A plexus‐convolutional neural network framework for fast remote sensing image super‐resolution in wavelet domain

Abstract

Satellite image processing has been widely used in recent years in a number of applications such as land classification, Identification transfer, resource exploration, super-resolution image, etc. Due to the orbital location, revision time, quick view angle limitations, and weather impact, the satellite images are challenging to manage. There are many types of resolution, such as spatial, spectral, and temporal. Still, in our case, we concentrated on spatial image resolution to super resolve the images from low-resolution images. For remote sensing image super-resolution fast wavelet-based super-resolution (FWSR), we propose a novel, fast wavelet-based plexus framework that performs super-resolution convolutional neural network (SRCNN)-like extraction of features based on three hidden layers. First, wavelet sub-band images are combined into a pre-defined full-scale data training factor, including approximation and interchangeable stand-alone units (frequency subbands). Second, to speed up image recovery, mapping the sub-band image of the wavelet is then measured using its approximate image. Third, the added sub-pixel layer at the end of the network model is intended to reproduce image quality using a plexus framework. The approximation sub-band images obtained after discrete wavelet transform wavelet decomposition are used as input rather than the original image because of their highfrequency data and preserved characteristics. Five current super-resolution neural network approaches are compared with the proposed technique and tested on three pubic satellite image datasets and two benchmark datasets. The experimental findings are well compared qualitatively and quantitatively. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

A deep inverse convolutional neural network-based semantic classification method for land cover remote sensing images

“…The inverse convolutional network part adopts the mirror structure of convolutional network, which aims at reconstructing the shape of the input target, so the multilevel inverse convolutional structure is also able to capture the shape details of different levels of the land-covered remote sensing images like convolutional network. In the convolutional network, the low-level features can describe the whole target rough information, such as target location, general shape, etc., while the more complex high-level features have classification characteristics and contain more target details 19 .…”

Deep Learning Based Automatic Vehicle License Plate Recognition System for Enhanced Vehicle Identification

“…A deep learning [21]system called ConvNet, also referred to as the Convolutional Neural Network (CNN), uses input data and applies biases and weights to various components. The input is then divided into its numerous components, as seen in Algorithm 1.…”

Enhanced dual branches network for arbitrary‐scale image super‐resolution

“…During training, 16 degraded patches of size 48*48 are used for a batch input. For arbitrary-scale upsampling in the EDBNet, the authors sample random scale factors in uniform distribution U (1,4). Each instance in a batch has different upscale target.…”

“…Introduction: Image super-resolution, as a classic image processing technique, aims to produce a high-resolution (HR) image based on a degraded low-resolution (LR) image. In recent years, single image superresolution (SISR) methods with deep convolutional neural networks (CNNs) [1][2][3][4][5] have been significantly developed over traditional superresolution (SR) methods and extensively applied in various fields, such as medical images [6,7] and satellite imaging [8]. However, most existing SISR pre-trained models can only perform single image restoration of the LR image which increase computational costs.…”