Land-Use Detection Using Residual Convolutional Neural Network

Land-Use detection is an important application in the context of remote sensing. This objective is to classify, a chunk of a satellite or high-earth orbit image of the earth, as the type of land-use. In this work, we have used recent advancement in computer vision with deep learning to improve the performance to the classification task. We have used a very deep convolutional neural network with the residual connection as a building block and the concept of transfer learning to train this model. The experiment shows that the performance of the classifier is very high with transfer learning on a pre-trained model rather than training from the sketch with such small dataset that is available for land use classification task. Our proposed approach generated a better result than the previously existing method in benchmark dataset.

[1]  Gui-Song Xia,et al.  Dirichlet-Derived Multiple Topic Scene Classification Model for High Spatial Resolution Remote Sensing Imagery , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[2]  Brian P. Salmon,et al.  Multiview Deep Learning for Land-Use Classification , 2015, IEEE Geoscience and Remote Sensing Letters.

[3]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .

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

[5]  Jude Shavlik,et al.  Chapter 11 Transfer Learning , 2009 .

[6]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Yanfei Zhong,et al.  A spectral–structural bag-of-features scene classifier for very high spatial resolution remote sensing imagery , 2016 .

[8]  Carlo Gatta,et al.  Unsupervised Deep Feature Extraction for Remote Sensing Image Classification , 2015, IEEE Transactions on Geoscience and Remote Sensing.

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

[10]  Bo Du,et al.  Deep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art , 2016, IEEE Geoscience and Remote Sensing Magazine.

[11]  Shawn D. Newsam,et al.  Spatial pyramid co-occurrence for image classification , 2011, 2011 International Conference on Computer Vision.

[12]  Liangpei Zhang,et al.  The Fisher Kernel Coding Framework for High Spatial Resolution Scene Classification , 2016, Remote. Sens..

[13]  Tong Zhang,et al.  Deep Learning Based Feature Selection for Remote Sensing Scene Classification , 2015, IEEE Geoscience and Remote Sensing Letters.

[14]  Xueming Qian,et al.  Semantic Annotation of High-Resolution Satellite Images via Weakly Supervised Learning , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[15]  Bo Du,et al.  Scene Classification via a Gradient Boosting Random Convolutional Network Framework , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[16]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[17]  Bo Huang,et al.  Transfer Learning With Fully Pretrained Deep Convolution Networks for Land-Use Classification , 2017, IEEE Geoscience and Remote Sensing Letters.