Satellite Image Categorization Using Scalable Deep Learning

Detecting and classifying objects from satellite images are crucial for many applications, ranging from marine monitoring to land planning, ecology to warfare, etc. Spatial and temporal information-rich satellite images are exploited in a variety of manners to solve many real-world remote sensing problems. Satellite image classification has many associated challenges. These challenges include data availability, the quality of data, the quantity of data, and data distribution. These challenges make the analysis of satellite images more challenging. A convolutional neural network architecture with a scaling method is proposed for the classification of satellite images. The scaling method can evenly scale all dimensions of depth, width, and resolution using a compound coefficient. It can be used as a preliminary task in urban planning, satellite surveillance, monitoring, etc. It can also be helpful in geo-information and maritime monitoring systems. The proposed methodology is based on an end-to-end, scalable satellite image interpretation. It uses spatial information from satellite images to categorize these into four categories. The proposed method gives encouraging and promising results on a challenging dataset with a high inter-class similarity and intra-class variation. The proposed method shows 99.64% accuracy on the RSI-CB256 dataset.

[1]  Yongil Kim,et al.  Semi-Supervised Land Cover Classification of Remote Sensing Imagery Using CycleGAN and EfficientNet , 2023, KSCE Journal of Civil Engineering.

[2]  E. Özbay,et al.  Classification of satellite images for ecology management using deep features obtained from convolutional neural network models , 2023, Iran Journal of Computer Science.

[3]  Samabia Tehsin,et al.  An effective deep learning model for ship detection from satellite images , 2022, Spatial Information Research.

[4]  S. Al‐Bulushi.  From the Sky to the Streets, and Back , 2022, Social Text.

[5]  N. Musaoğlu,et al.  Detection of mucilage phenomenon in the Sea of Marmara by using multi-scale satellite data , 2022, Environmental Monitoring and Assessment.

[6]  A. Novellino,et al.  Multispectral satellite imagery and machine learning for the extraction of shoreline indicators , 2022, Coastal Engineering.

[7]  W. Mapurisa,et al.  BRIGHTEARTH: PIPELINE FOR ON-THE-FLY 3D RECONSTRUCTION OF URBAN AND RURAL SCENES FROM ONE SATELLITE IMAGE , 2022, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences.

[8]  V. Manekar,et al.  Artificial Intelligence-Based Image Classification Techniques for Hydrologic Applications , 2021, Appl. Artif. Intell..

[9]  H. Pelgrum,et al.  High spatio-temporal monitoring of century-old biochar effects on evapotranspiration through the ETLook model: a case study with UAV and satellite image fusion based on additive wavelet transform (AWT) , 2021, GIScience & Remote Sensing.

[10]  Anis Koubaa,et al.  An Efficient Approach Based on Privacy-Preserving Deep Learning for Satellite Image Classification , 2021, Remote. Sens..

[11]  Grant J. Scott,et al.  Large-Scale, Multiple Level-of-Detail Change Detection from Remote Sensing Imagery Using Deep Visual Feature Clustering , 2021, Remote. Sens..

[12]  Marius Paraschiv,et al.  Ecological Monitoring with Spy Satellite Images - The Case of Red Wood Ants in Romania , 2021, Remote. Sens..

[13]  A. Farina,et al.  Space-Based Global Maritime Surveillance. Part I: Satellite Technologies , 2020, IEEE Aerospace and Electronic Systems Magazine.

[14]  E. Semenishchev,et al.  Missing area reconstruction in 3D scene from multi-view satellite images for surveillance applications , 2020, Security + Defence.

[15]  Daniel Dziob,et al.  Interdisciplinary Teaching Using Satellite Images as a Way to Introduce Remote Sensing in Secondary School , 2020, Remote. Sens..

[16]  Snehmani,et al.  Detection and mapping of snow avalanche debris from Western Himalaya, India using remote sensing satellite images , 2020, Geocarto International.

[17]  Yueming Hu,et al.  Deep Learning Segmentation and Classification for Urban Village Using a Worldview Satellite Image Based on U-Net , 2020, Remote. Sens..

[18]  Diofantos G. Hadjimitsis,et al.  The use of remote sensing for maritime surveillance for security and safety in Cyprus , 2020, Defense + Commercial Sensing.

[19]  Wataru Takeuchi,et al.  Building footprint extraction in Yangon city from monocular optical satellite image using deep learning , 2020, Geocarto International.

[20]  H. Hassani,et al.  Lithological mapping in Sangan region in Northeast Iran using ASTER satellite data and image processing methods , 2020, Geology, Ecology, and Landscapes.

[21]  Patrick Hostert,et al.  Detailed agricultural land classification in the Brazilian cerrado based on phenological information from dense satellite image time series , 2019, Int. J. Appl. Earth Obs. Geoinformation.

[22]  Leonid Ivanovsky,et al.  Urban areas analysis using satellite image segmentation and deep neural network , 2019, E3S Web of Conferences.

[23]  Elizaveta Zabolotskikh,et al.  Severe Marine Weather Systems During Freeze-Up in the Chukchi Sea: Cold-Air Outbreak and Mesocyclone Case Studies From Satellite Multisensor Measurements and Reanalysis Datasets , 2019, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[24]  Robert Stewart,et al.  Apache Spark Accelerated Deep Learning Inference for Large Scale Satellite Image Analytics , 2019, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[25]  P. Gaur.  Satellite Image Bathymetry and ROV Data Processing for Estimating Shallow Water Depth in Andaman region, India , 2019, 81st EAGE Conference and Exhibition 2019.

[26]  Agfianto Eko Putra,et al.  Ship Identification on Satellite Image Using Convolutional Neural Network and Random Forest , 2019, IJCCS (Indonesian Journal of Computing and Cybernetics Systems).

[27]  Tang-Huang Lin,et al.  The Environmental Effects of Urban Development in Hanoi, Vietnam from Satellite and Meteorological Observations from 1999–2016 , 2019, Sustainability.

[28]  Yuan Shen,et al.  Cloud Detection for FY Meteorology Satellite Based on Ensemble Thresholds and Random Forests Approach , 2018, Remote. Sens..

[29]  José A. M. Demattê,et al.  Multi-Temporal Satellite Images on Topsoil Attribute Quantification and the Relationship with Soil Classes and Geology , 2018, Remote. Sens..

[30]  P. Cabral,et al.  Satellite image fusion to detect changing surface permeability and emerging urban heat islands in a fast-growing city , 2018, PloS one.

[31]  Catherine Collier,et al.  Assessing the potential for satellite image monitoring of seagrass thermal dynamics: for inter- and shallow sub-tidal seagrasses in the inshore Great Barrier Reef World Heritage Area, Australia , 2018, Int. J. Digit. Earth.

[32]  Olena Dubovyk,et al.  Regional-scale monitoring of cropland intensity and productivity with multi-source satellite image time series , 2018 .

[33]  Patrick Lambert,et al.  3-D Deep Learning Approach for Remote Sensing Image Classification , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[34]  Lei Guo,et al.  When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNs , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[35]  Xiaoqiang Lu,et al.  Remote Sensing Image Scene Classification: Benchmark and State of the Art , 2017, Proceedings of the IEEE.

[36]  Stefan Voigt,et al.  Satellite Image Analysis for Disaster and Crisis-Management Support , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[37]  Samabia Tehsin,et al.  Target Classification of Marine Debris Using Deep Learning , 2022, Intelligent Automation & Soft Computing.

[38]  W. Emery,et al.  Coastal Marine Debris Detection and Density Mapping With Very High Resolution Satellite Imagery , 2022, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[39]  T. Tu,et al.  EVALUATION OF MANGROVE REHABILITATION AFTER BEING DESTROYED BY CHEMICAL WARFARE USING REMOTE SENSING TECHNOLOGY: A CASE STUDY IN CAN GIO MANGROVE FOREST IN MEKONG DELTA, SOUTHERN VIETNAM , 2021, Applied Ecology and Environmental Research.

[40]  Maria Trocan,et al.  Unsupervised Change Detection Analysis in Satellite Image Time Series Using Deep Learning Combined With Graph-Based Approaches , 2020, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[41]  D. van Soest,et al.  Satellite-based tree cover mapping for forest conservation in the drylands of Sub Saharan Africa (SSA): Application to Burkina Faso gazetted forests , 2019, Development Engineering.

[42]  Kemal Polat,et al.  CLASSIFICATION OF DIFFERENT FOREST TYPES wITH MACHINE LEARNING ALGORITHMS , 2016 .

[43]  R. Abedi,et al.  Estimation and Mapping Forest Attributes Using "k Nearest Neighbor" Method on IRS-P6 LISS III Satellite Image Data , 2015 .

[44]  Harsh Sadawarti,et al.  Hybrid Algorithm of Cuckoo Search and Particle Swarm Optimization for Natural Terrain Feature Extraction , 2015 .