计算机应用 ›› 2015, Vol. 35 ›› Issue (3): 849-853.DOI: 10.11772/j.issn.1001-9081.2015.03.849

• 虚拟现实与数字媒体 • 上一篇    下一篇

高分辨率遥感影像复杂场景的汇总统计方法

顾秀颖1,2, 赵子沂1,2, 方涛1,2, 霍宏1,2   

  1. 1. 上海交通大学 自动化系, 上海 200240;
    2. 系统控制与信息处理教育部重点实验室, 上海 200240
  • 收稿日期:2014-10-14 修回日期:2014-11-19 出版日期:2015-03-10 发布日期:2015-03-13
  • 通讯作者: 顾秀颖
  • 作者简介:顾秀颖(1990-),女,江苏泰兴人,硕士研究生,主要研究方向:遥感图像场景理解;赵子沂(1985-),男,山东临沂人,博士研究生,主要研究方向:模式识别、图像处理;方涛(1965-),男,四川彭山人,教授,博士,主要研究方向:图像理解、遥感科学与技术;霍宏(1972-),女,辽宁本溪人,讲师,硕士,主要研究方向:遥感图像理解
  • 基金资助:

    国家973计划项目(2012CB719903);国家自然科学基金资助项目(41071256);国家自然科学基金青年科学基金资助项目(41101386);国家自然科学基金委创新研究群体资助项目(61221003)

Summary statistics method for complex scenes of high-resolution remote sensing image

GU Xiuying1,2, ZHAO Ziyi1,2, FANG Tao1,2, HUO Hong1,2   

  1. 1. Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, China;
    2. Key Laboratory of System Control and Information Processing, Ministry of Education, Shanghai 200240, China
  • Received:2014-10-14 Revised:2014-11-19 Online:2015-03-10 Published:2015-03-13

摘要:

针对高分辨率遥感影像场景的分类,受人类视觉系统从场景中提取汇总统计信息用于场景感知的启发,提出场景汇总统计特征提取方法。该方法提取场景的平均方向信息和视觉杂乱度,利用Gabor滤波器统计场景的平均方向信息,并基于视觉拥堵进行场景的杂乱度度量,然后将两者组合在一起,形成基于汇总统计特征的复杂场景描述。在21类遥感数据集上的实验表明,当训练样本和测试样本各为50幅时,该方法的分类精度比Gist方法高6.5%,比词包模型(BOW)方法高3.22%,且计算简单,同时与Gist相比,不需要人工干预。

关键词: 汇总统计, 场景表达, 平均方向信息, 视觉杂乱度, 遥感影像场景

Abstract:

For the classification of high-resolution remote sensing images, inspired by human vision system which extracts summary statistics information for scene perception, a feature extraction method based on summary features was proposed. In the method average orientation information and visual clutter were extracted and combined to form a representation based on summary statistics, in which average orientation information was summarized by using Gabor filters and visual clutter was measured based on visual crowding.The experimental results on the classification of 21 classes of remote sensing image set reveal that the classification accuracy of the proposed method is 6.5% higher than Gist and 3.22% higher than Bag-Of-Words (BOW), when the number of training images and testing images are both 50. It also has lower calculation burden. While compared with Gist, the proposed method doesn't need any human intervention.

Key words: summary statistics, scene representation, average orientation information, visual clutter, remote image scene

中图分类号: