Computing Motion Using Analog and Binary Resistive Networks

Authors:
James Hutchinson;Christof Koch;Jin Luo;Carver Mead
Affiliations:
Jet Propulsion Laboratory;California Institute of Technology;California Institute of Technology;California Institute of Technology
Venue:
Computer
Year:
1988

Citing 7
Cited 21

Computational vision and regularization theory

Nature
Simple analog and hybrid networks for surface interpolation

AIP Conference Proceedings 151 on Neural Networks for Computing
Visual reconstruction

Visual reconstruction
On the estimation of optical flow: relations between different approaches and some new results

Artificial Intelligence
Analog VLSI and neural systems

Analog VLSI and neural systems
Measurement of Visual Motion

Measurement of Visual Motion
Energy Functions for Early Vision and Analog Networks

Energy Functions for Early Vision and Analog Networks

Computing with Structured Neural Networks

Computer
Multiple Resolution Segmentation of Textured Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Cooperative Vision Integration Through Data-Parallel Neural Computations

IEEE Transactions on Computers - Special issue on artificial neural networks
Bayesian Estimation of Motion Vector Fields

IEEE Transactions on Pattern Analysis and Machine Intelligence
Statistical pattern classification with electric circuits

Pattern Recognition Letters
Exploiting Discontinuities in Optical Flow

International Journal of Computer Vision
Pulse Arithmetic in VLSI Neural Networks

IEEE Micro
Simulating a Function of Visual Peripheral Processes with an Analog VLSI Network

IEEE Micro
Figure-Ground Segregation Using an Analog VLSI Chip

IEEE Micro
Analog Nonlinear Function Synthesis

IEEE Micro
Multimodal Estimation of Discontinuous Optical Flow using Markov Random Fields

IEEE Transactions on Pattern Analysis and Machine Intelligence
Analog Velocity Sensing Circuits Based on Bio-Inspired Correlation Neural Networks

MICRONEURO '99 Proceedings of the 7th International Conference on Microelectronics for Neural, Fuzzy and Bio-Inspired Systems
A new approach for testing artificial neural networks

VTS '97 Proceedings of the 15th IEEE VLSI Test Symposium
Motion estimation for region-based video coding

ICIP '95 Proceedings of the 1995 International Conference on Image Processing (Vol.2)-Volume 2 - Volume 2
Length-speed ratio (LSR) as a characteristic for moving elements real-time classification

Real-Time Imaging
New Robotics: Design Principles for Intelligent Systems

Artificial Life
Review:

Neural Computation
Comparison of stochastic and deterministic solution methods in Bayesian estimation of 2D motion

Image and Vision Computing
Incremental estimation of image flow using a Kalman filter

Journal of Visual Communication and Image Representation
Recursive displacement estimation and restoration of noisy-blurred image sequences

ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: image and multidimensional signal processing - Volume V
Image segmentation cues in motion processing: Implications for modularity in vision

Journal of Cognitive Neuroscience

Quantified Score

Hi-index	4.10

Visualization

Abstract

The authors describe recent developments in the theory of early vision that led from the formulation of the motion problem as an ill-posed one to its solution by minimizing certain 'cost' functions. These cost or energy functions can be mapped onto simple analog and digital resistive networks. The optical flow is computed by injecting currents into resistive networks and recording the resulting stationary voltage distribution at each node. The authors believe that these networks, which they implemented in complementary metal-oxide-semiconductor (CMOS) very-large-scale integrated (VLSI) circuits, represent plausible candidates for biological vision systems.