利用双指数函数导数模型进行高分辨率卫星影像目标检测  

A Novel High Resolution Satellite Imagery Object Detection Based on Derivative of Double Exponential

作　　者：胡学敏[1] 郑宏[1] 司小书[1] 

机构地区：[1]武汉大学电子信息学院智能计算与智能系统联合实验室,武汉市珞喻路129号430079

出　　处：《武汉大学学报（信息科学版）》2010年第11期1265-1270,共6页Geomatics and Information Science of Wuhan University

基　　金：国家自然科学基金资助项目(40571102);武汉大学自主科研基金资助项目(6081001)

摘　　要：提出了一种从高分辨率卫星影像中检测特定目标的方法。该方法首先用一种双边滤波的方法去除图像中的噪声,然后采用形态学处理的方法对图像进行分割和特征增强,并提取兴趣区域。在目标检测阶段,设计了一种基于双指数函数导数(DODE)模型的检测算子,该算子是面向具体目标设计的,能实现稳健的目标检测。对Google Earth中的影像分别进行了车辆检测实验和船舰检测实验,结果表明,此方法能够有效准确地检测高分辨率卫星影像中的特定目标。This paper presents a novel approach of detecting special objects from high resolution satellite imagery.In this approach,a bilateral filtering is used to reduce the noise firstly,and a morphology approach is proposed for ROI extraction and feature enhancement.A detection operator based on the derivative of the double exponential（DODE） is developed to detect enhanced objects.The operator is designed according to special objects.The experiments which include vehicle detection and ship detection from Google Earth images are discussed.The experimental results show that proposed approach is effective and feasible.

关 键 词：双指数函数导数 目标检测 高分辨率卫星影像 

分 类 号：P237.4[天文地球—摄影测量与遥感]