Built-up area detection from high resolution remote sensing images using geometric features

Junjun LI; Jiannong CAO; Yingying ZHU; Beibei CHENG

doi:10.11834/jrs.20208506

Chinese Satellites | Views : 0 下载量: 94 CSCD: 6 更多指标

PDF
Export
Share
Collection
Album

Built-up area detection from high resolution remote sensing images using geometric features
Vol. 24, Issue 3, Pages: 233-244(2020)
Published： 07 March 2020 ，
DOI： 10.11834/jrs.20208506

扫描看全文

李军军,曹建农,朱莹莹,程贝贝.2020.高分辨率遥感影像建筑区域局部几何特征提取.遥感学报,24(3): 233-244

Li J J, Cao J N, Zhu Y Y and Cheng B B. 2020. Built-up area detection from high resolution remote sensing images using geometric features. Journal of Remote Sensing（Chinese）, 24(3): 233-244
李军军,曹建农,朱莹莹,程贝贝.2020.高分辨率遥感影像建筑区域局部几何特征提取.遥感学报,24(3): 233-244 DOI： 10.11834/jrs.20208506.

Li J J, Cao J N, Zhu Y Y and Cheng B B. 2020. Built-up area detection from high resolution remote sensing images using geometric features. Journal of Remote Sensing（Chinese）, 24(3): 233-244 DOI： 10.11834/jrs.20208506.

摘要

及时准确地获取城市建筑区域的空间分布及其变化信息对于城市规划、空间地理数据库建设及区域社会经济分析具有重要意义。本文提出一种基于多尺度Gabor变换和感知聚类方法即张量投票 TV（Tensor Voting）相结合的自适应局部几何不变特征检测方法，并将其应用于高空间分辨率遥感影像建筑区域提取。首先，考虑到高分辨率遥感影像复杂的几何结构特征，使用Gabor滤波器组对影像进行多尺度多方向变换检测奇异性特征。然后，在感知聚类框架下，根据张量投票理论将不同方向子带系数位置编码为相应的二阶对称方向张量，为了突出影像几何特征，对不同尺度、不同方向子带中任意像素位置方向张量使用滤波器响应系数加权并求和完成多尺度特征融合。再次，对张量特征分解得到点结构与线结构显著性图并使用非极大抑制提取相应角点和曲线等局部几何特征，同时生成约束准则筛选角点以确定建筑物坐标。最后，利用概率密度估计结合局部角点特征生成全局概率密度场描述影像中像素从属于建筑目标的概率，并使用最大类间方差法（Otsu）阈值分割自动提取居民地多边形区域。使用分辨率分别为0.49 m、0.98 m的Google Earth及0.8 m的高分二号等影像数据集进行实验，实验结果表明本文方法相对于已有的Harris和HSCD点检测算法，在建筑区域提取质量上（Quality）上分别提高了4.79%，5.96%；1.47%，3.76%和1.91%，4.08%。

Abstract

Based on characteristic of High Spatial Resolution (HSR) image

an adaptive local geometric invariant feature extraction method based on Gabor transform and Tensor Voting (TV) is proposed and applied to building area extraction from HSR remote sensing images. First

image geometric features are analyzed. Second

the feasibility of extracting built-up area using local feature points and probability density estimation are determined. This study provides specific methods and steps. First

considering the abundant geometric features of high spatial resolution remote sensing images

multi-scale and multi-direction Gabor filter banks are adopted in detecting the singularity of images contain building area. In order to extract edge information of buildings

only real part Gabor coefficients are used. Meanwhile

we also measured the influence of Gabor kernels of different size on geometric feature extraction experiments

and the optimal scale parameter intervals for geometric feature extraction of remote sensing images with different spatial resolutions are thus determined. Second

it is a fact that the response of Gabor filter at each pixel is a measure for orientation certainty

thus

we introduce the orientation tensor which represents an ideal direction in the direction of the unit vector perpendicular to frequency. By weighting the orientation tensor with Gabor coefficients ans summing over it to complete the information fusion

the resulting tensor givens an estimate for local orientation and orientation uncertainty at image position. The tensors are then used as an initial estimate for global context refinement using tensor voting and the points are classified based on the their likelihoods of being part of a feature type

non-maximal suppression is used to extract geometric features. A key advantage of combining the Gabor filtering and tensor voting is that it eliminates the need for any thresholds therefore removing any data dependencies. In order to achieve a reliable extraction of local invariant feature such as corners from built-up area

three criterions are further proposed to refine the first stage result. Finally

each local building corner indicates a building be detected in image. However

only one of them is not sufficient alone to detecting a building. In fact

the more local points a buildings has

the more probable its detection becomes. Based on that fact

a probability density estimate method is generated to describe the probability that the pixel belongs to the building area

and the Otsu method is used to automatically extract the polygon area of the residential area. Experiments were carried out using image data sets such as Google and GF-2 with resolution higher than 1 meter

results showing that the proposed method can achieve higher accuracy in building area detection compared with the state-of-the-art corner detection algorithm such as Harris corner and High-speed corner detect method.

关键词

高分辨率遥感影像几何特征提取建筑区域检测Gabor变换张量投票概率密度场高分二号

Keywords

high spatial resolution remote sensing imagegeometric feature extractionbuilt-up area detectionGabor transformtensor votingprobability density fieldGF-2

references

Cheng Y X, Qin K, Zhang Y and Yuan Y. 2017. A residential area extraction method for high resolution remote sensing imagery by using visual saliency and perceptual organization. Acta Geodaetica et Cartographica Sinica, 46(12): 1959-1968

陈一祥, 秦昆, 张晔, 袁媛. 2017. 视觉显著性与知觉组织相结合的高分影像居民地提取方法. 测绘学报, 46(12): 1959-1968 [DOI: 10.11947/j.AGCS.2017.20170176http://dx.doi.org/10.11947/j.AGCS.2017.20170176]

Bhatti S S and Tripathi N K. 2014. Built-up area extraction using landsat 8 OLI imagery. GIScience and Remote Sensing, 51(4): 445-467 [DOI: 10.1080/15481603.2014.939539http://dx.doi.org/10.1080/15481603.2014.939539]

Zhang J, Li P J and Xu H Q. 2013. Urban built-up area extraction using combined spectral information and multivariate texture//Proceedings of 2013 IEEE International Geoscience and Remote Sensing Symposium. Melbourne, VIC, Australia: IEEE: 4249-4252 [DOI: 10.1109/IGARSS.2013.6723772http://dx.doi.org/10.1109/IGARSS.2013.6723772]

You Y F, Wang S Y, Wang B, Ma Y X, Sheng M, Liu W H, Xiao L. 2019. Study on hierarchical building extraction from high resolution remote sensing imagery, 23(1):125-136

游永发,王思远,王斌,马元旭,申明,刘卫华,肖琳.2019.高分辨率遥感影像建筑物分级提取.遥感学报,23(1):125-136

Li Y S, Tan Y H, Deng J J, Wen Q and Tian J W. 2015. cauchy graph embedding optimization for built-Up areas detection from high-resolution remote sensing images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(5): 2078-2096 [DOI: 10.1109/JSTARS.2015.2394504http://dx.doi.org/10.1109/JSTARS.2015.2394504]

Tao C, Tan Y H, Zou Z R and Tian J W. 2013. Unsupervised detection of built-up areas from multiple high-resolution remote sensing images. IEEE Geoscience and Remote Sensing Letters, 10(6): 1300-1304 [DOI: 10.1109/LGRS.2013.2237751http://dx.doi.org/10.1109/LGRS.2013.2237751]

Li P C, Xing S, Xu Q, Zhou Y, Liu Z Q, Zhang Y, Geng X. 2014. An automated approach for complex shape building reconstruction with key point detection. Journal of Remote Sensing, 18(6):1237-1246

李鹏程,邢帅,徐青,周杨,刘志青,张艳,耿迅.2014.关键点检测的复杂建筑物模型自动重建.遥感学报,18(6):1237-1246

Liu Y B, Zhang Z X, Zhong R F, Chen D, Ke Y H, Peethambaran J, Chen C Q and Sun L. 2018. Multilevel building detection framework in remote sensing images based on convolutional neural networks. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(10): 3688-3700 [DOI: 10.1109/JSTARS.2018. 2866284http://dx.doi.org/10.1109/JSTARS.2018. 2866284]

Zhao L J, Qin Y L, Gao G and Kuang G Y. 2009. Detection of built-up areas from high-resolution SAR images using the GLCM textural analysis. Journal of Remote Sensing, 13(3): 483-490 (赵凌君, 秦玉亮, 高贵, 匡纲要. 2009. 利用GLCM纹理分析的高分辨率SAR图像建筑区检测[J].遥感学报, 13(3): 483-490

[DOI: 10.3321/j.issn:1007-4619. 2009.03.011]

Pesaresi M, Gerhardinger A and Kayitakire F. 2008. A robust built-up area presence index by anisotropic rotation-invariant textural measure. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 1(3): 180-192 [DOI: 10.1109/JSTARS.2008.2002869http://dx.doi.org/10.1109/JSTARS.2008.2002869]

Krishnamachari S and Chellappa R. 1996. Delineating buildings by grouping lines with mrfs. IEEE Transactions on Image Processing, 5(1): 164-168 [DOI: 10.1109/83.481683http://dx.doi.org/10.1109/83.481683]

Su W, Li J, Chen Y H, Liu Z G, Zhang J S, Low T M, Suppiah I and Hashim S A M. 2008. Textural and local spatial statistics for the object-oriented classification of urban areas using high resolution imagery. International Journal of Remote Sensing, 29(11): 3105-3117 [DOI: 10.1080/01431160701469016http://dx.doi.org/10.1080/01431160701469016]

Sirmacek B and Unsalan C. 2009. Urban-area and building detection using SIFT keypoints and graph theory. IEEE Transactions on Geoscience and Remote Sensing, 47(4): 1156-1167 [DOI: 10.1109/TGRS.2008.2008440http://dx.doi.org/10.1109/TGRS.2008.2008440]

Sirmacek B and Unsalan C. 2010. Urban area detection using local feature points and spatial voting. IEEE Geoscience and Remote Sensing Letters, 7(1): 146-150 [DOI: 10.1109/LGRS.2009.2028744http://dx.doi.org/10.1109/LGRS.2009.2028744]

Sirmacek B and Unsalan C. 2011. A probabilistic framework to detect buildings in aerial and satellite images. IEEE Transactions on Geoscience and Remote Sensing, 49(1): 211-221 [DOI: 10.1109/TGRS.2010.2053713http://dx.doi.org/10.1109/TGRS.2010.2053713]

Tao C, Zou Z R and Ding X L. 2014. Residential area detection from high-resolution remote sensing imagery using corner distribution. Acta Geodaetica et Cartographica Sinica, 43(2): 164-169, 192

陶超, 邹峥嵘, 丁晓利. 2014. 利用角点进行高分辨率遥感影像居民地检测方法. 测绘学报, 43(2): 164-169, 192 [DOI: 10.13485/j.cnki.11-2089. 2014.0024http://dx.doi.org/10.13485/j.cnki.11-2089. 2014.0024]

M. Idrissa, V. Lacroix, A. Hincq, H. Bruynseels, and O. Swartenbroekx,“SPOT5 images for urbanization detection,

” in Proc. Adv. Concepts Intell.Vis. Syst., 2004.

Medioni G, Lee M S and Tang C K. 2000. A Computational Framework for Segmentation and Grouping. The Netherlands: Elsevier Science

Kim H S, Choi H K and Lee K H. 2009. Feature detection of triangular meshes based on tensor voting theory. Computer-Aided Design, 41(1): 47-58 [DOI: 10.1016/j.cad.2008.12.003http://dx.doi.org/10.1016/j.cad.2008.12.003]

Moreno R, Garcia M A and Puig D. 2010. Robust color image segmentation through tensor voting//Proceedings of the 20th International Conference on Pattern Recognition. Istanbul, Turkey: IEEE: 3372-3375 [DOI: 10.1109/ICPR. 2010.823http://dx.doi.org/10.1109/ICPR. 2010.823]

Poullis C and You S Y. 2010. Delineation and geometric modeling of road networks. ISPRS Journal of Photogrammetry and Remote Sensing, 65(2): 165-181 [DOI: 10.1016/j.isprsjprs.2009.10.004http://dx.doi.org/10.1016/j.isprsjprs.2009.10.004]

Harris C and Stephens M. 1988. A combined corner and edge detector//Proceedings of the Alvey Vision Conference. Manchester: Alvety Vision Club [DOI: 10.5244/C.2.23http://dx.doi.org/10.5244/C.2.23]

Wiedemann C, Heipke C, Mayer H and Jamet O. 1998. Empirical evaluation of automatically extracted road axes//Proceedings of the 9th Australasian Remote Sensing Photogrammetry Conference. Sydney: The University of New South Wales: 172-187

Rosten E and Drummond T. 2006. Machine learning for high-speed corner detection//Proceedings of the 9th European Conference on Computer Vision. Graz, Austria: Springer: 430-443 [DOI: 10.1007/11744023_34http://dx.doi.org/10.1007/11744023_34]

Alert me when the article has been cited

提交

Mapping high-resolution mangrove forests in China using GF-2 imagery under the tide

Combination of deep learning and vegetation index for coastal wetland mapping using GF-2 remote sensing images

Global-Local-Aware conditional random fields based building extraction for high spatial resolution remote sensing images

Extracting winter wheat spatial distribution information from GF-2 image

Study on urban surface water extraction from heterogeneous environments using GF-2 remotely sensed images