首页 | 本学科首页   官方微博 | 高级检索  
     

基于学习矢量量化的运动目标检测算法
引用本文:王世东,周德闯,汪箭. 基于学习矢量量化的运动目标检测算法[J]. 光电工程, 2012, 39(9): 42-48
作者姓名:王世东  周德闯  汪箭
作者单位: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
基金项目: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.

关 键 词:运动目标检测  学习矢量量化  YCbCr  灰度共生矩阵
收稿时间:2012-04-10

A Moving Object Detection Algorithm Based on Learning Vector Quantization
Affiliation:WANG Shi-dong 1,2,ZHOU De-chuang 1,WANG Jan 1 (1.State Key Laboratory of Fire Science,University of Science and Technology of China,Hefei 230026,China;2.Information Network Center,Anhui University of Architecture,Hefei 230022,China)
Abstract: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.
Keywords:moving object detection  learning vector quantization  YCbCr  gray level c-occurrence matrix
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号