基于条件随机场的遥感图像语义标注  

Remote sensing image semantic labeling based on conditional random field

作　　者：杨俊俐 姜志国[1,2] 周全[3] 张浩鹏[1,2] 史骏[1,2] 

机构地区：[1]北京航空航天大学宇航学院,北京100191 [2]数字媒体北京市重点实验室,北京100191 [3]南京邮电大学通信与信息工程学院,南京210003

出　　处：《航空学报》2015年第9期3069-3081,共13页Acta Aeronautica et Astronautica Sinica

基　　金：国家自然科学基金(61371134;61071137;60776793);中央高校基本科研业务费专项资金~~

摘　　要：遥感图像包含的信息丰富,纹理复杂,而遥感图像语义标注又为后续的目标识别、检测、场景分析及高层语义的提取提供了重要信息和线索,这使其成为遥感图像理解领域中一个关键且极具挑战性的任务。首先针对遥感图像语义标注问题,提出采用条件随机场(CRF)框架对遥感图像的底层特征和上下文信息建模的方法,将Texton纹理特征与CRF中的自相关势能结合来捕捉遥感图像中的纹理信息及其上下文分布,采用组合Boosting算法进行Texton纹理特征选择和参数学习;然后将Lab空间中的颜色信息与CRF中的互相关势能结合来描述颜色上下文;最后用Graph Cut算法对CRF进行推导求解,得到图像自动语义标注结果。同时,建立了可见光遥感图像数据库Google-4,并对全部图像进行了人工标注。Google-4上的实验结果表明:采用CRF框架与Texton纹理特征和颜色特征相结合对遥感图像建模的方法与基于支持向量机(SVM)的方法相比较,能够取得更准确的语义标注结果。Remote sensing images exhibit abundant information and complicated texture, and remote sensing image semantic labeling provides important information and clue for the subsequent object recognition, detection, scene analysis and high-level semantic extraction, which makes it a significant and extremely challenging task in remote sensing image understanding field. To address the task of remote sensing image semantic labeling, we propose to utilize the conditional random field （CRF） framework to model the low-level features and context information in remote sensing images. A texture descriptor ＇Texton＇ is combined with the association potential in CRF framework to capture the texture layout in remote sensing images. ＇Texton; feature selection and model parameter learning are carried out by employing the joint Boosting algorithm. And color information in Lab color space is used in the interaction potential in CRF to describe the color context. Then a Graph Out algorithm is utilized to infer the CRF model to get the automatic semantic labeling results of the images. At the same time, we establish an optical remote sensing image database Google-4 and label all the images by manual annotation. Experimental results on Google-4 show that the CRF modeling scheme combined with ;Texton; and color feature can accomplish the semantic labeling task of remote sensing images more accurately compared to the support vector machine （SVM）-based methods.

关 键 词：遥感图像 图像理解 语义标注 条件随机场 上下文 

分 类 号：V19[航空宇航科学与技术—人机与环境工程] TP391[自动化与计算机技术—计算机应用技术]