运动视觉系统误差建模  

Uncertainty modeling for motion vision system

作　　者：周凌翔[1] 顾伟康[1] 

机构地区：[1]浙江大学信息与电子工程学系信息与智能系统研究所,浙江杭州310027

出　　处：《浙江大学学报（自然科学版）》1999年第5期547-553,共7页

摘　　要：为了充分利用图像信息,运动视觉系统需要定量处理测量误差,特别是像素量化效应导致的不确定性.在提出一般运动视觉系统点特征误差的正态概率模型的基础上,用特征坐标的期望值和协方差矩阵之逆来描述位置的不确定性,其扩展形式建立了二维图像点和三维特征点位置不确定性的统一描述.同时也具体给出了误差形成、传播和估计的计算公式和实验结果.In order to manipulate image information optimally, the vision system must quantitatively take the measurement uncertainties into account, especially the digital quantization errors. In this paper a normal probability error model of point features in a general motion vision system is presented. We provide a novel representation, which describes uncertainty with the expects of the feature coordinates as well as the inverse of the covariance matrix. 2D image points uncertainties can also be represented by an extension of this unified 3D form. Explicit formulas and experimental results for both error generation and evolution are presented.

关 键 词：计算机视觉 误差建模 运动分析 数据融合 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]