从二维视图识别三维目标的多网络融合方法  

A Multiple Networks Fusion Approach for 3-D Ojbect Recognition from 2-D Veiws

作　　者：贾财潮[1] 戚飞虎[1] 于询[2] 张季涛[2] 

机构地区：[1]上海交通大学计算机科学与工程系,上海200030 [2]西安应用光学研究所,西安710100

出　　处：《光学学报》2001年第2期177-180,共4页Acta Optica Sinica

基　　金：国防科工委九五预研资助项目

摘　　要：提出了一种从二维视图识别三维目标的多网络融合方法 ,基于单个网络分类的置信度概念 ,有效地结合多个网络的输出结果作出最终分类判决。应用三个多层前向网络 (隐层神经元数、初始权值等取不同值 ) ,设计了基于分类确信度的多网络融合结构。对四类车辆目标进行的识别实验表明 。A multiple networks fusion approach is proposed for 3D object recognition from 2D views. As the probability of correct classification is correlated with certainty of a network, a fusion method based on certainty is developed which combines the outputs from all the neural networks to improve classification performance. A multiple networks fusion structure is constructed by combining three multi layer forward propagation network that differ from the others in internal parameters such as the number of hidden layer nodes, initial random weights et al.. The performance is compared to that of individual MLP using four different vehicles involving clean and noisy images. It is shown that multiple networks fusion has major advantages over single multi payer forward propagation network.

关 键 词：多网络融合 三维目标识别 置信度 多层前向网络 二维视图 自动目标识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP183[自动化与计算机技术—计算机科学与技术]