One Dimensional Multi-Velocity Motion Detection Neural Networks Based on Lateral Inhibitory Mechanism

王爱群; 郑南宁; 袁立行; 龙甫荟

您当前的位置：

首页 >

文章列表页 >

One Dimensional Multi-Velocity Motion Detection Neural Networks Based on Lateral Inhibitory Mechanism

更新时间：2025-12-08

- One Dimensional Multi-Velocity Motion Detection Neural Networks Based on Lateral Inhibitory Mechanism
- Acta Electronica Sinica Issue 11, (1997)
- 作者机构：
  
  西安交通大学人工智能与机器人研究所
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP183
- Published：1997
- 稿件说明：
移动端阅览
[1]王爱群,郑南宁,袁立行,龙甫荟.基于侧抑制机制的一维多速度运动检测神经网络[J].电子学报,1997(11):22-26.

王爱群, 郑南宁, 袁立行, et al. One Dimensional Multi-Velocity Motion Detection Neural Networks Based on Lateral Inhibitory Mechanism[J]. Acta Electronica Sinica, 1997, (11).
[1]王爱群,郑南宁,袁立行,龙甫荟.基于侧抑制机制的一维多速度运动检测神经网络[J].电子学报,1997(11):22-26. DOI：

王爱群, 郑南宁, 袁立行, et al. One Dimensional Multi-Velocity Motion Detection Neural Networks Based on Lateral Inhibitory Mechanism[J]. Acta Electronica Sinica, 1997, (11). DOI：

摘要

运动感知是生物视觉系统的一个重要组成部分．动物对自然界的认识一大部分是通过运动感知．本文通过对同时具有方向和速率选择性的视觉皮层运动区神经元的侧抑制机制的模拟，提出了一种新的乘积抑制速度检测子（ＭｕｌｔｉｐｌｉｃａｔｉｖｅＩｎｈｉｂｉｔｏｒｙＶｅｌｏｃｉｔｙＤｅｔｅｃｔｏｒ－ＭＩＶＤ），其时空联合参数Ｋ决定了检测子的最优速度，基于ＭＩＶＤ的响应幅度差特性，我们构造了两个多速度融合神经网络（一个简单神经网络和一个主动神经网络）来检测一维运动速度．实验结果表明具有反馈的主动ＭＩＶＤ神经网络能够给出较好的检测结果．

Abstract

Motion perception is one of the most important components of biological vision system. In this paper

by simulating the lateral inhibitory mechanism of the neurons in the motion area of visual cortex

we propose a new Multiplicative Inhibitory Velocity Detector（MIVD）. The optimum velocity of this detector is determined by its spatial-temporal joint parameter K. Based on the respoase disarity of MIVD

we construct two multi velocity fusion Neural Networks（a simple one and an active one）to detect the velocity of one dimensional motion.The experiments show that the active MIVD Neural Networks with feedback have better detecting result.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Real-Time Gesture Recognition Algorithm Based on LoRa Signals

Continual Learning Methods and Applications in Computer Vision

End-to-End Full Complex-Valued Domain SAR Target Classification Neural Network

Related Author

HAN Chong

DU Hao

GUO Jian

SUN Li-juan

FANG Yan

Wei Yun-chao

Cong Run-min

Zuo Wang-meng

Related Institution

College of Computer, Nanjing University of Posts and Telecommunications

Jiangsu Key Laboratory of Intelligent Sensing and Computing for Internet of Things

School of Computer Science and Technology, Beijing Jiaotong University

School of Control Science and Engineering, Shandong University

School of Computer Science and Technology, Harbin Institute of Technology

⁰