基于学习矢量量化的运动目标检测算法  

A Moving Object Detection Algorithm Based on Learning Vector Quantization

作　　者：王世东[1,2] 周德闯[1] 汪箭[1] 

机构地区：[1]中国科学技术大学火灾科学国家重点实验室,合肥230026 [2]安徽建筑工业学院信息网络中心,合肥230022

出　　处：《光电工程》2012年第9期42-48,共7页Opto-Electronic Engineering

基　　金：国家自然科学基金重大研究计划重点支持项目(91024027)

摘　　要：提出一种基于学习矢量量化的运动目标检测算法。通过训练样本,网络能自适应地确定区分运动目标和背景的阈值向量。输入向量包含图像的YCbCr颜色空间分量和灰度共生矩阵的方向特征。两者融合到算法中,有效抑制了背景亮度变化对运动目标检测的干扰。仿真实验结果表明,即使在背景模型亮度剧烈变化的情况下,算法也能够准确检测出运动目标。A moving object detection algorithm based on Learning Vector Quantization （LVQ） is presented. By training samples, the threshold vector of extracting the moving objects has the self adaptive ability. The input vector includes components of YCbCr color space and direction feature of Gray Level Co occurrence Matrix （GLCM）. These two features are integrated to the algorithm, which has the efficiency of inhibiting the disturbance of background brightness variation. Experiment results indicate that the moving objects can be extracted correctly by using the algorithm, even if the complex background has an acute brightness variation.

关 键 词：运动目标检测 学习矢量量化 YCBCR 灰度共生矩阵 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]