基于混合结构神经网络的自适应背景模型

Adaptive Background Model Based on Hybrid Structure Neural Network

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.网络的权值和结构随着视频中运动检测过程动态更新,无需独立的训练视频.网络的自适应性表现在网络的学习速率根据相邻帧运动差异自适应计算得到,且网络中的模式节点个数根据权重的变化动态增加或删除.实验结果表明,本文提出的方法在无需手工设置学习速率的情况下,运动区域检测准确率优于其他几种常见的运动检测背景模型,对背景或灯光的突然变化适应速度很快.

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 dynamically along with motion detection and no training video needed.Adaptability of background model includes adaptive learning rate calculated form motion difference between adjacent frames,and number of pattern node changes according to weight variation.Experimental results on benchmark videos show that,without any manual setting of learning rate,the proposed algorithm can detection motion more precisely than other familiar background models,and it can also adapts to sudden background or lighting changes more quickly.