Research Article
Performance Evaluation of Fast DCP Algorithm for Single Image Dehazing
@INPROCEEDINGS{10.1007/978-3-031-28975-0_11, author={I. Sravanthi and A. Sudha Madhavi and G. Venkata Pavan and B. Karthik Sai Kiran and A. Bhaavan Sri Sailesh and Ch. V V Santhosh Kumar and Ch. Venkateswara Rao}, title={Performance Evaluation of Fast DCP Algorithm for Single Image Dehazing}, proceedings={Cognitive Computing and Cyber Physical Systems. Third EAI International Conference, IC4S 2022, Virtual Event, November 26-27, 2022, Proceedings}, proceedings_a={IC4S}, year={2023}, month={3}, keywords={Computer Vision Computational Time Dark Channel Prior Dehazing Object Detection Segmentation Scattering}, doi={10.1007/978-3-031-28975-0_11} }- I. Sravanthi
A. Sudha Madhavi
G. Venkata Pavan
B. Karthik Sai Kiran
A. Bhaavan Sri Sailesh
Ch. V V Santhosh Kumar
Ch. Venkateswara Rao
Year: 2023
Performance Evaluation of Fast DCP Algorithm for Single Image Dehazing
IC4S
Springer
DOI: 10.1007/978-3-031-28975-0_11
Abstract
Poor weather circumstances including fog, dust, and atmospheric dispersion of other particles can degrade the clarity of photos taken in outdoor settings. High-level computer vision tasks like picture segmentation and object detection may become more difficult as a result of this issue. However, earlier research on image dehazing, such as Dark Channel Prior (DCP), suffers from a significant computing burden and degradation of the original image, such as oversaturation and halos. In this work, an improved image dehazing approach (Fast DCP) based on down sampling has been proposed. The proposed algorithm executes the dehazing of a haze image with a smaller amount computational time without degrading the quality of the image. The performance measures of proposed algorithm have been analysed in terms of PSNR, MMSE and SSIM and compared with existing DCP algorithm. The simulation results proven that, the computational time for proposed algorithm has been reduced by 70% when compared to DCP without degrading image quality.
