基准线约束的建筑物立面重复纹理检测

doi:10.13474/j.cnki.11-2246.2023.0071

测绘通报 ›› 2023, Vol. 0 ›› Issue (3): 49-54.doi: 10.13474/j.cnki.11-2246.2023.0071

基准线约束的建筑物立面重复纹理检测

贾琛¹, 刘欣怡¹, 张永军¹, 祝宪章¹, 任维成², 何庆², 冯幼贵²

1. 武汉大学遥感信息工程学院, 湖北武汉 430079;
2. 山东正元航空遥感技术有限公司, 山东济南 250000

收稿日期:2022-04-20 修回日期:2023-02-06 发布日期:2023-04-04
通讯作者: 刘欣怡。E-mail:liuxy0319@whu.edu.cn
作者简介:贾琛(1999-),男,硕士生,主要从事三维建模与纹理提取的研究工作。E-mail:1294184482@qq.com
基金资助:
国家自然科学基金（42201474；41871368）

Repetitive texture detection of building facade constrained by baseline

JIA Chen¹, LIU Xinyi¹, ZHANG Yongjun¹, ZHU Xianzhang¹, REN Weicheng², HE Qing², FENG Yougui²

1. School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China;
2. Shandong Zhengyuan Aerial Remote Sensing Technology Co., Ltd., Jinan 250000, China

Received:2022-04-20 Revised:2023-02-06 Published:2023-04-04

摘要/Abstract

摘要： 重复纹理是立面中极为常见的特征之一，从立面图像中自动检测重复纹理结构是建筑物立面分析的一个重要环节。本文提出了一种基准线约束的纹理检测方法，以自动检测重复对象的位置和尺寸。该方法首先采用贝叶斯自适应超像素分割算法构建出超像素邻接图，计算色差后，对墙体进行分离获得候选对象；然后，计算得到候选对象的外接矩形，并从原图中提取出直线段对外接矩形进行约束；最后，基于建筑物立面结构的先验知识对建筑物立面纹理进行修复。试验结果表明，本文方法在检测几何形状为矩形纹理时，可实现对纹理位置和尺寸信息的准确检测，以及被遮挡重复对象的有效修复。

关键词: 超像素, 色差, 线约束, 重复纹理检测, 纹理修复

Abstract: Repeated texture is one of the most important features in building facades. How to automatically detect repeating textures from facade images is an important part of building facade analysis. This paper proposes a new Baseline Constrained Texture Detection Method to automatically detect the exact location and size of repeating objects. The method first uses Bayesian adaptive superpixel segmentation to construct a superpixel adjacency map, and then separates the wall by calculating chromatic aberration to obtain candidate objects. Secondly, extract straight lines from the original image, and perform preprocessing such as normal classification and line segment clustering on the obtained straight lines. Finally, texture repair is performed based on prior knowledge of building facade structure. The experimental results show that the proposed method can effectively detect the position and size information of repeated textures when detecting repeated textures whose geometric shapes are rectangles, and repair the occluded repeated objects.

Key words: superpixel, chromatic aberration, baseline constraint, repeated texture detection, texture repair

中图分类号:

P237

贾琛, 刘欣怡, 张永军, 祝宪章, 任维成, 何庆, 冯幼贵. 基准线约束的建筑物立面重复纹理检测[J]. 测绘通报, 2023, 0(3): 49-54.

JIA Chen, LIU Xinyi, ZHANG Yongjun, ZHU Xianzhang, REN Weicheng, HE Qing, FENG Yougui. Repetitive texture detection of building facade constrained by baseline[J]. Bulletin of Surveying and Mapping, 2023, 0(3): 49-54.

参考文献

[1] 张永军, 张祖勋, 龚健雅.天空地多源遥感数据的广义摄影测量学[J].测绘学报, 2021, 50(1):1-11.
[2] ZHAO P, FANG T, XIAO J, et al. Rectilinear parsing of architecture in urban environment[C]//Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.San Francisco:IEEE, 2010:342-349.
[3] 严少华, 陈敏, 赵怡涛, 等. 局部结构约束下的宽基线影像直线特征匹配[J]. 测绘通报, 2020(5):51-54.
[4] XIAO H F, MENG G F, WANG L F, et al.. Facade repetition detection in a fronto-parallel view with fiducial lines extraction[J]. Neurocomputing, 2018, 273:435-447.
[5] WANG Yuefeng, FAN Hongchao, ZHOU Guoqing. Reconstructing facade semantic models using hierarchical topological graphs[J]. Transactions in GIS, 2020, 24(4):1073-1097.
[6] PARK M, BROCKLEHURST K, COLLINS R T, et al. Deformed lattice detection in real-world images using mean-shift belief propagation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(10):1804-1816.
[7] COHEN A, OSWALD M R, LIU Yanxi, et al. Symmetry-aware façade parsing with occlusions[C]//Proceedings of 2018 International Conference on 3D Vision (3DV).Qingdao:IEEE, 2018:393-401.
[8] MVLLER P, ZENG Gang, WONKA P, et al. Image-based procedural modeling of facades[J].ACM Transactions on Graphics, 2007, 26(3):1-9.
[9] Yongzhi, Wang. Accurate facade feature extraction method for buildings from three-dimensional point cloud data considering structural information[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 139:146-153.
[10] ALEGRE F, DELLAERT F. A probabilistic approach to the semantic interpretation of building facades[EB/OL].[2022-03-12].-s://www.researchgate.net/publication/27521955_A_Probabilistic_Approach_to_the_Semantic_Interpretation_of_Building_Facades.
[11] TYLE AČU1 EK R, ŠÁRA R. A weak structure model for regular pattern recognition applied to facade images[C]//Proceedings of the 10th Asian conference on Computer vision-Volume Part I. Queenstown, New Zealand:ACM, 2010:450-463.
[12] TEBOUL O, KOKKINOS I, SIMON L, et al. Shape grammar parsing via reinforcement learning[C]//Proceedings of 2011 CVPR.Colorado Springs, CO:IEEE, 2011:2273-2280.
[13] BECKER S. Generation and application of rules for quality dependent façade reconstruction[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2009, 64(6):640-653.
[14] MATHIAS M, MARTINOVIĆ A, VAN GOOL L. ATLAS:a three-layered approach to facade parsing[J]. International Journal of Computer Vision, 2016, 118(1):22-48.
[15] UZIEL R, RONEN M, FREIFELD O. Bayesian adaptive superpixel segmentation[C]//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul, Korea (South):IEEE, 2020:8469-8478.
[16] SHARMA G, WU W, DALAL E N. The CIEDE2000 color-difference formula:implementation notes, supplementary test data, and mathematical observations[J]. Color Research & Application, 2005, 30(1):21-30.
[17] 张永军, 万一, 史文中, 等. 多源卫星影像的摄影测量遥感智能处理技术框架与初步实践[J]. 测绘学报, 2021, 50(8):1068-1083.
[18] 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.
[19] GROMPONE VON GIOI R, JAKUBOWICZ J, MOREL J M, et al. LSD:a fast line segment detector with a false detection control[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(4):722-732.

基准线约束的建筑物立面重复纹理检测

Repetitive texture detection of building facade constrained by baseline

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	宗慧琳, 袁希平, 甘淑, 张晓伦, 梁昌献, 赵振峰. 改进AKAZE算法的泥石流区无人机影像特征匹配[J]. 测绘通报, 2023, 0(2): 91-96,103.
[2]	张佳宝, 谢福鼎, 金翠. 基于超像素图卷积网络的高光谱图像分类[J]. 测绘通报, 2023, 0(1): 84-87.
[3]	卓广平, 张俊花. 基于几何约束与局部描述的航空影像直线匹配[J]. 测绘通报, 2022, 0(3): 60-64.
[4]	杨景玉, 贾多科, 王阳萍. 基于超像素分割与CRF的高分辨率遥感影像变化检测[J]. 测绘通报, 2022, 0(2): 25-30,49.
[5]	刘海飞, 杨敏华, 王晶, 徐刚, 陈杰. 利用结构面对象的高分遥感影像建筑物变化检测[J]. 测绘通报, 2021, 0(6): 16-20.
[6]	聂倩, 七珂珂, 赵艳福. 融入超像素分割的高分辨率影像面向对象分类[J]. 测绘通报, 2021, 0(6): 44-49.
[7]	王挺, 陈超然, 彭梦圆, 黄尔双, 黄霞. POS辅助和核线约束的倾斜影像匹配方法[J]. 测绘通报, 2021, 0(5): 91-95.
[8]	陈利燕, 林鸿, 吴健华. 融合随机森林和超像素分割的建筑物自动提取[J]. 测绘通报, 2021, 0(2): 49-53.
[9]	刘霞, 郭亚男. 基于随机森林的遥感影像变化检测[J]. 测绘通报, 2020, 0(5): 16-20.
[10]	梁雪萍, 薛东剑, 贾诗超. 超像素在多极化SAR数据分类中的应用——以ALOS PALSAR为例[J]. 测绘通报, 2020, 0(5): 107-110.
[11]	徐启恒, 黄滢冰, 陈洋. 结合超像素和卷积神经网络的国产高分辨率遥感影像云检测方法[J]. 测绘通报, 2019, 0(1): 50-55.
[12]	王晓红, 邓仕雄, 何志伟, 曹留霞, 闫星光. 结合SURF算法和单应性矩阵的无人机影像匹配[J]. 测绘通报, 2018, 0(7): 38-42.
[13]	王竞雪, 张雪. 结合几何约束和梯度描述子的直线段匹配[J]. 测绘通报, 2018, 0(5): 29-34.
[14]	肖明虹, 冯文卿, 眭海刚. 超像素分割和多方法融合的遥感影像变化检测方法[J]. 测绘通报, 2018, 0(10): 93-97,121.
[15]	谢洪, 吴博义, 龚珣, 王奕丹. POS辅助下的车载序列影像匹配[J]. 测绘通报, 2017, 0(4): 44-48.