[1]白鹤,郑丽颖.基于SIFT和三角网格的VHR建筑物检测技术[J].应用科技,2017,(06):48-52.[doi:10.11991/yykj.201610001]
 BAI He,ZHENG Liying.Building detection from VHR based on SIFT and Delaunay triangulation[J].yykj,2017,(06):48-52.[doi:10.11991/yykj.201610001]
点击复制

基于SIFT和三角网格的VHR建筑物检测技术(/HTML)
分享到:

《应用科技》[ISSN:1009-671X/CN:23-1191/U]

卷:
期数:
2017年06期
页码:
48-52
栏目:
计算机技术与应用
出版日期:
2017-12-05

文章信息/Info

Title:
Building detection from VHR based on SIFT and Delaunay triangulation
作者:
白鹤 郑丽颖
哈尔滨工程大学 计算机视觉与听觉实验室, 黑龙江 哈尔滨 150001
Author(s):
BAI He ZHENG Liying
Computer Vision and Audition Lab, Harbin Engineering University, Harbin 150001, China
关键词:
遥感图像建筑物检测SIFT算法关键点欧氏距离Delaunay三角剖分匹配点配准精度
Keywords:
remote sensing imagebuilding registrationSIFT algorithmkey pointsDelaunay triangulationEuclidean distancematched pointsregistration accuracy
分类号:
TP751.1
DOI:
10.11991/yykj.201610001
文献标志码:
A
摘要:
传统尺度不变特征变换(scale-invariant feature transform,SIFT)算法的误配准问题导致基于该算法的建筑物检测率较低,因此提出一种改进的高分辨率(very high resolution,VHR)遥感卫星图像中建筑物的检测方法。首先通过改进传统的SIFT配准方法,使其能够更加准确地描述VHR遥感卫星图像中的建筑物信息,之后通过欧氏距离获得2幅图像的初始匹配点集,然后将配准后的一幅图像中所得到的配准点作为Delaunay三角剖分的初始点集,根据Delaunay三角剖分特性,剔除SIFT算法中误匹配的特征点,得到最终的结果。实验结果表明,研究所提出的算法可以有效地检测出一幅VHR遥感卫星图像中的建筑物信息,在时间效率、配准精度、建筑物的检测普遍性上,都能得到很好的预期效果。
Abstract:
The mis-registration problem of traditional scale-invariant feature transform (SIFT) algorithm results in a low detection rate of buildings based on this algorithm. Therefore, this paper proposed an improved detection method of buildings in very high resolution (VHR) satellite imagery. First, the traditional SIFT registration method was improved to characterize the building information in VHR remote sensing satellite images. Then, the set of initial matching points of two images could be obtained with Euclidean distance, followed by taking matched registration points in an image as the initial point set of the Delaunay triangulation. Finally, the result was got by removing mismatched feature points according to Delaunay triangulation properties. Experimental results show that the algorithm proposed in this paper can effectively detect the building information in a VHR remote sensing satellite image. Moreover, the proposed algorithm performs well in terms of time efficiency, registration accuracy and universality in detection of buildings.

参考文献/References:

[1] 杨益军, 赵荣椿, 汪文秉. 航空图像中人工建筑物的自动检测[J]. 计算机工程, 2002, 28(8): 20-22.
[2] HUA Tao, ZHAO Yong. An novel location technology based on SIFT features matching[J]. Journal of astronautic metrology and measurement, 2014, 125(1): 3385-3388.
[3] 雷小群, 李芳芳, 肖本林. 一种基于改进SIFT算法的遥感影像配准方法[J]. 测绘科学, 2010, 35(3): 143-145.
[4] TAO Chao, TAN Yihua, CAI Huajie, et al. Airport detection from large IKONOS images[J]. IEEE geoscience and remote sensing letters, 2011, 8(1): 128-132.
[5] RASIMMAHDI A, RABIEE H R. RASIM: a novel rotation and scale invariant matching of local image interest point[J]. IEEE geoscience and remote sensing letters, 2011, 20(12): 3580-3591.
[6] 刘佳, 傅卫平, 王雯, 等. 基于改进SIFT算法的图像匹配[J]. 仪器仪表学报, 2013, 34(5): 1108-1112.
[7] 丁永祥, 夏巨湛, 王英, 等. 任意多边形的Delaunay三角剖分[J]. 计算机学报, 1994, 17(4): 270-275.
[8] 万琳. 基于三角网格的图像表示方法研究[D]. 武汉: 华中科技大学, 2009: 1-92.
[9] 田军委, 程钢. 改进Delaunay三角剖分算法[J]. 西安工业大学学报, 2011, 31(4): 334-338.
[10] 基于Bowyer-Watson三角网生成算法的研究[J]. 计算机工程与应用, 2013, 49(6): 198-200.
[11] 贺强, 张树生, 白晓亮, 等. 基于邻域相似性的三角网格光顺算法[J]. 计算机科学, 2010, 37(3): 289-291.
[12] 时永杰, 宋杰, 徐丹. 基于等边三角形网格化的二维图像变形[C]//中国计算机图形学大会. 昆明, 中国, 2012: 139-145.

备注/Memo

备注/Memo:
收稿日期:2016-10-25。
基金项目:国家自然科学基金项目(61771155)
作者简介:白鹤(1991-),男,硕士研究生;郑丽颖(1976-),女,教授
通讯作者:郑丽颖,E-mail:zhengliying@hrbeu.edu.cn
更新日期/Last Update: 2018-01-06