3D CHANGE DETECTION IN URBAN AREAS BASED ON DCNN USING A SINGLE IMAGE

Abstract. In this paper, a novel approach is proposed for 3D change detection in urban areas using only a single satellite images. To this purpose, a dense convolutional neural network (DCNN) is utilized in order to estimate a digital surface model (DSM) from a single image. In this regard, a densely connected convolutional network is employed for feature extraction and an upsampling method based on dilated convolution is employed for estimating the height values. The proposed DCNN is trained using satellite and Light Detection and Ranging (LiDAR) data which are provided in 2012 from Isfahan, Iran. Subsequently, the trained network is utilized in order to estimate DSM of a single satellite image that is provided in 2006. Finally, the changed areas are detected by subtracting the estimated DSMs. Evaluating the accuracy of the detected changed areas indicates 66.59, 72.90 and 67.90 for correctness, completeness, and kappa, respectively.

[1]  Michael Ying Yang,et al.  Change Detection between Multimodal Remote Sensing Data Using Siamese CNN , 2018, ArXiv.

[2]  George Vosselman,et al.  Change detection for updating medium scale maps using laster altimetry , 2004 .

[3]  Naoto Yokoya,et al.  IMG2DSM: Height Simulation From Single Imagery Using Conditional Generative Adversarial Net , 2018, IEEE Geoscience and Remote Sensing Letters.

[4]  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.

[5]  Francisco Herrera,et al.  Towards Highly Accurate Coral Texture Images Classification Using Deep Convolutional Neural Networks and Data Augmentation , 2018, Expert Syst. Appl..

[6]  Xiao Xiang Zhu,et al.  IM2HEIGHT: Height Estimation from Single Monocular Imagery via Fully Residual Convolutional-Deconvolutional Network , 2018, ArXiv.

[7]  R. Reulke,et al.  Remote Sensing and Spatial Information Sciences , 2005 .

[8]  J. Hyyppä,et al.  International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol.XXXVI, Part 3 / W52 , 2007 .

[9]  Yunde Jia,et al.  Vehicle Type Classification Using a Semisupervised Convolutional Neural Network , 2015, IEEE Transactions on Intelligent Transportation Systems.

[10]  Nassir Navab,et al.  Deeper Depth Prediction with Fully Convolutional Residual Networks , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[11]  M. Turker,et al.  Automatic detection of earthquake‐damaged buildings using DEMs created from pre‐ and post‐earthquake stereo aerial photographs , 2005 .

[12]  Kyu-Ri Choi,et al.  A FEATURE BASED APPROACH TO AUTOMATIC CHANGE DETECTION FROM LIDAR DATA IN URBAN AREAS , 2009 .

[13]  Franck Jung.  Detecting building changes from multitemporal aerial stereopairs , 2004 .

[14]  F. Rottensteiner,et al.  Classification of urban LiDAR data using conditional random field and random forests , 2013, Joint Urban Remote Sensing Event 2013.

[15]  Parham Pahlavani,et al.  A new feature selection from lidar data and digital aerial images acquired for an urban/c environment using an ANFIS-based classification and a fuzzy rough set method , 2015 .

[16]  Hossein Arefi,et al.  Convolutional neural network architecture for digital surface model estimation from single remote sensing image , 2019, Journal of Applied Remote Sensing.

[17]  D. Lu,et al.  Change detection techniques , 2004 .

[18]  J. Hyyppä,et al.  Automatic detection of buildings from laser scanner data for map updating , 2003 .

[19]  Hossein Arefi,et al.  Height estimation from single aerial images using a deep convolutional encoder-decoder network , 2019, ISPRS Journal of Photogrammetry and Remote Sensing.

[20]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[21]  Christian Ginzler,et al.  Change Detection in Mire Ecosystems: Assessing Changes of Forest Area using Airborne Remote Sensing Data , 2007 .

[22]  Peijun Li,et al.  Extraction of earthquake-induced collapsed buildings using very high-resolution imagery and airborne lidar data , 2015 .

[23]  Chang-Su Kim,et al.  Change Detection in High Resolution Satellite Images Using an Ensemble of Convolutional Neural Networks , 2018, 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).