Automatic extraction of built-up area based on deep convolution neural network

Built-up area has been one of the most important objects to be extracted in remote sensing images. Several factors such as complex structure, diverse texture and varied background, bring the challenges for the task of built-up area extraction. In this paper, a multiple input structure of deep convolution neural network (CNN) is proposed to extract built-up area automatically, which can fuse the information of panchromatic and multispectral remote sensing image. The image patch based classification results are further refined by postprocessing of segmentation techniques. The experiments demonstrate that the proposed method has better generalization ability compared to the state-of-the-art method, and the overall classification accuracy is above 98%.

[1]  Yihua Tan,et al.  Unsupervised Detection of Built-Up Areas From Multiple High-Resolution Remote Sensing Images , 2013, IEEE Geoscience and Remote Sensing Letters.

[2]  Yu Meng,et al.  New normalized difference index for built-up land enhancement using airborne visible infrared imaging spectrometer imagery , 2014 .

[3]  Tamás Szirányi,et al.  Improved Harris Feature Point Set for Orientation-Sensitive Urban-Area Detection in Aerial Images , 2013, IEEE Geoscience and Remote Sensing Letters.

[4]  Martino Pesaresi,et al.  A Robust Built-Up Area Presence Index by Anisotropic Rotation-Invariant Textural Measure , 2008, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[5]  Yi Li,et al.  Built-Up Area Detection From Satellite Images Using Multikernel Learning, Multifield Integrating, and Multihypothesis Voting , 2015, IEEE Geoscience and Remote Sensing Letters.

[6]  A. Huete.  A soil-adjusted vegetation index (SAVI) , 1988 .

[7]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Cheng Li,et al.  Texture-based urban detection using contourlet coefficient on remote sensing imagery , 2015 .

[9]  Avnish Varshney,et al.  A Comparative Study of Built-up Index Approaches for Automated Extraction of Built-up Regions From Remote Sensing Data , 2014, Journal of the Indian Society of Remote Sensing.

[10]  Liangpei Zhang,et al.  Morphological Building/Shadow Index for Building Extraction From High-Resolution Imagery Over Urban Areas , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[11]  J. A. Schell,et al.  Monitoring vegetation systems in the great plains with ERTS , 1973 .

[12]  Yihua Tan,et al.  Cauchy Graph Embedding Optimization for Built-Up Areas Detection From High-Resolution Remote Sensing Images , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[13]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

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

[15]  Sara Bouzekri,et al.  A New Spectral Index for Extraction of Built-Up Area Using Landsat-8 Data , 2015, Journal of the Indian Society of Remote Sensing.

[16]  Lorenzo Bruzzone,et al.  Labeled co-occurrence matrix for the detection of built-up areas in high-resolution SAR images , 2013, Remote Sensing.