Classification for Remote Sensing Data With Improved CNN-SVM Method

The efficient classification of remote sensing images (RSIs) has become the key of remote sensing application. To tackle the high computational cost in the traditional classification method, in this paper we propose a new RSI classification method based on improved convolutional neural network (CNN) and support vector machine (SVM) (CNN-SVM). In this method, we first designed a seven-layer CNN structure and took the ReLU function as the activation function. We then inputted the RSI into the CNN model and extracted feature maps and replaced the output layer of the CNN network via training the feature maps in the SVM classifier. Next, taking the simulation experiments of MNIST handwritten digital dataset and UC Merced Land Use remote sensing dataset as examples, we tested and verified the proposed method in this experiment. Finally, the empirical study of volcanic ash cloud (VAC) classification from moderate resolution imaging spectroradiometer (MODIS) RSI was carried out and evaluated. The experimental results show that compared with the traditional methods, the proposed method has lower loss value and better generalization in modeling training; the total classification accuracy of VAC and Kappa coefficient reached 93.5% and 0.8502, respectively, and achieved preferable VAC identification and visual effects. It will enhance the classification accuracy to the massive remote sensing data.

[1]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Gui-Song Xia,et al.  Extreme value theory-based calibration for the fusion of multiple features in high-resolution satellite scene classification , 2013 .

[3]  Huang Jie,et al.  Ship object detection in remote sensing images using convolutional neural networks , 2017 .

[4]  Jefersson Alex dos Santos,et al.  Towards better exploiting convolutional neural networks for remote sensing scene classification , 2016, Pattern Recognit..

[5]  Jing Ge,et al.  Modeling alpine grassland cover based on MODIS data and support vector machine regression in the headwater region of the Huanghe River, China , 2018, Remote Sensing of Environment.

[6]  Wei Lee Woon,et al.  Simultaneous extraction of roads and buildings in remote sensing imagery with convolutional neural networks , 2017 .

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

[8]  Cheng-Fan Li,et al.  A New Fuzzy Clustering Method With Neighborhood Distance Constraint for Volcanic Ash Cloud , 2016, IEEE Access.

[9]  Chengfan Li,et al.  Volcanic ash cloud detection from MODIS image based on CPIWS method , 2017, Acta Geophysica.

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

[11]  Pabitra Mitra,et al.  BASS Net: Band-Adaptive Spectral-Spatial Feature Learning Neural Network for Hyperspectral Image Classification , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Sildomar T. Monteiro,et al.  Semantic segmentation of multisensor remote sensing imagery with deep ConvNets and higher-order conditional random fields , 2019, Journal of Applied Remote Sensing.

[13]  Junwei Han,et al.  Automatic landslide detection from remote-sensing imagery using a scene classification method based on BoVW and pLSA , 2013 .

[14]  Qianqing Qin,et al.  Scene Classification Based on Multiscale Convolutional Neural Network , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[15]  David Bull,et al.  A supervised hierarchical segmentation of remote-sensing images using a committee of multi-scale convolutional neural networks , 2016 .

[16]  Steven E. Franklin,et al.  A comparison of pixel-based and object-based image analysis with selected machine learning algorithms for the classification of agricultural landscapes using SPOT-5 HRG imagery , 2012 .

[17]  Andreas Stohl,et al.  Ash Metrics for European and Trans‐Atlantic Air Routes During the Eyjafjallajökull Eruption 14 April to 23 May 2010 , 2018 .

[18]  Farid Melgani,et al.  Convolutional SVM Networks for Object Detection in UAV Imagery , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[19]  David Zhang,et al.  F-SVM: Combination of Feature Transformation and SVM Learning via Convex Relaxation , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[20]  Yi Zheng,et al.  Remote sensing scene classification based on rotation-invariant feature learning and joint decision making , 2019, EURASIP J. Image Video Process..

[21]  Dengxin Dai,et al.  Satellite Image Classification via Two-Layer Sparse Coding With Biased Image Representation , 2011, IEEE Geoscience and Remote Sensing Letters.

[22]  Jun Rao,et al.  A Y-Net deep learning method for road segmentation using high-resolution visible remote sensing images , 2019, Remote Sensing Letters.

[23]  Desheng Liu,et al.  A comparison of object-based and contextual pixel-based classifications using high and medium spatial resolution images , 2013 .

[24]  Zongxu Pan,et al.  Ship Detection in Gaofen-3 SAR Images Based on Sea Clutter Distribution Analysis and Deep Convolutional Neural Network , 2018, Sensors.

[25]  Jun Li,et al.  Improved hyperspectral image classification by active learning using pre-designed mixed pixels , 2016, Pattern Recognit..

[26]  Michele Volpi,et al.  Land cover mapping at very high resolution with rotation equivariant CNNs: towards small yet accurate models , 2018, ISPRS Journal of Photogrammetry and Remote Sensing.

[27]  Hongguang Sun,et al.  A Hybrid Classification Approach Based on Support Vector Machine and K-Nearest Neighbor for Remote Sensing Data , 2017, Int. J. Pattern Recognit. Artif. Intell..

[28]  Kang Zhang,et al.  Complex scene classification of remote sensing images based on CNN , 2018 .

[29]  Reza Shah-Hosseini,et al.  Fusion of deep learning with adaptive bilateral filter for building outline extraction from remote sensing imagery , 2018, Journal of Applied Remote Sensing.

[30]  Lijun Zhao,et al.  Analysis of the inter-dataset representation ability of deep features for high spatial resolution remote sensing image scene classification , 2018, Multimedia Tools and Applications.