen, Vivian Roode, Sebastian Kozerke, and Bart M, in [13] proposed a new three-dimensional (3D) multiscale OFbased method for analyzing a true 3D cardiac motion at voxel precision. Rizwan Chaudhry, Gregory Hager, Ren´e Vidal and Avinash Ravichandran, in [14] proposed usage of generalization of the Binet-Cauchy kernels to nonlinear dynamical systems (NLDS) and represented each frame of a video using a histogram of oriented optical flow (HOOF) to recognize human actions by classifying HOOF time-series.…”

confidence: 99%

“…By design, these methods discard the remaining motion information and solely rely on the information conveyed by shift invariant intensity patterns. In contrast, motion-based methods explicitly model the existing misalignment as local motions and use the variation in motion as cues for registration [8] and the existence of an underlying cause [10].…”

confidence: 99%