Accuracy vs efficiency trade-offs in optical flow algorithms
H Liu, TH Hong, M Herman, T Camus… - Computer vision and …, 1998 - Elsevier
There have been two thrusts in the development of optical flow algorithms. One has
emphasized higher accuracy; the other faster implementation. These two thrusts, however …
emphasized higher accuracy; the other faster implementation. These two thrusts, however …
Accuracy vs. efficiency trade-offs in optical flow algorithms
H Liu, TH Hong, M Herman, R Chellappa - Computer Vision—ECCV'96 …, 1996 - Springer
There have been two thrusts in the development of optical flow algorithms. One has
emphasized higher accuracy; the other faster implementation. These two thrusts, however …
emphasized higher accuracy; the other faster implementation. These two thrusts, however …
A charge-based CMOS parallel analog vector quantizer
G Cauwenberghs, V Pedroni - Advances in Neural …, 1994 - proceedings.neurips.cc
We present an analog VLSI chip for parallel analog vector quantiza (cid: 173) tion. The
MOSIS 2.0 J.. Lm double-poly CMOS Tiny chip contains an array of 16 x 16 charge-based …
MOSIS 2.0 J.. Lm double-poly CMOS Tiny chip contains an array of 16 x 16 charge-based …
Neuromorphic learning VLSI systems: A survey
G Cauwenberghs - … Systems Engineering: Neural Networks in Silicon, 1998 - Springer
Carver Mead introduced “neuromorphic engineering”[1] as an interdisciplinary approach to
the design of biologically inspired neural information processing systems, whereby …
the design of biologically inspired neural information processing systems, whereby …
Future high performance computing capabilities: Summary report of the advanced scientific computing advisory committee (ascac) subcommittee
The ASCAC Subcommittee on Future High Performance Computing (HPC) Capabilities has
reviewed opportunities and challenges related to the most promising technologies that are …
reviewed opportunities and challenges related to the most promising technologies that are …
Length–speed ratio (LSR) as a characteristic for moving elements real-time classification
MA Fernández, A Fernández-Caballero, MT López… - Real-Time Imaging, 2003 - Elsevier
In this article, the length–speed ratio (LSR) is proposed as a basic characteristic for the real-
time detection of moving objects. We define the LSR of a uniform moving zone as the …
time detection of moving objects. We define the LSR of a uniform moving zone as the …
Fast hardware implementation of Gabor filter based motion estimation
A Spinéi, D Pellerin, D Fernandes… - Integrated Computer …, 2000 - content.iospress.com
Motion estimation in image sequences is a fundamental issue in many applications as for
instance in artificial vision and three-dimensional scene reconstruction. Among all the …
instance in artificial vision and three-dimensional scene reconstruction. Among all the …
Ensemble competitive learning neural networks with reduced input dimension
J Kim, J Ahn, S Cho - International Journal of Neural Systems, 1995 - World Scientific
Conventional neural networks utilize all the dimensions of the original input patterns for
training and classification. However, a particular attribute of the input patterns does not …
training and classification. However, a particular attribute of the input patterns does not …
Neural structures for visual motion tracking
This paper addresses visual motion tracking by a connectionist method, and aims at
showing how the flexibility and the generalization power of neural networks can enhance a …
showing how the flexibility and the generalization power of neural networks can enhance a …
VLSI implementation of the Hippocampal dentate gyrus
OTC Chen, T Berger, BJ Sheu - World Congress on Neural …, 2021 - taylorfrancis.com
The VLSI implementation of a mathematical model of the functional properties of the
hippocampal formation has been developed. The hippocampal formation is a brain system …
hippocampal formation has been developed. The hippocampal formation is a brain system …