IJBTT

Real Time Dehazing System for Automobiles
	© 2020 by IJCTT Journal
	Volume-68 Issue-3
	Year of Publication : 2020
	Authors : Basil Eldho, Shruti Manmadhan, Susan Jacob, Prof. Joby George HOD
	DOI :  10.14445/22312803/IJCTT-V68I3P120

How to Cite?

Basil Eldho, Shruti Manmadhan, Susan Jacob, Prof. Joby George HOD, "Real Time Dehazing System for Automobiles," International Journal of Computer Trends and Technology, vol. 68, no. 3, pp. 99-102, 2020. Crossref, 10.14445/22312803/IJCTT-V68I3P120

Abstract
Cars have been a common mode of transport ever since their innovation. Fog, smoke and heavy rains pose huge hindrances of sight for people when they drive. This has led to many dangerous accidents especially when it comes to driving at high altitudes or narrow roads. Hence, we propose a real-time image de-hazing system using machine learning and convolutional neural networking concepts. It captures the path in front of the car as video which is then converted to frames and removes all the factors that reduce the clarity of the image. To do so, the loss per pixel is calculated. Here, training sets are utilized in order to obtain better outcomes. Hazed and dehazed images are analyzed and compared and then converted back to dehazed video. It requires a huge refresh rate to make it real time and finally achieve the output.

Keywords
Convolutional neural networks, machine learning, digital image processing, training data set, layers, dehaze.

Reference
[1] Wajahat Akhtar, Sergio Roa-Ovalle, Florian Baumann, “Real Time Single Image and Soil Removal Using CNNs”, Computer Science in Cars Symposium
[2] Cameron Hodges, Mohammed Bennamoun, Hossein Rahmani, “Single image dehazing using deep neural networks”, Pattern Recognition Letters
[3] Alona Golts, Daniel Freedman, Michael Elad, Unsupervised Single Image Dehazing Using Dark Channel Prior Loss, IEEE Transactions on Image Processing.
[4] A. Alajarmeh, R.A. Salam, K. Abdulrahim, M.F. Marhusin, A.A. Zaidan, B.B. Zaidan, “Real-time Framework for Image Dehazing Based on Linear Transmission and Constant-time Airlight Estimation”, Information Sciences
[5] Wenqi Ren, Jingang Zhang, Xiangyu Xu, Lin Ma, Xiaochun Cao, Gaofeng Meng, Wei Liu, “Deep Video Dehazing With Semantic, Segmentation”, IEEE Transactions on Image Processing
[6] Wencheng Wang, Xiaohui Yuan, Xiaojin Wu, Yunlong Liu, “Fast Image Dehazing Method Based on Linear Transformation”, IEEE Transactions on Multimedia
[7] Chongyi Li, Jichang Guo, Fatih Porikli, Huazhu Fu, Yanwei Pang, “A Cascaded Convolutional Neural Network for Single Image Dehazing”, IEEE Access
[8] Faming Fang, Tingting Wang, Yang Wang, Tieyong Zeng, Guixu Zhang, “Variational Single Image Dehazing for Enhanced Visualization”, IEEE Transactions on Multimedia
[9] Venkateswaran S, Devisri R, Karthika C, Karthika U, “Video Dehazing Approach Using Structure Features Prior”, International Journal of Computer Trends and Technology