Fast color balance and multi-path fusion for sandstorm image enhancement
- PDF / 5,664,674 Bytes
- 8 Pages / 595.276 x 790.866 pts Page_size
- 6 Downloads / 312 Views
ORIGINAL PAPER
Fast color balance and multi-path fusion for sandstorm image enhancement Bo Wang1 · Bowen Wei1 · Zitong Kang1 · Li Hu1 · Chongyi Li2 Received: 5 June 2020 / Revised: 15 August 2020 / Accepted: 14 September 2020 © Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Outdoor images captured during sandstorm weather condition frequently yield color cast and poor visibility, which causes some applications to fail in computer vision, such as video surveillance and object recognition systems. In this paper, a fast color balance method followed by an effective fusion model is proposed to enhance the sandstorm-degraded images. Firstly, color channel compensation and piece-wise affine transform balance the aberrant pixels obtained by camera and remove color cast. Then, multi-path fusion comprising of underexposure and contrast-enhanced inputs is used for visibility enhancement, where saturation and Laplacian contrast are measured as weight maps and constructed for Gaussian pyramids. In order to reduce block effects and artifacts of the reconstructed image, we introduce the multi-scale strategy for each path. Experimental results of both synthetic and real-world sandstorm images demonstrate that the proposed color balance method features high computational efficiency and performs much better than comparative methods in terms of image quality. In addition, our fusion-based method also outperforms existing enhancement algorithms of sandstorm image via qualitative and quantitative evaluations. Keywords Sandstorm image · Color balance · Multi-path fusion · Weight maps
1 Introduction Poor visibility of images caused by inclement weather condition seriously influences the performance of outdoor object recognition, video surveillance systems, remote sensing systems and so on. In particular, compared with hazy images, sandstorm images exhibit undesirable color shift effects, very low contrast and visibility due to floating sand-dust particles absorbing and scattering the incident light to the lens of cameras. Therefore, the large absorption of blue hue of the spectrum by atmospheric particles results in characteristic distributions of RGB color histograms, which makes the sandstorm images show brown, yellow or even orange in different situations.
B
Bo Wang [email protected]
1
School of Physics and Electronic-Electrical Engineering, Ningxia University, Yinchuan 750021, People’s Republic of China
2
School of Computer Science and Engineering, Nanyang Technological University, Singapore 639798, Singapore
Intuitively, color constancy-based methods can be implemented to correct poor illumination and color-biased images, thus restoring color information of objects and scenes. There are a number of classic and computationally efficient approaches used for estimating the color of the light source and achieving color constancy, i.e., Grey-World (GW) [1], Max-RGB (MRGB) [2], Shades-of-Grey (SoG) [3], GreyEdge (GE) [4], Weighted Grey-Edge (Weighted-GE) [5]. On the other hand, in order to enhance visibility
Data Loading...
