计算机应用 ›› 2017, Vol. 37 ›› Issue (6): 1787-1792.DOI: 10.11772/j.issn.1001-9081.2017.06.1787

• 计算机视觉与虚拟现实 • 上一篇    下一篇

基于邻域总变分和势直方图函数的高分辨率遥感影像建筑物提取

施文灶1,2,3, 刘金清1,2,3   

  1. 1. 福建师范大学 光电与信息工程学院, 福州 350108;
    2. 福建师范大学 医学光电科学与技术教育部重点实验室, 福州 350007;
    3. 福建师范大学 福建省光子技术重点实验室, 福州 350007
  • 收稿日期:2016-11-10 修回日期:2016-12-22 出版日期:2017-06-10 发布日期:2017-06-14
  • 通讯作者: 施文灶
  • 作者简介:施文灶(1982-),男,福建晋江人,讲师,博士,主要研究方向:智能测控,遥感影像建筑物提取和变化检测;刘金清(1964-),男,福建莆田人,教授,主要研究方向:数字图像目标识别和提取、数字信号处理设计与开发。
  • 基金资助:
    教育部"长江学者和创新团队发展计划"创新团队项目滚动支持计划(IRT_15R10);福建省自然科学基金项目(2017J01464)。

Building extraction from high-resolution remotely sensed imagery based on neighborhood total variation and potential histogram function

SHI Wenzao1,2,3, LIU Jinqing1,2,3   

  1. 1. College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou Fujian 350108, China;
    2. Key Laboratory of OptoElectronic Science and Technology for Medicine of Ministry of Education, Fujian Normal University, Fuzhou Fujian 350007, China;
    3. Fujian Provincial Key Laboratory of Photonics Technology, Fujian Normal University, Fuzhou Fujian 350007, China
  • Received:2016-11-10 Revised:2016-12-22 Online:2017-06-10 Published:2017-06-14
  • Supported by:
    This work is partially supported by the Program for Changjiang Scholars and Innovative Research Team in University (IRT_15R10), the Natural Science Foundation of Fujian (2017J01464).

摘要: 针对现在的高分辨率遥感影像建筑物识别与提取方法存在的准确率低及数据要求严格等问题,提出一种基于邻域总变分(NTV)和势直方图函数(PHF)的方法。首先,计算遥感影像各像元的加权邻域总变分似然函数取值,并进行区域生长分割,将矩形度和长宽比作为约束条件提取候选建筑物;然后,进行阴影自动提取;最后,利用数学形态学对阴影进行处理,计算处理后的阴影和候选建筑物之间的邻接关系得到建筑物,并用最小外接矩形对其边界进行拟合。为了验证所提算法的有效性,选取深圳市PLEIADES影像中9幅具有代表性的子影像进行实验。实验结果表明,所提方法的平均查准率和平均查全率分别达到97.71%和84.21%,与水平集和基于颜色不变性特征两种建筑物提取方法相比,在总体性能F1上具有10%以上的提高。

关键词: 高分辨率遥感影像, 势直方图函数, 邻域总变分, 形态学, 建筑物提取

Abstract: Concerning the problems of the low accuracy and high requirements for data in the existing building identification and extraction methods from high-resolution remotely sensed imagery, a new method based on Neighborhood Total Variation (NTV) and Potential Histogram Function (PHF) was proposed. Firstly, the value of weighted NTV likelihood function for each pixel of a remotely sensed imagery was calculated, the segmentation was done with region growing method, and the candidate buildings were selected from the segmentation results with the constraints of rectangular degree and aspect ratio. Then, the shadows were detected automatically. At last, shadows were processed with morphology operations. The buildings were extracted by computing the adjacency relationship of the processed shadows and candidate buildings, and the building boundaries were fitted with the minimum enclosing rectangle. For verifying the validity of the proposed method, nine representative sub-images were chosen from PLEIADES images covering Shenzhen for experiment. The experimental results show that, the average precision and recall of the proposed method are 97.71% and 84.21% for the object-based evaluation, and the proposed method has increased the overall performance F1by more than 10% compared with two other building extraction methods based on level set and color invariant feature.

Key words: high-resolution remotely sensed imagery, Potential Histogram Function (PHF), Neighborhood Total Variation (NTV), morphology, building extraction

中图分类号: