Motion detection in spatio-temporal space

Liou, Shih-Ping; Jain, Ramesh

doi:10.1016/0734-189x(89)90134-5

Cited by 33 publications

(8 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By replacing I(x+dx, y+dy, t+dt) by its first-order Taylor expansion, (8) yields I x u + I y v + I t = 0, where u = dx/dt and v = dy/dt. It is expressed in vector form as:…”

Section: Brightness Constancy Assumptionmentioning

confidence: 99%

See 1 more Smart Citation

On improving the robustness of differential optical flow

Rashwan

Puig

García

2011

2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops)

View full text Add to dashboard Cite

Differential optical flow techniques estimate flow fields based on the derivatives of consecutive images. However, the use of partial derivatives amplifies the possible noise present in those images, thus degrading the accuracy of the computed flow fields. This problem is usually overcome by smoothing the gradient images with Gaussian filters. However, the latter tends to blur discontinuities, yielding an undesired loss of accuracy. This paper proposes tensor voting as an alternative to Gaussian filtering that yields more robust and accurate optical flow fields. The proposed model yields state-of-the-art results on the Middlebury optical flow database and benchmark.

show abstract

“…By replacing I(x+dx, y+dy, t+dt) by its first-order Taylor expansion, (8) yields I x u + I y v + I t = 0, where u = dx/dt and v = dy/dt. It is expressed in vector form as:…”

Section: Brightness Constancy Assumptionmentioning

confidence: 99%

“…Thus, the latter is a necessary but not sufficient condition for pixels belonging to textured moving regions. In order to avoid that problem, a second angle β is introduced according to the confidence measure proposed in [8]:…”

Section: Spatio-temporal Image Segmentationmentioning

confidence: 99%

On improving the robustness of differential optical flow

Rashwan

Puig

García

2011

2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops)

View full text Add to dashboard Cite

show abstract

“…Even though many techniques have been developed for this purpose, most techniques use just two or three frames of a sequence. Only recently, the so-called spaLio-emporal approach [1,4,5,6,10,14] started using longer sequences. This approach pictures time-varying stimuli as occupying a three-dimensional space, in which x and y are two spatial dimensions and t is the temporal dimension.…”

Section: Introductionmentioning

confidence: 99%

<title>Parallel algorithm for volumetric segmentation</title>

Liou

Jain

1991

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

Developing techniques for interpreting the structure of volumetric data is useful in many applications. A key initial stage is volumetric segmentation, involving the processes of pariilionirig and idenificaion. Here, we present a parallel algorithm which, through the use of a-partitioning and volume filtering, segments volumetric image data such that the greylevel variation within each volume can be described by a regression model. Experimental results demonstrate the effectiveness of this algorithm on several real-world 3D images.

show abstract

“…We should stress here that in this paper we deal with the geometry of the visual input itself, i.e., the geometry of the hypersurface associated with image intensity f(x,y,t). The extrinsic geometry of this hypersurface has been used for the purpose of motion detection in computer vision [20]. We will relate (intrinsic) geometric properties of the hypersurface, in particular the Riemann tensor, to the problems of motion detection and the estimation of optic flow.…”

Section: Introductionmentioning

confidence: 99%

A geometric framework for nonlinear visual coding

Barth¹,

Watson²

2000

Opt. Express

View full text Add to dashboard Cite

It is argued that important aspects of early and middle level visual coding may be understood as resulting from basic geometric processing of the visual input. The input is treated as a hypersurface defined by image intensity as a function of two spatial coordinates and time. Analytical results show how the Riemann curvature tensor R of this hypersurface represents speed and direction of motion. Moreover, the results can predict the selectivity of MT neurons for multiple motions and for motion in a direction along the optimal spatial orientation. Finally, a model based on integrated R components predicts global-motion percepts related to the barber-pole illusion.

show abstract

Motion detection in spatio-temporal space

Cited by 33 publications

References 17 publications

On improving the robustness of differential optical flow

On improving the robustness of differential optical flow

<title>Parallel algorithm for volumetric segmentation</title>

A geometric framework for nonlinear visual coding

Contact Info

Product

Resources

About