Automatic Building Rooftop Extraction From Aerial Images via Hierarchical RGB-D Priors

被引:36
作者
Xu, Shibiao [1 ]
Pan, Xingjia [1 ]
Li, Er [1 ]
Wu, Baoyuan [2 ]
Bu, Shuhui [3 ]
Dong, Weiming [1 ]
Xiang, Shiming [1 ]
Zhang, Xiaopeng [1 ]
机构
[1] Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
[2] Tencent AI Lab, Shenzhen 518000, Peoples R China
[3] Northwestern Polytech Univ, Sch Aeronaut, Xian 710072, Shaanxi, Peoples R China
来源
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2018年 / 56卷 / 12期
基金
中国国家自然科学基金;
关键词
High-order conditional random field (CRF); multilevel segmentation; RGB-D priors; rooftop extraction; SALIENCY DETECTION; LIDAR DATA; SEGMENTATION; RECOGNITION; SELECTION; RECOVERY; STEREO; DENSE;
D O I
10.1109/TGRS.2018.2850972
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
Accurate building rooftop extraction from high-resolution aerial images is of crucial importance in a wide range of applications. Owing to the varying appearance and large-scale range of scene objects, especially for building rooftops in different scales and heights, single-scale or individual prior-based extraction technique is insufficient in pursuing efficient, generic, and accurate extraction results. The trend toward integrating multiscale or several cue techniques appears to be the best way; thus, such integration is the focus of this paper. We first propose a novel salient rooftop detector integrating four correlative RGB-D priors (depth cue, uniqueness prior, shape prior, and transition surface prior) for improved rooftop extraction to address the preceding complex issues mentioned. Then, these correlative cues are computed from image layers created by our multilevel segmentation and further fused into the state-of-the-art high-order conditional random field (CRF) framework to locate the rooftop. Finally, an iterative optimization strategy is applied for high-quality solving, which can robustly handle varying appearance of building rooftops. Performance evaluations in the SZTAKI-INRIA benchmark data sets show that our method outperforms the traditional color-based algorithm and the original high-order CRF algorithm and its variants. The proposed algorithm is also evaluated and found to produce consistently satisfactory results for various large-scale, real-world data sets.
引用
收藏
页码:7369 / 7387
页数:19
相关论文
共 58 条
[11]  
Bischke B., 2017, Multi-Task Learning for Segmentation of Building Footprints with Deep Neural Networks
[12]  
Boykov YY, 2001, EIGHTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOL I, PROCEEDINGS, P105, DOI 10.1109/ICCV.2001.937505
[13]  
Bu SH, 2016, 2016 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2016), P4564, DOI 10.1109/IROS.2016.7759672
[14]   Global Contrast Based Salient Region Detection [J].
Cheng, Ming-Ming ;
Mitra, Niloy J. ;
Huang, Xiaolei ;
Torr, Philip H. S. ;
Hu, Shi-Min .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2015, 37 (03) :569-582
[15]   Mean shift: A robust approach toward feature space analysis [J].
Comaniciu, D ;
Meer, P .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (05) :603-619
[16]   Automatic Rooftop Extraction in Nadir Aerial Imagery of Suburban Regions Using Corners and Variational Level Set Evolution [J].
Cote, Melissa ;
Saeedi, Parvaneh .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2013, 51 (01) :313-328
[17]  
Duan L, 2015, PROC CVPR IEEE, P3119, DOI 10.1109/CVPR.2015.7298931
[18]   Multi-scale object-based image analysis and feature selection of multi-sensor earth observation imagery using random forests [J].
Duro, Dennis C. ;
Franklin, Steven E. ;
Dube, Monique G. .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2012, 33 (14) :4502-4526
[19]   Shadow-Based Rooftop Segmentation in Visible Band Images [J].
Femiani, John ;
Li, Er ;
Razdan, Anshuman ;
Wonka, Peter .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2015, 8 (05) :2063-2077
[20]   Direct least square fitting of ellipses [J].
Fitzgibbon, A ;
Pilu, M ;
Fisher, RB .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1999, 21 (05) :476-480