Near-infrared guided color image dehazing
read more
Citations
Review of Video and Image Defogging Algorithms and Related Studies on Image Restoration and Enhancement
Recent advances in image dehazing
Filmy Cloud Removal on Satellite Imagery with Multispectral Conditional Generative Adversarial Nets
Automatic and Accurate Shadow Detection Using Near-Infrared Information
Unified multi-spectral pedestrian detection based on probabilistic fusion networks
References
Guided Image Filtering
Guided image filtering
Single image dehazing
Edge-preserving decompositions for multi-scale tone and detail manipulation
Single image haze removal using dark channel prior
Related Papers (5)
Frequently Asked Questions (19)
Q2. What is the reason why the authors have proposed an image dehazing method?
The intuition behind this technique is that NIR has deep penetration due to its long wavelength and thus according to the Rayleigh’s scattering law, the details of distant objects can be well preserved in the NIR image.
Q3. What is the process of transferring the details from the NIR image to the color image?
The fact that NIR penetrates further than the visible band due to its long wavelength allows us to transfer the details from the NIR image to the color image.
Q4. How do the authors compute the airlight color?
The authors have estimated the airlight color by exploiting the dissimilarity between the RGB and the NIR, and developed an image dehazing procedure to enforce the NIR gradient constraint through an optimization framework.
Q5. What is the effect of the proposed image dehazing method on distant objects?
Experimental results on real captured images demonstrate that the proposed image dehazing method unveils the details of the scene with less noise and better color distribution.
Q6. What is the idea of the paper?
The idea the authors proposed here to estimate the airlight color consists of finding a local patch Ω with pixels having large similarities, followed by searching an airlight color that leads to the smallest correlation between t and J.
Q7. How can the authors achieve the near-infrared spectrum?
The near-infrared spectrum can be easily acquired by using off-the-shelf digital cameras with minor modifications [6], or potentially through a single RGBN camera, in which multiple images with different properties can be captured simultaneously [7].
Q8. What is the first step of the proposed scheme?
In order to recover J as formulated in (1), the first step of their approach is to estimate the global airlight color A. A commonly used idea in literatures is to approximate the airlight color from the most hazed region in the scene, where the transmission tends to be zero.
Q9. How long does it take to process a 1 megapixel color image?
From the experiments, it takes around 60 seconds to process a 1 megapixel color image using matlab on a laptop with 2.6GHz processor and 4G RAM.
Q10. How do the authors determine the density of a haze map?
By using the pair of RGB and NIR images, the authors are able to infer the density of haze and thus, pixels that have large similarities are selected to generate a local patch, within which the authors search for an airlight color A that leads to the smallest correlation, measured by Pearson’s correlation coefficient C, between t and J. Please refer to [3] for the detailed definition of C. Specifically, the authors update A’s components using the steepest decent method by minimizing the Equation (4).
Q11. What is the main criteria for a good local patch?
A good local patch should meet two major criteria: i) pixels within the patch should have intermediate level of haze so that both J and A contribute to the observed intensity value The authorin equation (1); ii) pixels within the patch should have similar properties (i.e., surface reflectance).
Q12. What is the common method of estimating the airlight color?
Most current literatures [2][4] simply approximate the airlight color from the brightest region in the scene by assuming such regions are usually at infinity and have the most haze.
Q13. What are the main reasons why haze is a problem in landscape photography?
Haze and mist significantly reduce the visibility in landscape photographs, which impact visual quality and bring difficulties for many computer vision applications [1].
Q14. What is the main contribution of the paper?
Their main contribution are in two folds:• Propose an optimization framework to resolve image de-hazing problem guided with NIR gradient constraints.•
Q15. What is the advantage of the near-infrared?
The advantage of deep penetration of the near-infrared (NIR) due to its long wavelength (∼ 1um) makes it possible to unveil the details, which could be completely lost in the visible band.
Q16. How can the authors recover the haze-free image?
By solving the optimization problem stated in (9) using Iteratively Reweighted Least Squares (IRLS) with initialized J0 and t0 derived from (7) and (5), the authors can recover the haze-free image J and the transmission map t simultaneously.
Q17. What is the cause of the haze effect?
the haze effect is due to the presence of particles in the atmosphere, with comparable size to the wavelength in the visible band (haze ∼ 0.1um, mist ∼ 1um), that absorb and scatter light.
Q18. What are the parameters that control the level of detail transfer?
(10)In equation (9), λ2 and λ3 are pre-determined parameters with small values (0.01 in their experiments), and λ1 controls the level of detail transfer that comes from the NIR image.
Q19. What is the effect of the image dehazing method?
Comparing to Schaul et al.’s work [8], since their approach adopts the haze model, the authors can not only selectively enhance the details based on the transmission map, but also well recover the original color of the scene.