Deep learning model for real-time image compression in Internet of Underwater Things (IoUT)
- PDF / 3,066,982 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 3 Downloads / 232 Views
SPECIAL ISSUE PAPER
Deep learning model for real‑time image compression in Internet of Underwater Things (IoUT) N. Krishnaraj1 · Mohamed Elhoseny2 · M. Thenmozhi3 · Mahmoud M. Selim4 · K. Shankar5 Received: 22 February 2019 / Accepted: 2 May 2019 © Springer-Verlag GmbH Germany, part of Springer Nature 2019
Abstract Recently, the advancements of Internet-of-Things (IoT) have expanded its application in underwater environment which leads to the development of a new field of Internet of Underwater Things (IoUT). It offers a broader view of applications such as atmosphere observation, habitat monitoring of sea animals, defense and disaster prediction. Data transmission of images captured by the smart underwater objects is very challenging due to the nature of underwater environment and necessitates an efficient image transmission strategy for IoUT. In this paper, we model and implement a discrete wavelet transform (DWT) based deep learning model for image compression in IoUT. For achieving effective compression with better reconstruction image quality, convolution neural network (CNN) is used at the encoding as well as decoding side. We validate DWT–CNN model using extensive set of experimentations and depict that the presented deep learning model is superior to existing methods such as super-resolution convolutional neural networks (SRCNN), JPEG and JPEG2000 in terms of compression performance as well as reconstructed image quality. The DWT–CNN model attains an average peak signal-to-noise ratio (PSNR) of 53.961 with average space saving (SS) of 79.7038%. Keywords Deep learning · Image compression · IoUT · Underwater · Image reconstruction
1 Introduction * K. Shankar [email protected] N. Krishnaraj [email protected] Mohamed Elhoseny [email protected] M. Thenmozhi [email protected] Mahmoud M. Selim [email protected] 1
Department of Computer Science and Engineering, SASI Institute of Technology and Engineering, Tadepalligudem, Andhra Pradesh, India
2
Faculty of Computers and Information, Mansoura University, Mansoura, Egypt
3
Department of IT, SRM Institute of Science and Technology, Kanchipuram, Tamil Nadu, India
4
Department of Mathematics, Al‑Aflaj College of Science and Human Studies, Prince Sattam Bin Abdulaziz University, Al Kharj, Saudi Arabia
5
School of Computing, Kalasalingam Academy of Research and Education, Krishnankoil, India
Internet-of-Things (IoT) connects different objects in the world through Internet and exchanges information with one another with no or less human involvement [1, 23]. Recently, some studies reported the significance of IoT in underwater and outlook the world-wide network of underwater sensor nodes as well as intelligent interlinked underwater objects as a fundamental part of the IoT ecosystem, named as the Internet of Underwater Things (IoUT) [2]. IoUT is a scientific evolution of computing and communication. It is termed as a global network of interlinked underwater objects with digital unit [3]. They observe, understand
Data Loading...
