A Real-Time Haze Removal & Mosaicing using Rapid Prototype Hardware
Sai Venu Prathap Katari1, K. Kishore Kumar2, K Gopi3

1Dr. Sai Venu Prathap K., Associate Professor, Department. of ECE, Sri Venkateswara College of Engineering (SVCE), Tirupati (A.P), India.
2K Kishore Kumar,  Assistant Professor, Dept. of ECE, Sri Venkateswara College of Engineering (SVCE), (A.P), India.
3K Gopi,  Assistant Professor, Department. of ECE, SVCE Tirupati. (A.P), India.
Manuscript received on July 06, 2020. | Revised Manuscript received on July 25, 2020. | Manuscript published on August 10, 2020. | PP: 29-34 | Volume-9 Issue-10, August 2020 | Retrieval Number: 100.1/ijitee.J73700891020 | DOI: 10.35940/ijitee.J7370.0891020
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: In this paper, a pivotal technique was proposed that reduces the haze and combines the haze free image to increase the Field of View (FoV) in real-time with a rapid prototype hardware device. The Initial focus is to reduce the haze in an image with Dark Channel Prior Technique and the FSD method is utilized to mosaic the haze free images. Low contrast may occur due to the scattering light, air particles or fog in nature which results in a haze image that needs to be reduced and enhance the image for better vicinity. Haze reduction approach depends on entropy and information fidelity. Our Haze free algorithm executes multiple phases such as dark channel prior computation, estimation and refinement of transmission map and restoration of RGB values. The second technique is the mosaic process that improves the field of view of a scene and the phases that execute are corner detection, extraction, geometric computation and blending. Our experimental results have shown better when compared to the other algorithms. The whole process is executed in real-time with a standalone device called Intel compute stick. 
Keywords: Haze, Dark Channel Prior, Mosaic, Steerable filters, FAST, Corner detection.