Building Extraction Based on an Optimized Stacked Sparse Autoencoder of Structure and Training Samples Using LIDAR DSM and Optical Images

In this paper, a building extraction method is proposed based on a stacked sparse autoencoder with an optimized structure and training samples. Building extraction plays an important role in urban construction and planning. However, some negative effects will reduce the accuracy of extraction, such as exceeding resolution, bad correction and terrain influence. Data collected by multiple sensors, as light detection and ranging (LIDAR), optical sensor etc., are used to improve the extraction. Using digital surface model (DSM) obtained from LIDAR data and optical images, traditional method can improve the extraction effect to a certain extent, but there are some defects in feature extraction. Since stacked sparse autoencoder (SSAE) neural network can learn the essential characteristics of the data in depth, SSAE was employed to extract buildings from the combined DSM data and optical image. A better setting strategy of SSAE network structure is given, and an idea of setting the number and proportion of training samples for better training of SSAE was presented. The optical data and DSM were combined as input of the optimized SSAE, and after training by an optimized samples, the appropriate network structure can extract buildings with great accuracy and has good robustness.

[1]  Bisheng Yang,et al.  Automatic registration of UAV-borne sequent images and LiDAR data , 2015 .

[2]  Martial Hebert,et al.  Man-made structure detection in natural images using a causal multiscale random field , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[3]  Wang Jianhua,et al.  A Survey of Building Extraction Methods from Optical High Resolution Remote Sensing Imagery , 2016 .

[4]  Taejung Kim,et al.  Development of a graph-based approach for building detection , 1999, Image Vis. Comput..

[5]  Parvaneh Saeedi,et al.  Three-Dimensional Polygonal Building Model Estimation From Single Satellite Images , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[7]  Haiyan Guan,et al.  Partially supervised hierarchical classification for urban features from lidar data with aerial imagery , 2013 .

[8]  Ye Zhang,et al.  Shadow Detection and Removal for Occluded Object Information Recovery in Urban High-Resolution Panchromatic Satellite Images , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[9]  Yiming Yan,et al.  A Hierarchical Building Segmentation in Digital Surface Models for 3D Reconstruction , 2017, Sensors.

[10]  Hichem Sahli,et al.  A Stochastic Framework for the Identification of Building Rooftops Using a Single Remote Sensing Image , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[11]  Norbert Haala,et al.  An update on automatic 3D building reconstruction , 2010 .

[12]  Cem Ünsalan,et al.  Urban-Area and Building Detection Using SIFT Keypoints and Graph Theory , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Fei Deng,et al.  Integration of orthoimagery and lidar data for object-based urban thematic mapping using random forests , 2013 .

[14]  Huseyin Gokhan Akcay,et al.  Automatic Detection of Geospatial Objects Using Multiple Hierarchical Segmentations , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[15]  LiJonathan,et al.  URBAN THEMATIC MAPPING BY INTEGRATING LIDAR POINT CLOUD WITH COLOUR IMAGERY , 2011 .

[16]  Zhengjun Liu,et al.  Building extraction from high resolution satellite imagery based on multi-scale image segmentation and model matching , 2008, 2008 International Workshop on Earth Observation and Remote Sensing Applications.

[17]  Jianya Gong,et al.  A Two-step Displacement Correction Algorithm for Registration of Lidar Point Clouds and Aerial Images without Orientation Parameters , 2010 .

[18]  Xiaopeng Zhang,et al.  Robust Rooftop Extraction From Visible Band Images Using Higher Order CRF , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[19]  Haiyan Guan,et al.  3D Building Reconstruction from Airborne Lidar Point Clouds Fused with Aerial Imagery , 2011 .

[20]  Wang Xiaoqin,et al.  Building Extraction and Its Height Estimation over Urban Areas based on Morphological Building Index , 2015 .

[21]  Yunsheng Zhang,et al.  Building Change Detection Using Old Aerial Images and New LiDAR Data , 2016, Remote. Sens..

[22]  David A. Clausi,et al.  A Multiscale Latent Dirichlet Allocation Model for Object-Oriented Clustering of VHR Panchromatic Satellite Images , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[23]  Fumio Yamazaki,et al.  Use of Digital Surface Model Constructed from Digital Aerial Images to Detect Collapsed Buildings during Earthquake , 2011 .

[24]  O. Tournaire,et al.  An efficient stochastic approach for building footprint extraction from digital elevation models , 2010 .

[25]  Jianzhong Wu,et al.  Stacked Sparse Autoencoder (SSAE) for Nuclei Detection on Breast Cancer Histopathology Images , 2016, IEEE Transactions on Medical Imaging.

[26]  Haiyan Guan,et al.  URBAN THEMATIC MAPPING BY INTEGRATING LIDAR POINT CLOUD WITH COLOUR IMAGERY , 2012 .