结合方向梯度和支持向量机的立面窗户提取方法A method for extracting facade windows combined with HOG operator and SVM
张士诚,李新萍,盛奇
摘要(Abstract):
针对建筑物立面的窗户提取问题,该文采用结合方向梯度特征、机器学习以及窗户规则性排列特征的方法:首先利用一个窗户模板的HOG特征,将模板与图像中的矩阵进行相关系数匹配,提取出正负样本;通过使用基于HSI色彩模型的颜色分布直方图和梯度方向直方图的方法对窗户特征进行提取,得到样本训练的SVM分类器,通过SVM识别所有窗户矩阵,根据矩阵灰度的相关条件对图像窗户目标筛选;再使用聚类求平均的方法获得精确的位置;最后根据建筑物立面窗户之间的规则排列特性作进一步筛选和补充。结果表明,该方法可以在极少人工处理的基础上有效识别大部分窗户结构,为建筑物精细化建模提供基础。
关键词(KeyWords): 特征提取;HOG算子;模板匹配;支持向量机
基金项目(Foundation): 武汉大学地球空间环境与大地测量教育部重点实验室开放基金资助项目(18-01-02);; 东华理工大学江西省数字国土重点实验室开放研究基金资助项目(DLLJ201801)
作者(Author): 张士诚,李新萍,盛奇
DOI: 10.16251/j.cnki.1009-2307.2020.09.024
参考文献(References):
- [1] 杨必胜,董震,魏征,等.从车载激光扫描数据中提取复杂建筑物立面的方法[J].测绘学报,2013,42(3):411-417.(YANG Bisheng,DONG Zhen,WEI Zheng,et al.Extracting complex building facades from mobile laser scanning data[J].Acta Geodaetica et Cartographica Sinica,2013,42(3):411-417.)
- [2] 龚健雅,崔婷婷,单杰,等.利用车载移动测量数据的建筑物立面建模方法[J].武汉大学学报(信息科学版),2015,40(9):1137-1143.(GONG Jianya,CUI Tingting,SHAN Jie,et al.A survey on facade modeling using LiDAR point clouds and image sequences collected by mobile mapping systems[J].Geomatics and Information Science of Wuhan University,2015,40(9):1137-1 143.)
- [3] 邵磊,董广军,于英,等.车载激光扫描数据中建筑物立面快速提取[J].地球信息科学学报,2018,20(4):462-470.(SHAO Lei,DONG Guangjun,YU Ying,et al.A fast method of building extraction from mobile LiDAR scanning data[J].Journal of Geo-Information Science,2018,20(4):462-470.)
- [4] MAYER H,REZNIK S.Building facade interpretation from image sequences[J]ISPRS Journal of Photogrammetry and Remote Sensing,2007,61(6):371-380.
- [5] IWASZCZUK D,HOEGNER L,STILLA U.Detection of windows in IR building textures using masked correlation[C]//ISPRS Conference on Photogrammetric Image Analysis.Berlin,Heidelberg:Springer,2011:133-146.
- [6] SIRMACEK B,HOEGNER L,STILLA U.Detection of windows and doors from thermal images by grouping geometrical features[C]//2011 Joint Urban Remote Sensing Event.[S.l.]:IEEE,2011:133-136.
- [7] LEE S C,NEVATIA R.Extraction and integration of window in a 3D building model from ground view images[C]//Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington,DC,USA:IEEE,2004:2.
- [8] RECKY M,LEBERL F.Windows detection using k-means in cie-lab color space[C]//2010 20th International Conference on Pattern Recognition.Istanbul,Turkey:IEEE,2010:356-359.
- [9] ALI H,SEIFERT C,JINDAL N,et al.Window detection in facades[C]//14th International Conference on Image Analysis and Processing (ICIAP 2007).Modena,Italy:IEEE,2007:837-842.
- [10] 王曦.基于语义的建筑物立面窗户检测算法研究及实现[D].北京:北京大学,2010.(WANG Xi.Research and implementation of semantic based facade window detection algorithm for buildings[D].Beijing:Beijing University,2010.)
- [11] 胡峰松,朱浩.基于HSI颜色空间和行扫描的车牌定位算法[J].计算机工程与设计,2015,36(4):977-982.(HU Fengsong,ZHU Hao.License plate location algorithm based on HSI color space and line scan[J].Computer Engineering and Design,2015,36(4):977-982.)
- [12] MIKOLAJCZYK K,SCHMID C.A performance evaluation of local descriptors[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630.
- [13] LOWE D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
- [14] 唐永鹤,卢焕章.基于灰度差分不变量的快速局部特征描述算法[J].光学精密工程,2012,2(20):447-454.(TANG Yonghe,LU Huanzhang.Fast local feature description algorithm based on gray difference invariant[J].Optical and Precision Engineering,2012,2(20):447-454.)
- [15] DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.San Diego,CA,USA:IEEE,2005.
- [16] 马岱农,桑海峰.基于边缘方向直方图的印鉴鉴别方法[J].辽宁科技大学学报,2010,33(3):258-261.(MA Dainong,SANG Haifeng.Method of seal identification with edge direction histogram[J].Journal of University of Science and Technology Liaoning,2010,33(3):258-261.)
- [17] 陈龙,潘志明,毛庆洲,等.利用HOG-LBP自适应融合特征实现禁令交通标志检测[J].武汉大学学报(信息科学版),2013,38(2):191-194.(CHEN Long,PAN Zhiming,MAO Qingzhou,et al.Using HOG-LBP adaptive fusion feature to realize ban traffic sign detection[J].Geomatics and Information Science of Wuhan University,2013,38(2):191-194.)
- [18] 徐渊,许晓亮,李才年,等.结合SVM分类器与HOG特征提取的行人检测[J].计算机工程,2016,42(1):56-60,65(XU Yuan,XU Xiaoliang,LI Cainian,et al.Pedestrian detection combining with SVM classifier and HOG feature extraction[J].Computer Engineering,2016,42(1):56-60,65)
- [19] 贾永红.数字图像处理[M].3版.武汉:武汉大学出版社,2015.(JIA Yonghong.Digital image processing[M].3rd ed.Wuhan:Wuhan University Press,2015.)
- [20] 周柯.基于HOG特征的图像人体检测技术的研究与实现[D].武汉:华中科技大学,2008.(ZHOU Ke.Research and implementation of HOG based human detection in image[D].Wuhan:Huazhong University of Science and Technology,2008.)