HF-FCN: Hierarchically Fused Fully Convolutional Network for Robust Building Extraction

Automatic building extraction from remote sensing images plays an important role in a diverse range of applications. However, it is significantly challenging to extract arbitrary-size buildings with largely variant appearances or occlusions. In this paper, we propose a robust system employing a novel hierarchically fused fully convolutional network (HF-FCN), which effectively integrates the information generated from a group of neurons with multi-scale receptive fields. Our architecture takes an aerial image as the input without warping or cropping it and directly generates the building map. The experiment results tested on a public aerial imagery dataset demonstrate that our method surpasses state-of-the-art methods in the building detection accuracy and significantly reduces the time cost.

[1]  Luc Van Gool,et al.  The 2005 PASCAL Visual Object Classes Challenge , 2005, MLCW.

[2]  Parvaneh Saeedi,et al.  A novel approach for polygonal rooftop detection in satellite/aerial imageries , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[3]  Takayoshi Yamashita,et al.  Multiple Object Extraction from Aerial Imagery with Convolutional Neural Networks , 2016, IRIACV.

[4]  Zhuowen Tu,et al.  Holistically-Nested Edge Detection , 2015, ICCV.

[5]  Chengdong Wu,et al.  Shadow-based Building Detection and Segmentation in High-resolution Remote Sensing Image , 2014, J. Multim..

[6]  C. Unsalan,et al.  Building detection from aerial images using invariant color features and shadow information , 2008, 2008 23rd International Symposium on Computer and Information Sciences.

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

[8]  W. Woon,et al.  Novel Approach for Rooftop Detection Using Support Vector Machine , 2013 .

[9]  Geoffrey E. Hinton,et al.  Machine Learning for Aerial Image Labeling , 2013 .

[10]  Saman Ghaffarian,et al.  Automatic building detection based on Purposive FastICA (PFICA) algorithm using monocular high resolution Google Earth images , 2014 .

[11]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[12]  Seunghoon Hong,et al.  Learning Deconvolution Network for Semantic Segmentation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[13]  Vibhav Vineet,et al.  Conditional Random Fields as Recurrent Neural Networks , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[14]  Qiming Qin,et al.  An Efficient Approach for Automatic Rectangular Building Extraction From Very High Resolution Optical Satellite Imagery , 2015, IEEE Geoscience and Remote Sensing Letters.

[15]  Parvaneh Saeedi,et al.  Automatic Rooftop Extraction in Nadir Aerial Imagery of Suburban Regions Using Corners and Variational Level Set Evolution , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[16]  Andrea Manno-Kovacs,et al.  Building Detection From Monocular VHR Images by Integrated Urban Area Knowledge , 2015, IEEE Geoscience and Remote Sensing Letters.

[17]  Fadi Dornaika,et al.  Object Classification using Hybrid Holistic Descriptors: Application to Building Detection in Aerial Orthophotos , 2015, Polibits.

[18]  Vincent Mazet,et al.  Automatic rectangular building detection from VHR aerial imagery using shadow and image segmentation , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

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

[20]  Ramakant Nevatia,et al.  Detection and Modeling of Buildings from Multiple Aerial Images , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.