To solve the problem that the dark channel prior algorithm is susceptible to white objects or bright areas, which leads to inaccurate estimation of atmospheric light and transmission, a dark channel prior image fog removal algorithm based on superpixel segmentation is proposed. Firstly, the simple linear iterative clustering superpixel algorithm is used to improve the dark channel prior. Secondly, the foggy image is segmented by superpixel segmentation by using the improved dark channel before obtaining superpixel blocks,and then the local atmospheric light value is calculated for each superpixel block and the average value is taken. Then, the gamma correction is performed on the coarse transmission map, and the average gradient value is used as a weight to fuse the weights of the coarse transmission map and the corrected transmission map to obtain the final transmission map. Finally, the inverse process of the atmospheric scattering model is used to obtain the dehazing image. The experimental results show that superpixel segmentation solves the problem of the dark channel prior algorithm to estimate the atmospheric light’s dependence on the brightest pixel. The proposed algorithm can improve the clarity and retain the texture details of the image well and is superior to other comparison algorithms.
WANGYuhang, YANGKai, ZHANGJinghui, et al.A fusion algorithm for underwater polarization image e-nhancement[J].Journal of Chongqing University of Technology(Natural Science), 2024, 38(7): 127-132. (in Chinese)
[4]
CAIB, XUX, JIAK, et al. DehazeNet: an end-to-end system for single image haze removal[J]. IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society, 2016, 25(11): 5187-5198.
[5]
SALAZAR-COLORESS, CRUZ-ACEVESI. Single image dehazing using a multilayer perceptron[J]. Journal of Electronic Imaging, 2018, 27(4): 043022.
WANGHe, HANLei. Image dehazing algorithm based on Res2net and pyramid pooling[J]. Journal of Test and Measurement Technology, 2023, 37(5): 455-460. (in Chinese)
[8]
HEK, SUNJ, TANGX. Single image haze removal using dark channel prior[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009: 1956-1963.
[9]
WANGJ B, HEN, ZHANGL L, et al. Single image dehazing with a physical model and dark channel prior[J]. Neurocomputing, 2015, 149: 718-728.
[10]
ZHUQ, MAI J, SHAOL. A fast single image haze removal algorithm using color attenuation prior[J]. IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society, 2015, 24(11): 3522-3533.
[11]
DAIQ, FANZ, SONGQ, et al. Polarization defogging method for color image based on automatic estimation of global parameters[J]. Journal of Applied Optics, 2018, 39(4): 58-63.
[12]
XUH, TANY B, LIUB W, et al. Image dehazing method based on superpixels and dark channel prior[J]. Periodical of Ocean University of China, 2020, 50(10): 118-124.
[13]
LIZ, ZHENGX, BHANUB, et al. Fast region-adaptive defogging and enhancement for outdoor images containing sky[C]//2020 25th International Conference on Pattern Recognition (ICPR), 2020: 8267-8274.
[14]
YANW, CUIL. Image dehaze algorithm based on improved atmospheric scattering models[J]. IEEE Access, 2024, 12: 98971-98976.
[15]
NARASIMHANS G, NAYARS K. Vision and the atmosphere[J]. International Journal of Computer Vision, 2002, 48(3): 233-254.
[16]
JIANGY, SUNC, ZHAOY, et al. Image dehazing using adaptive bi-channel priors on superpixels[J]. Computer Vision and Image Understanding, 2017, 165: 17-32.
[17]
ACHANTAR, SHAJIA, SMITHK, et al. SLIC superpixels compared to state-of-the-art superpixel methods[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 2274-2282.
[18]
YANGM, LIZ, LIUJ. Super-pixel based single image haze removal[C]//2016 Chinese Control and Decision Conference(CCDC), 2016: 1965-1969.
[19]
LUZ, LONGB, LIK, et al. Effective guided image filtering for contrast enhancement[J]. IEEE Signal Processing Letters, 2018, 25(10): 1585-1589.
[20]
HUK, ZENGQ, WANGJ, et al. A method for defogging sea fog images by integrating dark channel prior with adaptive sky region segmentation[J]. Journal of Marine Science and Engineering, 2024, 12(8): 1255.
[21]
LIB, RENW, FUD, et al. Benchmarking single image dehazing and beyond[J]. IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society, 2018, 28(1): 492-505.
[22]
MITTALA, SOUNDARARAJANR, BOVIKA C. Making a“completely blind”image quality analyzer[J]. IEEE Signal Processing Letters, 2013, 20(3): 209-212.