Optimal Compression of Remote Sensing Images Using Deep Learning during Transmission of Data

Industrial internet of things has grown quite popular in recent years and involves a large number of intelligent devices linked together to build a system that can investigate, communicate, gather and observe information. Due to this requirement, there is more demand for compression techniques which compresses data, leading to less usage of resources and low complexity. This is where Convolutional Neural Networks (CNN) play a large role in the field of computer vision, especially in places where high applications such as interpretation coupled with detection is required. Similarly, low-level applications such as image compression cannot be resolved using this methodology. In this paper, a compression technique for remote sensing images using CNN is proposed. This methodology incorporates CNN in a compact learning environment wherein the actual image that consists of structural data is coded using Lempel Ziv Markov chain algorithm. This process is followed by image reconstruction in order to obtain the actual image in high quality. Other methodologies such as optimized trunctiona, JPEG2000, JPEC and binary tree were compared using a large number of experiments in terms of space saving, reconstructed image quality and efficiency. The output obtained indicates that the proposed methodology shows effective improvement, attaining a 50 dB signal to noise ratio and space saving of 90%.

Download Full-text

A Novel Low-Complexity Frequency Estimation Algorithm for Industrial Internet-of-Things Applications

IEEE Transactions on Instrumentation and Measurement ◽

10.1109/tim.2020.3034629 ◽

2021 ◽

Vol 70 ◽

pp. 1-10

Author(s):

Giuseppe Campobello ◽

Antonino Segreto ◽

Nicola Donato

Keyword(s):

Internet Of Things ◽

Frequency Estimation ◽

Estimation Algorithm ◽

Low Complexity ◽

Industrial Internet Of Things ◽

Industrial Internet

Download Full-text

Curvelet Transform based Denoising of Multispectral Remote Sensing Images

Journal of Physics Conference Series ◽

10.1088/1742-6596/2089/1/012064 ◽

2021 ◽

Vol 2089 (1) ◽

pp. 012064

Author(s):

P. Lokeshwara Reddy ◽

Santosh Pawar ◽

S.L. Prathapa Reddy

Keyword(s):

Remote Sensing ◽

Signal To Noise Ratio ◽

Curvelet Transform ◽

Structural Similarity ◽

Spatial Location ◽

Multispectral Image ◽

Sensor Technology ◽

Remote Sensing Images ◽

Unequally Spaced ◽

Multispectral Remote Sensing

Abstract With the advent of sensor technology, the exertion of multispectral image (MSI) is comely omnipresent. Denoising is an essential quest in multispectral image processing which further improves recital of unmixing, classification and supplementary ensuing praxis. Explication and ocular analysis are essential to extricate data from remote sensing images for broad realm of supplications. This paper describes curvelet transform based denoising of multispectral remote sensing images. The implementation of curvelet transform is done by using both wrapping function and unequally spaced fast Fourier transform (USFFT) and they diverge in selection of spatial grid which is used to construe curvelets at every orientation and scale. The coefficients of curvelets are docket by a scaling factor, angle and spatial location criterion. This paper crisps on denoising of Linear Imaging Self Scanning Sensor (LISS) III images. The proposed denoising approach has also been collated with some existing schemes for assessment. The efficacy of proposed approach is analyzed with calculation of facet matrices such as Peak signal to noise ratio and Structural similarity at distinct variance of noise..

Download Full-text

СОЗДАНИЕ АРХИТЕКТУРЫ «РАСПРЕДЕЛЕННОГО СПУТНИКА» ДЛЯ НИЗКООРБИТАЛЬНЫХ ИНФОРМАЦИОННО-ТЕЛЕКОММУНИКАЦИОННЫХ СИСТЕМ НА ОСНОВЕ ГРУППИРОВКИ МИКРО- И НАНОСПУТНИКОВ

Aerospace technic and technology ◽

10.32620/aktt.2018.2.05 ◽

2018 ◽

pp. 33-43

Author(s):

Михаил Ефимович Ильченко ◽

Теодор Николаевич Нарытник ◽

Борис Михайлович Рассамакин ◽

Владимир Ильич Присяжный ◽

Сергей Владимирович Капштык

Keyword(s):

Remote Sensing ◽

Internet Of Things ◽

Transport Infrastructure ◽

Radio Link ◽

Industrial Internet Of Things ◽

Satellite Transmitter ◽

Telecommunication Systems ◽

The Earth ◽

Industrial Internet ◽

Distributed Satellite

Presented are the results of an analysis of the growing interest in the use of low Earth orbits (up to 1500 km high) for the introduction and development of the Internet of things (Internet of Things - IoT). Industrial Internet of things (Industrial Internet of Things-IIoT). Internet of things for remote areas (Remote Internet of Things - RioT, for the purposes of scientific research and economic use of natural resources, control of the development and operation of infrastructure projects, the operation of territorially distributed industrial production, transport infrastructure. Factors significantly limiting the further introduction of micro and nano satellites are given. The authors proposed to resolve this contradiction on the basis of the developed concept of creating the architecture of a "distributed satellite". As an example, the article considers possible applications of the distributed satellite architecture in two segments of the space information systems market: remote sensing of the Earth and telecommunication systems. The application of the "distributed satellite" in radar systems with synthesized aperture (SAR-system) was considered taking into account the requirements of the operators of satellite SAR-systems and consumers of their information. It is shown. that the use of the "distributed satellite" architecture in SAR-systems also makes it possible to realize the technology of multi-static radar with a "soft" interference base (from 200 m to 1 km). The scheme of organization and interaction of the "distributed satellite" in the satellite-transmitter on the platform of the micro satellite, which is the core of the satellite cluster, and several satellites-receivers on the cube-sat platform is presented. The functions performed by the satellite-transmitter, the inter-satellite radio link and the satellite-receiver are considered in detail. The work of the "distributed satellite" is illustrated by the presented structural diagram of the SAR-system for remote sensing of the Earth, a version of the architecture of the low-orbit satellite communication system and the scheme for constructing a satellite system for the provision of IoT services. In conclusion, it is noted that the architecture of the "distributed satellite" makes it possible to effectively use satellites of the class of micro/nano satellite (cube-sat) to create complex space-based information and telecommunication systems

Download Full-text

A Fast and Efficient Adaptive Threshold Rate Control Scheme for Remote Sensing Images

The Scientific World JOURNAL ◽

10.1100/2012/691413 ◽

2012 ◽

Vol 2012 ◽

pp. 1-6

Author(s):

Xiao Chen ◽

Xiaoqing Xu

Keyword(s):

Remote Sensing ◽

Rate Control ◽

Signal To Noise Ratio ◽

Computational Cost ◽

Rate Distortion ◽

Adaptive Threshold ◽

Remote Sensing Images ◽

Minimum Number ◽

Code Complexity ◽

Bit Planes

The JPEG2000 image compression standard is ideal for processing remote sensing images. However, its algorithm is complex and it requires large amounts of memory, making it difficult to adapt to the limited transmission and storage resources necessary for remote sensing images. In the present study, an improved rate control algorithm for remote sensing images is proposed. The required coded blocks are sorted downward according to their numbers of bit planes prior to entropy coding. An adaptive threshold computed from the combination of the minimum number of bit planes, along with the minimum rate-distortion slope and the compression ratio, is used to truncate passes of each code block during Tier-1 encoding. This routine avoids the encoding of all code passes and improves the coding efficiency. The simulation results show that the computational cost and working buffer memory size of the proposed algorithm reach only 18.13 and 7.81%, respectively, of the same parameters in the postcompression rate distortion algorithm, while the peak signal-to-noise ratio across the images remains almost the same. The proposed algorithm not only greatly reduces the code complexity and buffer requirements but also maintains the image quality.

Download Full-text

Optimal deep learning based image compression technique for data transmission on industrial Internet of things applications

Transactions on Emerging Telecommunications Technologies ◽

10.1002/ett.3976 ◽

2020 ◽

pp. e3976 ◽

Cited By ~ 5

Author(s):

Ben Sujitha ◽

Velmurugan Subbiah Parvathy ◽

E. Laxmi Lydia ◽

Poonam Rani ◽

Zdzislaw Polkowski ◽

...

Keyword(s):

Deep Learning ◽

Internet Of Things ◽

Image Compression ◽

Data Transmission ◽

Industrial Internet Of Things ◽

Compression Technique ◽

Industrial Internet

Download Full-text

End-to-End Super-Resolution for Remote-Sensing Images Using an Improved Multi-Scale Residual Network

Remote Sensing ◽

10.3390/rs13040666 ◽

2021 ◽

Vol 13 (4) ◽

pp. 666

Author(s):

Hai Huan ◽

Pengcheng Li ◽

Nan Zou ◽

Chao Wang ◽

Yaqin Xie ◽

...

Keyword(s):

Remote Sensing ◽

Feature Fusion ◽

Signal To Noise Ratio ◽

Model Performance ◽

Super Resolution ◽

Structural Similarity ◽

Remote Sensing Images ◽

Residual Network ◽

Multi Scale ◽

Information Image

Remote-sensing images constitute an important means of obtaining geographic information. Image super-resolution reconstruction techniques are effective methods of improving the spatial resolution of remote-sensing images. Super-resolution reconstruction networks mainly improve the model performance by increasing the network depth. However, blindly increasing the network depth can easily lead to gradient disappearance or gradient explosion, increasing the difficulty of training. This report proposes a new pyramidal multi-scale residual network (PMSRN) that uses hierarchical residual-like connections and dilation convolution to form a multi-scale dilation residual block (MSDRB). The MSDRB enhances the ability to detect context information and fuses hierarchical features through the hierarchical feature fusion structure. Finally, a complementary block of global and local features is added to the reconstruction structure to alleviate the problem that useful original information is ignored. The experimental results showed that, compared with a basic multi-scale residual network, the PMSRN increased the peak signal-to-noise ratio by up to 0.44 dB and the structural similarity to 0.9776.

Download Full-text