面向非合作目标识别的大规模类属超图建模  

Learning Large Scale Class Specific Hyper Graphs for Non-Cooperative Object Recognition

作　　者：夏胜平[1] 宋锐[1] 刘建军[1] 张乐峰[1] 虞华[1] Edwin Hancock 

机构地区：[1]国防科学技术大学电子科学与工程学院ATR实验室,湖南长沙410073 [2]英国约克大学计算机系

出　　处：《电子学报》2011年第6期1399-1404,共6页Acta Electronica Sinica

基　　金：国家自然科学基金(No.60972114)

摘　　要：针对大量不同成像条件下获得的多视图像,研究利用局部不变特征及其空间布局约束构建用于非合作目标识别的类属超图模型的方法.该方法首先将每一幅图像表示为使用选定的稳健SIFT特征构成的属性图,然后提出了一种属性图相似性传播聚类原理.在给定的F度量的约束下,利用该原理进行聚类,并根据熵函数最小化优化条件,可迭代得到特定目标属性图样本集合的最优聚类,进一步将所获得的聚类简化成以非冗余属性图作为节点的类属超图模型.本文用大量图像样本进行了试验测试.实验结果验证了模型的可扩展性和识别性能.This paper describes how to construct a class specific hyper-graph（CSHG） model from a large corpus of multi-view images using local invariant features and their spatial configuration.As the first step of this method,each image is represented with a graph,which is constructed from a group of selected robust SIFT features.Secondly,a similarity propagation based graph clustering（SPGC） method is then proposed.Using this clustering method,the positive example graphs of a specific class accompanied with a set of negative example graphs are clustered into one or more clusters,which minimize an entropy function with a restriction defined on the F-measure.Based on SPGC and the rules of minimizing an entropy function,each cluster is simplified into a tree structure composed of a series of irreducible graphs.Finally,a recognition oriented class specific hyper-graph is generated from the given graph set.Using a trained CSHG model,object recognition can be implemented.Experimental results demonstrate the scalability and recognition performance of the method.

关 键 词：目标识别 类属超图 局部不变特征 属性图 尺度不变特征 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]