A Fast Image Dehazing Algorithm Using Morphological Reconstruction
| Autor: | Eduardo Cabal-Yepez, Sergio Ledesma, Luis M. Ledesma-Carrillo, J. M. Ramos-Arreguin, Guillermo Botella, Sebastián Salazar-Colores |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Haze
Channel (digital image) Machine vision Scattering Structural similarity Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Environmental pollution 02 engineering and technology Iterative reconstruction Computer Graphics and Computer-Aided Design Grayscale Transmission (telecommunications) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Algorithm Software Image restoration |
| Zdroj: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. |
| ISSN: | 1941-0042 |
| Popis: | Outdoor images are used in a vast number of applications, such as surveillance, remote sensing, and autonomous navigation. The greatest issue with these types of images is the effect of environmental pollution: haze, smog, and fog originating from suspended particles in the air, such as dust, carbon and water drops, which cause degradation to the image. The elimination of this type of degradation is essential for the input of computer vision systems. Most of the state-of-the-art research in dehazing algorithms is focused on improving the estimation of transmission maps, which are also known as depth maps. The transmission maps are relevant because they have a direct relation to the quality of the image restoration. In this paper, a novel restoration algorithm is proposed using a single image to reduce the environmental pollution effects, and it is based on the dark channel prior and the use of morphological reconstruction for the fast computing of transmission maps. The obtained experimental results are evaluated and compared qualitatively and quantitatively with other dehazing algorithms using the metrics of the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM) index; based on these metrics, it is found that the proposed algorithm has improved performance compared to recently introduced approaches. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|