Image defogging method and system
An image and input image technology, applied in the field of image processing and computer vision, can solve the problem of easy to produce halo effect, the color of the image is too saturated, etc., and achieve the effect of fast and effective dehazing.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Publication Date
- 2016-03-30
- Estimated Expiration
- Not applicable · inactive patent
Smart Images
Figure 1 Figure 2 Figure 3
Abstract
Description
technical field
[0001] The invention belongs to the field of image processing and computer vision, and in particular relates to an image defogging method and system thereof. Background technique
[0002] At present, for image dehazing, the research work mainly focuses on the dehazing of a single image. Commonly used image defogging methods include Retinex method, Fattal method, He method and Tarel method.
[0003] The Retinex method assumes that the input degraded image is the product of the brightness image and the reflection image. By removing or reducing the influence of the brightness image, the reflective image that reflects the essence of the scene is preserved as much as possible to remove the fog. However, it uses the non-linear function value of the chromaticity of the input image to compensate for the loss of color information in the process of color information processing, and cannot restore the true color of the scene.
[0004] The Fattal method first assumes ...
Examples
Embodiment Construction
[0022] Such as figure 1 As shown, the present invention provides a kind of image defogging method, and it comprises the following steps:
[0023] Step 1, collecting images containing fog;
[0024] Step 2, obtain the initial atmospheric scattering function according to the boundary conditions of the image;
[0025] Step 3, using recursive bilateral filtering to refine the initial atmospheric scattering function;
[0026] Step 4, use the recursive bilateral filter again to obtain the local contrast;
[0027] Step five, based on local contrast, adaptively process fog regions with different concentrations;
[0028] Step 6. According to the image degradation model, the dehazing result is quickly obtained, and the final result is output and displayed after adjusting the tone.
[0029] Preferably, in step 2, the global atmospheric light A is obtained according to the image degradation model, and a window ω(i) centered on the pixel i is used to perform minimum value filtering on t...