C. M. Higgins and C. Koch. Analog CMOS velocity sensors. In Electronic Imagin'97, San Jose, CA., February 1997. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
An Efficient Neuromorphic Analog Network For Motion Estimation - Torralba, Herault (1999) (Correct)
....they give reliable measurements of velocity and they allow an easy treatment of the aperture problem. However, due to the complexity of implementing a battery of spatiotemporal filters, current VLSI motion chips use gradient based algorithms [24] 6] or correlation based algorithms [12] 7] [9] as they can be implemented within very compact circuits. In this paper we present a new energy based algorithm that significantly minimizes the complexity of these kinds of methods. The reduction of complexity is due to: 1) the use of a new wideband velocity tuned filter (VTF) simpler than the ....
C.M. Higgins and C. Koch. Analog CMOS velocity sensors. In Electronic Imagin'97, San Jose, CA., February 1997.
Analogue Architectures for Vision: Cellular Neural Networks and.. - Torralba (1999) (Correct)
....aliasing, they give reliable measurements of velocity and they allow an easy treatment of the 41 aperture problem. However, due to the complexity of implementing a battery of spatiotemporal filters, current VLSI motion chips use gradient based algorithms [82, 24] or correlation based algorithms [46, 25, 33] as they can be implemented within very compact circuits. In this chapter we present energy based algorithm that significantly minimizes the complexity of these kinds of methods. The reduction of complexity is due to: 1) the use of a new wideband velocity tuned filter (VTF) simpler than the ....
C. M. Higgins and C. Koch. Analog CMOS velocity sensors. In Electronic Imagin'97, San Jose, CA., February 1997.
PhD Thesis: Overview - Alan Stocker (Correct)
....dimension or 2x1D by creating a two dimensional array out of one dimensional motion units. The best local information that one can get with these feed forward computation schemes is so called Normal Flow where only local velocities orthogonal to the intensity edge, or gradient, are calculated [3, 2, 4, 5, 11, 7, 1]. The use of such normal flow information to achieve motion segmentation has been shown [8] However, this was done in one dimension where the aperture problem does not occur and feed forward computation of local motion is well defined. In two dimensions this is no longer the case and normal flow ....
C. Higgins and C. Koch. Analog cmos velocity sensors. Proc. of Electronic Imaging SPIE, 3019, Februar 1997.
Analogue Architectures for Vision: Cellular Neural Networks and.. - Torralba (1999) (Correct)
No context found.
C. M. Higgins and C. Koch. Analog CMOS velocity sensors. In Electronic Imagin'97, San Jose, CA., February 1997.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC