視覺感知的模擬超大規(guī)模集成電路實現（影印版）

Foreword
Preface
1 Introduction
1.1 Artificial Autonomous Systems
1.2 Neural Computation and Analog Integrated Circuits
2 Visual Motion Perception
2.1 Image Brightness
2.2 Correspondence Problem
2.3 Optical Flow
2.4 Matching Models
2.5 Flow Models
2.6 Outline for a Visual Motion Perception System
2.7 Review of a VLSI Implementations
3 Optimization Networks
3.1 Associative Memory and Optimization
3.2 Constraint Satisfaction Problems
3.3 Winner-takes-all Networks
3.4 Resistive Network
4 Visual Motion Perception Networks
4.1 Model for Optical Flow Estimation
4.2 Network Architecture
4.3 Simulation Results for Natural Image Sequences
4.4 Passive Non-linear Network Conducatances
4.5 Extended Recurrent Network Architectures
4.6 Remarks
5 Analog VLSI Implementation
5.1 Implementation Substrate
5.2 Phototransduction
5.3 Extraction of the Spatio-temporal Brightness Gradients
5.4 Single Optical Flow Unit
5.5 Layout
6 Smooth Optical Flow Chip
6.1 Response Characteristics
6.2 Intersection-of-constraints Solution
6.3 Flow Field Estimation
6.4 Device Mismatch
6.5 Processing Speed
6.6 Applications
7 Extended Network Implementations
7.1 Motion Segmentation Chip
7.2 Motion Selection Chip
8 Comparison to Human Motion Vision
8.1 Human vs.Chip Perception
8.2 Computational Architecture
8.3 Remarks
A Variational Calculus
B Simulation Methods
C Transistors and Basic Circuits
D Process Parameters and Chips Specifications
References
Index