| 基于混合结构神经网络的自适应背景模型 |
| |
| 引用本文： | 王志明,张丽,包宏.基于混合结构神经网络的自适应背景模型[J].电子学报,2011,39(5):1053-1058. |
| |
| 作者姓名： | 王志明 张丽 包宏 |
| |
| 作者单位： | 王志明,包宏,WANG Zhi-ming,BA Hong(北京科技大学计算机与通信工程学院计算机科学与技术系,北京,100083);张丽,ZHANG Li(清华大学工程物理系,北京,100084) |
| |
| 摘 要： | 本文提出一种基于神经网络的视频中运动目标检测自适应背景模型.对每个像素点(或局部区域)建立一个混合结构的神经网络背景模型,模型由一个4层前馈神经网络组成,输入层接受像素HSV特征,特征层实现特征提取功能,模式层以概率神经网络的方式完成像素属于背景概率的计算,输出层以赢者取胜的方式完成前景背景分类和模式层激活节点选择功能...
|
| 关 键 词： | 视频监控 运动检测 神经网络(NN) 概率神经网络(PNN) 赢者取胜(WTA) |
| 收稿时间： | 2010-03-29 |
Adaptive Background Model Based on Hybrid Structure Neural Network |
| |
| WANG Zhi-ming,ZHANG Li,BA Hong.Adaptive Background Model Based on Hybrid Structure Neural Network[J].Acta Electronica Sinica,2011,39(5):1053-1058. |
| |
| Authors: | WANG Zhi-ming ZHANG Li BA Hong |
| |
| Affiliation: | WANG Zhi-ming1,ZHANG Li2,BAO Hong1(1.Department of Computer Science and Technology,School of Computer and Communication Engineering,University of Science andTechnology Beijing,Beijing,100083,China,2.Department of Engineering Physics,Tsinghua University,100084,China) |
| |
| Abstract: | This paper proposed a new background model for motion detection in video surveillance based on neural network(NN).A neural network background model was build for every pixel(or a small local region).It is a four-layer feedforward neural network.Input layer accept HSV pixel value,feature layer extract features form HSV,pattern layer work as a background probability calculator.Output layer classifies the pixel into background or foreground,and finds the activated node.Weights and structure of network updated ... |
| |
| Keywords: | video surveillance motion detection neural network(NN) probabilistic neural network(PNN) winner take all(WTA) |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《电子学报》浏览原始摘要信息 |
|
点击此处可从《电子学报》下载全文 |
|
