Deep learning architectures for land cover classification using red and near-infrared satellite images

Classification of remotely sensed data requires the modelling of suitable image processing algorithms. The rise of machine learning systems upgraded the viability of satellite image applications. Using Convolutional Neural Networks (CNN), benchmark classification exactness can be accomplished for land cover grouping. Motivated by the concept of Normalized Difference Vegetation Index (NDVI), this paper utilizes only the red and near infrared (NIR) band information for classifying the publicly available SAT-4 and SAT-6 datasets. This is done, since NDVI computation requires only the two band (red and NIR) information and the classes involved in the dataset are types of vegetation. In this work, new deep learning architectures for three different networks (AlexNet, ConvNet, VGG) were proposed by hypertuning the network and the input as two band data. The modified architectures with the two band information along with reduced number of filters were trained and tested model manages to classify the images into different classes. The proposed architectures are compared against the existing architectures in terms of accuracy, precision and trainable parameters. The proposed architecture is found to perform equally efficient by retaining high accuracy with less number of trainable parameters, when compared against the the performance of benchmark deep learning architectures for satellite image classification.

[1]  Jiangye Yuan,et al.  Domain-Adapted Convolutional Networks for Satellite Image Classification: A Large-Scale Interactive Learning Workflow , 2018, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[2]  Haifeng Li,et al.  RSI-CB: A Large Scale Remote Sensing Image Classification Benchmark via Crowdsource Data , 2017, ArXiv.

[3]  Qi Tian,et al.  Enhancing Micro-video Understanding by Harnessing External Sounds , 2017, ACM Multimedia.

[4]  K. P. Soman,et al.  Least Square Denoising in Spectral Domain for Hyperspectral Images , 2017 .

[5]  V. Sowmya,et al.  Dependency of Various Color and Intensity Planes on CNN Based Image Classification , 2017, SIRS.

[6]  Qiuyan Yu,et al.  Feasibility Study of Land Cover Classification Based on Normalized Difference Vegetation Index for Landslide Risk Assessment , 2016 .

[7]  Qingshan Liu,et al.  Learning Multiscale Deep Features for High-Resolution Satellite Image Scene Classification , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Wei Liu,et al.  Neural Compatibility Modeling with Attentive Knowledge Distillation , 2018, SIGIR.

[9]  Bertrand Le Saux,et al.  Segment-before-Detect: Vehicle Detection and Classification through Semantic Segmentation of Aerial Images , 2017, Remote. Sens..

[10]  Nikolaos Doulamis,et al.  Deep supervised learning for hyperspectral data classification through convolutional neural networks , 2015, 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[11]  Stefan Winkler,et al.  Ground-based image analysis: A tutorial on machine-learning techniques and applications , 2016, IEEE Geoscience and Remote Sensing Magazine.

[12]  V. Sowmya,et al.  Aerial and Satellite Image Denoising using Least Square Weighted Regularization Method , 2016 .

[13]  Yong Wang,et al.  Assessing relationship of air quality index and vegetation type using hyperspectral remote sensing , 2017, 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[14]  V. Sowmya,et al.  Least Square Based Fast Denoising Approach to Hyperspectral Imagery , 2016 .

[15]  V. Sowmya,et al.  Hyperspectral Image Denoising Using Legendre-Fenchel Transform for Improved Sparsity Based Classification , 2016 .

[16]  Supratik Mukhopadhyay,et al.  DeepSat: a learning framework for satellite imagery , 2015, SIGSPATIAL/GIS.

[17]  S. Narayana Reddy,et al.  Land cover classification based on NDVI using LANDSAT8 time series: A case study Tirupati region , 2016, 2016 International Conference on Communication and Signal Processing (ICCSP).

[18]  Suvajit Dutta,et al.  A comparative study of deep learning models for medical image classification , 2017 .

[19]  Nilanjan Dey,et al.  A survey of image classification methods and techniques , 2014, 2014 International Conference on Control, Instrumentation, Communication and Computational Technologies (ICCICCT).

[20]  Jianshu Luo,et al.  Analysis and Denoising of Hyperspectral Remote Sensing Image in the Curvelet Domain , 2013 .

[21]  Qihao Weng,et al.  A survey of image classification methods and techniques for improving classification performance , 2007 .

[22]  Indranil Misra,et al.  Kernel based learning approach for satellite image classification using support vector machine , 2011, 2011 IEEE Recent Advances in Intelligent Computational Systems.

[23]  Yucel Cimtay,et al.  Calculation of vegetation index for short wave infrared hyperspectral images , 2017, 2017 25th Signal Processing and Communications Applications Conference (SIU).

[24]  Konstantinos Karantzalos,et al.  BENCHMARKING DEEP LEARNING FRAMEWORKS FOR THE CLASSIFICATION OF VERY HIGH RESOLUTION SATELLITE MULTISPECTRAL DATA , 2016 .

[25]  Thomas Hofmann,et al.  Learning Aerial Image Segmentation From Online Maps , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[26]  Jun Ma,et al.  NeuroStylist: Neural Compatibility Modeling for Clothing Matching , 2017, ACM Multimedia.

[27]  Lior Bragilevsky,et al.  Deep learning for Amazon satellite image analysis , 2017, 2017 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM).

[28]  Jamie Sherrah,et al.  Semantic Labeling of Aerial and Satellite Imagery , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[29]  Chunmei Zhang,et al.  Improving hyperspectral data classification of satellite imagery by using a sparse based new model with learning dictionary , 2014, 2014 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS).