Single Image Defogging Method Combined with Multi-exposure Fusion Approach Based on Parameter Dynamic Selection

A single image defogging method combined with multi-exposure fusion approach based on parameter dynamic selection is proposed in this paper. Gamma correction was used to improve the contrast of the haze source image, and spatial linear saturation stretch was used to enhance the color saturation. Then, multi-exposure fusion scheme based on dynamic parameter selection is used to collect the patches with the best contrast, saturation and texture structure from each image and fuse them into a single fog-free image. The experimental results show that the proposed method is effective in defogging.

[1]  Di Wang,et al.  A Phase Congruency and Local Laplacian Energy Based Multi-Modality Medical Image Fusion Method in NSCT Domain , 2019, IEEE Access.

[2]  Zia-ur Rahman,et al.  Retinex processing for automatic image enhancement , 2004, J. Electronic Imaging.

[3]  Yuan-Kai Wang,et al.  Single Image Defogging by Multiscale Depth Fusion , 2014, IEEE Transactions on Image Processing.

[4]  Fabrizio Russo.  An image enhancement technique combining sharpening and noise reduction , 2002, IEEE Trans. Instrum. Meas..

[5]  Alan Conrad Bovik,et al.  Referenceless Prediction of Perceptual Fog Density and Perceptual Image Defogging , 2015, IEEE Transactions on Image Processing.

[6]  Zeyun Yu,et al.  A fast and adaptive method for image contrast enhancement , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[7]  Gabriel Thomas,et al.  Histogram Specification: A Fast and Flexible Method to Process Digital Images , 2011, IEEE Transactions on Instrumentation and Measurement.

[8]  Dacheng Tao,et al.  DehazeNet: An End-to-End System for Single Image Haze Removal , 2016, IEEE Transactions on Image Processing.

[9]  Yi-Chung Hu,et al.  Optimization Theory, Methods, and Applications in Engineering 2014 , 2012 .

[10]  Yanjing Sun,et al.  An Image Fusion Method Based on Sparse Representation and Sum Modified-Laplacian in NSCT Domain , 2018, Entropy.

[11]  Adrian Galdran,et al.  Image dehazing by artificial multiple-exposure image fusion , 2018, Signal Process..

[12]  Jiayi Zhou,et al.  A novel multi-focus image fusion approach based on image decomposition , 2017, Inf. Fusion.

[13]  Zhang Shu-qing,et al.  FAST SEGMENTATION METHOD OF HIGH-RESOLUTION REMOTE SENSING IMAGE , 2009 .

[14]  J. Iqbal,et al.  Single image haze removal using improved dark channel prior , 2013, 2013 5th International Conference on Modelling, Identification and Control (ICMIC).

[15]  Dianwei Liu,et al.  FAST SEGMENTATION METHOD OF HIGH-RESOLUTION REMOTE SENSING IMAGE: FAST SEGMENTATION METHOD OF HIGH-RESOLUTION REMOTE SENSING IMAGE , 2009 .

[16]  Huan Wang,et al.  A Novel Multi-exposure Image Fusion Approach Based on Parameter Dynamic Selection , 2018, Proceedings of 2018 Chinese Intelligent Systems Conference.

[17]  Qiang Huang,et al.  Detection and Recognition of Abnormal Running Behavior in Surveillance Video , 2012 .