| 3D Change Detection in Urban Areas based on DCNN using a single image |
| Paper ID : 1141-SMPR |
| Authors: |
|
Hamed Amini Amirkolaee1, Hossein Arefi *2 1School of Surveying and Geospatial Eng., College of Eng., University of Tehran, Tehran, Iran 2University of Tehran |
| 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 estimated DSMs indicates 2.487 m, 0.731 and 0.274 for root mean squared error, average relative error, and average log10 error, respectively. |
| Keywords: |
| Change detection, LiDAR, Single image, CNN, DSM, Urban area |
| Status : Conditional Accept (Oral Presentation) |
