Extraction of residential area from high resolution images based on wavelet texture and primitive merging
HU Hualong1, XUE Wu1,2,3, QIN Zhiyuan1
1. Institute of Geospatial Information, Information Engineering University, Zhengzhou 450001, China;
2. State Key Laboratory of Geo-information Engineering, Xi'an 710054, China;
3. Key Laboratory of Mine Spatial Information Technologies of NASG, Henan Polytechnic University, Jiaozuo 454003, China
由于高分辨率全色影像(简称“高分影像”)中的信息高度细节化,再加上噪声的影响,会导致传统基于纹理特征的居民地提取方法效果不理想。为此,提出一种基于小波纹理和基元合并的居民地提取方法。首先,利用结合小波变换(wavelet transform,WT)的分形网络进化算法(fractal net evolution approach,FNEA)获取初始基元,并对基元的多尺度小波纹理进行分析;然后,在人工给定种子基元的基础上合并具有相似纹理的基元;最后,对基元合并的结果进行数学形态学修整,得到居民地区域。利用天绘一号(TH-1)全色影像对所提方法进行验证及对比分析的结果表明,该方法对高分影像中的街区式居民地可取得较高的提取精度和计算效率。
Due to the highly detailed information and noise in the high resolution panchromatic images, the results of traditional residential area extraction algorithms based on texture features are not satisfactory. To tackle this problem, the authors propose a method based on wavelet texture and primitive merging in this paper. For obtaining the initial primitives, the image was firstly segmented by fractal net evolution approach modified by the wavelet transform, and then the multi-scale wavelet texture features extraction method was directly applied to the irregular image primitives. Based on the artificially provided seed primitives, the algorithm merged the primitives with similar texture features and then applied morphological methods to the result of primitive merging. In the experiment, Mapping Satellite-1(TH-1) panchromatic images were used to validate the proposed method. The comparative analysis with other texture features-based methods shows that the proposed method could extract the street-block residential area from high resolution panchromatic images with a higher extraction accuracy and computational efficiency.
胡华龙, 薛武, 秦志远. 基于小波纹理和基元合并的高分影像居民地提取[J]. 国土资源遥感, 2017, 29(1): 21-28.
HU Hualong, XUE Wu, QIN Zhiyuan. Extraction of residential area from high resolution images based on wavelet texture and primitive merging. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(1): 21-28.
[1] 于博,王力,牛铮.基于中性集对北川羌族自治县新城人工建设用地的识别[J].国土资源遥感,2015,27(1):106-112.doi:10.6046/gtzyyg.2015.01.17. Yu B,Wang L,Niu Z.Analysis of built-up land detection in new Beichuan County based on neutrosophic set[J].Remote Sensing for Land and Resources,2015,27(1):106-112.doi:10.6046/gtzyyg.2015.01.17.
[2] 易凤佳,李仁东,常变蓉,等.长株潭地区建设用地扩张遥感时空特征分析[J].国土资源遥感,2015,27(2):160-166.doi:10.6046/gtzyyg.2015.02.25. Yi F J,Li R D,Chang B R,et al.Spatial-temporal features of construction land expansion in Changzhutan(Changsha-Zhuzhou-Xiangtan) area based on remote sensing[J].Remote Sensing for Land and Resources,2015,27(2):160-166.doi:10.6046/gtzyyg.2015.02.25.
[3] 杨存建,周成虎.TM影像的居民地信息提取方法研究[J].遥感学报,2000,4(2):146-150. Yang C J,Zhou C H.Extracting residential areas on the TM imagery[J].Journal of Remote Sensing,2000,4(2):146-150.
[4] Zha Y,Gao J,Ni S.Use of normalized difference built-up index in automatically mapping urban areas from TM imagery[J].International Journal of Remote Sensing,2003,24(3):583-594.
[5] Xu H.A new index for delineating built-up land features in satellite imagery[J].International Journal of Remote Sensing,2008,29(14):4269-4276.
[6] Pesaresi M,Gerhardinger A,Kayitakire F.A robust built-up area presence index by anisotropic rotation-invariant textural measure[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2008,1(3):180-192.
[7] Zhong P,Wang R S.A multiple conditional random fields ensemble model for urban area detection in remote sensing optical images[J].IEEE Transactions on Geoscience and Remote Sensing,2007,45(12):3978-3988.
[8] 金飞,张占睦,芮杰,等.基于树型小波变换和尺度共生矩阵的居民地提取[J].海洋测绘,2009,29(6):48-51. Jin F,Zhang Z M,Rui J,et al.Residential area extraction based on tree-structure wavelet and scale-based concurrent matrix[J].Hydrographic Surveying and Charting,2009,29(6):48-51.
[9] Hu X Y,Shen J J,Shan J,et al.Local edge distributions for detection of salient structure textures and objects[J].IEEE Geoscience and Remote Sensing Letters,2013,10(3):466-470.
[10] Unsalan C,Boyer K L.Classifying land development in high-resolution panchromatic satellite images using straight-line statistics[J].IEEE Transactions on Geoscience and Remote Sensing,2004,42(4):907-919.
[11] 陶超,邹峥嵘,丁晓利.利用角点进行高分辨率遥感影像居民地检测方法[J].测绘学报,2014,43(2):164-169,192. Tao C,Zou Z R,Ding X L.Residential area detection from high-resolution remote sensing imagery using corner distribution[J].Acta Geodaetica et Cartographica Sinica,2014,43(2):164-169,192.
[12] Baatz M,Schäpe A.Multiresolution segmentation:An optimization approach for high quality multi-scale image segmentation[C]//Strobl J,Blaschke T,Griesebner G.Angewandte geographische infor-mationsverarbeitung XII:beiträge zum AGIT-symposium.Salzburg:Herbert Wichmann Verlag,2000:12-23.
[13] 曹建农,王平禄,董昱威.高分辨率遥感影像上居民地自动提取方法[J].武汉大学学报:信息科学版,2014,39(7):831-837. Cao J N,Wang P L,Dong Y W.Automatic extraction technique of residential areas in high resolution remote sensing image[J].Geomatics and Information Science of Wuhan University,2014,39(7):831-837.
[14] 黄昕.高分辨率遥感影像多尺度纹理、形状特征提取与面向对象分类研究[D].武汉:武汉大学,2009:60-65. Huang X.Multiscale Texture and Shape Feature Extraction and Object-Oriented Classification for Very High Resolution Remotely Sensed Imagery[D].Wuhan:Wuhan University,2009:60-65.
[15] Achanta R,Shaji A,Smith K,et al.SLIC superpixels compared to state-of-the-art superpixel methods[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(11):2274-2282.
[16] 刘彬,王朝英,侯志强.融合聚类和分级区域合并的彩色图像分割方法[J].计算机工程与应用,2011,47(30):202-205. Liu B,Wang Z Y,Hou Z Q.Color image segmentation algorithm using clustering and hierarchical region merge[J].Computer Engineering and Applications,2011,47(30):202-205.
[17] Tong H J,Maxwell T,Zhang Y,et al.A supervised and fuzzy-based approach to determine optimal multi-resolution image segmentation parameters[J].Photogrammetric Engineering & Remote Sensing,2012,78(10):1029-1044.
[18] Haris K,Efstratiadis S N,Maglaveras N,et al.Hybrid image segmentation using watersheds and fast region merging[J].IEEE Transactions on Image Processing,1998,7(12):1684-1699.
[19] 李向辉,陈一祥,王海斌,等.基于Gabor滤波和局部特征点密度的居民区提取[J].国土资源遥感,2015,27(3):59-64.doi:10.6046/gtzyyg.2015.03.11. Li X H,Chen Y X,Wang H B,et al.Urban area detection based on Gabor filtering and density of local feature points[J].Remote Sensing for Land and Resources,2015,27(3):59-64.doi:10.6046/gtzyyg.2015.03.11.