An Overview of Different Approaches used for Processing Satellite Images

In country such as India due to monsoon and frequent climatic changes leads to natural disasters such as floods, drought, landslides, cyclones, forest fire, earthquake and so on. The post disaster badly impacts on human life, economy and environment. As remote sensing technology advanced, the satellite images with high resolution can be processed and analyzed to get the required results. These analyzed results can be used for rescue operations after disaster or to predict any disasters before their occurrences. Some of the applications such as post disaster event management widely use onboard processing to get faster analyzed results. Various operations such as satellite image- enhancement, compression, classification and segmentation are performed on satellite images. Results of these techniques mainly used in applications such as disaster management, Land Use Land Cover, Change detection, landslide and many more. In recent days, satellite image processing are performed using new technical aspects such as deep learning, Artificial intelligence and machine learning to get fast and more accurate results. Edge-Computing-Enabled Deep Learning and Leveraging Deep Learning are the approaches used for satellite image enhancement. Panoptic Segmentation of Multispectral Satellite Images approaches are mainly used for satellite image segmentation. Deep Learning based approach and Genererative Adverserial Network architecture are applied to get change detection in satellite images. Lossless algorithm for hyperspectral data compression and Neural network lossy compression techniques are preferably used for satellite image compression. Approaches such as Hybrid data model centric approach and Multiscale Convolutional Neural Network are applied to perform object detection. And also machine learning algorithms are mainly used for classification of satellite images. This paper provides comparative study survey on these various approaches used for processing of satellite images.