Extracting Urban Impervious Surface from WorldView-2 and Airborne LiDAR Data Using 3D Convolutional Neural Networks

The urban impervious surface has been recognized as a key quantifiable indicator in assessing urbanization and its environmental impacts. Adopting deep learning technologies, this study proposes an approach of three-dimensional convolutional neural networks (3D CNNs) to extract impervious surfaces from the WorldView-2 and airborne LiDAR datasets. The influences of different 3D CNN parameters on impervious surface extraction are evaluated. In an effort to reduce the limitations from single sensor data, this study also explores the synergistic use of multi-source remote sensing datasets for delineating urban impervious surfaces. Results indicate that our proposed 3D CNN approach has a great potential and better performance on impervious surface extraction, with an overall accuracy higher than 93.00% and the overall kappa value above 0.89. Compared with the commonly applied pixel-based support vector machine classifier, our proposed 3D CNN approach takes advantage not only of the pixel-level spatial and spectral information, but also of texture and feature maps through multi-scale convolutional processes, which enhance the extraction of impervious surfaces. While image analysis is facing large challenges in a rapidly developing big data era, our proposed 3D CNNs will become an effective approach for improved urban impervious surface extraction.

[1]  Huadong Guo,et al.  Synergistic Use of Optical and PolSAR Imagery for Urban Impervious Surface Estimation , 2014 .

[2]  Andrea Cavallaro,et al.  Sensor Capability and Atmospheric Correction in Ocean Colour Remote Sensing , 2015, Remote. Sens..

[3]  D. Roberts,et al.  Generalizing machine learning regression models using multi-site spectral libraries for mapping vegetation-impervious-soil fractions across multiple cities , 2018, Remote Sensing of Environment.

[4]  Junwei Han,et al.  Learning Rotation-Invariant Convolutional Neural Networks for Object Detection in VHR Optical Remote Sensing Images , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Yong Dou,et al.  Airport Detection on Optical Satellite Images Using Deep Convolutional Neural Networks , 2017, IEEE Geoscience and Remote Sensing Letters.

[6]  Xuefei Hu,et al.  Estimating impervious surfaces from medium spatial resolution imagery using the self-organizing map and multi-layer perceptron neural networks. , 2009 .

[7]  Nataliia Kussul,et al.  Deep Learning Classification of Land Cover and Crop Types Using Remote Sensing Data , 2017, IEEE Geoscience and Remote Sensing Letters.

[8]  Curt H. Davis,et al.  Training Deep Convolutional Neural Networks for Land–Cover Classification of High-Resolution Imagery , 2017, IEEE Geoscience and Remote Sensing Letters.

[9]  Zhongchang Sun,et al.  Long-term effects of land use/land cover change on surface runoff in urban areas of Beijing, China , 2013 .

[10]  Peijun Du,et al.  Multisource Earth Observation Data for Land-Cover Classification Using Random Forest , 2018, IEEE Geoscience and Remote Sensing Letters.

[11]  James B. Campbell,et al.  Comparing Urban Impervious Surface Identification Using Landsat and High Resolution Aerial Photography , 2013, Remote. Sens..

[12]  Hanqiu Xu,et al.  Rule-based impervious surface mapping using high spatial resolution imagery , 2013 .

[13]  Kaiming He,et al.  Focal Loss for Dense Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[14]  P. Tarolli,et al.  Improving impervious surface estimation: an integrated method of classification and regression trees (CART) and linear spectral mixture analysis (LSMA) based on error analysis , 2018 .

[15]  Uwe Stilla,et al.  Deep Learning Earth Observation Classification Using ImageNet Pretrained Networks , 2016, IEEE Geoscience and Remote Sensing Letters.

[16]  Amy Loutfi,et al.  Classification and Segmentation of Satellite Orthoimagery Using Convolutional Neural Networks , 2016, Remote. Sens..

[17]  Lei Zhang,et al.  Mapping seasonal impervious surface dynamics in Wuhan urban agglomeration, China from 2000 to 2016 , 2018, Int. J. Appl. Earth Obs. Geoinformation.

[18]  Kaiwen Zhong,et al.  Measuring spatio-temporal dynamics of impervious surface in Guangzhou, China, from 1988 to 2015, using time-series Landsat imagery. , 2018, The Science of the total environment.

[19]  Huadong Guo,et al.  A Modified Normalized Difference Impervious Surface Index (MNDISI) for Automatic Urban Mapping from Landsat Imagery , 2017, Remote. Sens..

[20]  Andrea Vedaldi,et al.  MatConvNet: Convolutional Neural Networks for MATLAB , 2014, ACM Multimedia.

[21]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[22]  Yi Qiang,et al.  Wetland Accretion Rates Along Coastal Louisiana: Spatial and Temporal Variability in Light of Hurricane Isaac’s Impacts , 2015 .

[23]  Ming Yang,et al.  3D Convolutional Neural Networks for Human Action Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Seung-Jong Bae,et al.  The Impact of Impervious Surface on Water Quality and Its Threshold in Korea , 2016 .

[25]  Hongsheng Zhang,et al.  Improving the impervious surface estimation with combined use of optical and SAR remote sensing images , 2014 .

[26]  Hashem Akbari,et al.  Effect of increasing urban albedo on meteorology and air quality of Montreal (Canada) – Episodic simulation of heat wave in 2005 , 2016 .

[27]  Lorenzo Torresani,et al.  Learning Spatiotemporal Features with 3D Convolutional Networks , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[28]  Igor Sevo,et al.  Convolutional Neural Network Based Automatic Object Detection on Aerial Images , 2016, IEEE Geoscience and Remote Sensing Letters.

[29]  Hongwei Liu,et al.  Convolutional Neural Network With Data Augmentation for SAR Target Recognition , 2016, IEEE Geoscience and Remote Sensing Letters.

[30]  Walid Ouerghemmi,et al.  Hyperspectral Imagery for Environmental Urban Planning , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[31]  Lindi J. Quackenbush,et al.  Impervious surface quantification using a synthesis of artificial immune networks and decision/regression trees from multi-sensor data , 2012 .

[32]  Xiuping Jia,et al.  Hyperspectral Image Classification Using Convolutional Neural Networks and Multiple Feature Learning , 2018, Remote. Sens..

[33]  Qi Yue,et al.  Deep Learning for Hyperspectral Data Classification through Exponential Momentum Deep Convolution Neural Networks , 2016, J. Sensors.

[34]  Curt H. Davis,et al.  Fusion of Deep Convolutional Neural Networks for Land Cover Classification of High-Resolution Imagery , 2017, IEEE Geoscience and Remote Sensing Letters.

[35]  Xinwu Li,et al.  Estimating urban impervious surfaces from Landsat-5 TM imagery using multilayer perceptron neural network and support vector machine , 2011 .

[36]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[37]  Louise Willemen,et al.  Machine Learning Using Hyperspectral Data Inaccurately Predicts Plant Traits Under Spatial Dependency , 2018, Remote. Sens..

[38]  Pierre Alliez,et al.  Convolutional Neural Networks for Large-Scale Remote-Sensing Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[39]  Haipeng Wang,et al.  Target Classification Using the Deep Convolutional Networks for SAR Images , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[40]  Hui Lin,et al.  Urban Impervious Surfaces Estimation From Optical and SAR Imagery: A Comprehensive Comparison , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[41]  Jianguo Wu,et al.  A hierarchical analysis of the relationship between urban impervious surfaces and land surface temperatures: spatial scale dependence, temporal variations, and bioclimatic modulation , 2016, Landscape Ecology.

[42]  Xiuping Jia,et al.  Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks , 2016, IEEE Transactions on Geoscience and Remote Sensing.