Vijaya Lakshmi THIRUMALA, Venkata SatyaNarayana KARANAM, Pratap Reddy LANKIREDDY, Aruna Kumari KAKUMANI, Rakesh Kumar YACHARAM

Haze-level prior approach to enhance object visibility under atmospheric degradation

Outdoor captured scenes are degraded by atmospheric particles and water droplets. Due to scattering and absorption effects in the atmosphere, degraded images lose contrast and color fidelity. Performances of the computer vision algorithms are bound to suffer from low-contrast scene radiance. In many single-image dehazing models, the larger the deviation in estimation of the key parameters such as transmission map and atmospheric light, the higher the halo artifacts and loss of fine details in the dehazed image. The available models assume that the scattering light is independent of wavelength, as the size of the atmospheric particles is larger compared to the wavelength of light. The model presented in this paper emphasizes the appropriate estimation of intensified transmission map from the hazy images by exploiting the scattering coeﬀicient in order to address the issues of haze concentrations. Experiments conducted on thick and thin hazy images provide an optimal estimation of the model parameters, which can be applied directly in real-time situations. The available models are observed to be inconsistent sometimes in the enhancement of contrast, saturation and color information either together or independently. The proposed model addresses these issues by extracting the haze-relevant features from the hazy images, such as hue disparity, contrast, and darkness, which yield more vivid saturation results. Moreover, the proposed model addresses different haze densities in the scene without the use of refinement filters

PDF

___

1] Liang D, Kaneko S, Hashimoto M, Iwata K, Zhao X et al. Robust object detection in severe imaging conditions using co-occurrence background model. International Journal of Optomechatronics 2014; 8 (1): 1559-9612. doi: 10.1080/15599612.2014.890686
[2] Liang J, Ren L, Ju H, Zhang W, Qu E. Polarimetric dehazing method for dense haze removal based on distribution analysis of angle of polarization. Optics Express 2015; 23 (9): 26146. doi: 10.1364/OE.23.026146
[3] He K, Sun J, Tang X. Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence 2011; 33 (12): 2341-2353. doi: 10.1109/TPAMI.2010.168
[4] Fang S, Xia X, Huo X, Chen C. Image dehazing using polarization effects of objects and airlight. Optics Express 2014; 22 (16). doi: 10.1364/OE.22.019523
[5] Lu H, Li Y, Zhang L, Serikawa S. Contrast enhancement for images in turbid water. Journal of the Optical Society of America 2015; 32 (5): 886-93. doi: 10.1364/JOSAA.32.000886
[6] Zhu Y, Tang G, Zhang X, Jiang J, Tian Q. Haze removal method for natural restoration of images with sky. Neurocomputing 2017; 275 (9): 499-510. doi: 10.1016/j.neucom.2017.08.055
[7] Farhan H, Jechang J. Visibility enhancement of scene images degraded by foggy weather conditions with deep neural networks. Journal of Sensors 2016; (2016): 3894832:1-3894832:9. doi: 10.1155/2016/3894832
[8] Alkholidi A. Free space optical communications — theory and practices. In: Mutamed Khatib (editor). Wireless Communications. 1st ed. INTECH 2014, pp. 159-212. doi: 10.5772/58884
[9] Makarau A, Richter R, Müller R, Reinartz P. Haze detection and removal in remotely sensed multispectral imagery. IEEE Transactions on Geoscience and Remote Sensing 2014; 52: 5895-5905. doi: 10.1109/TGRS.2013.2293662
[10] Rasti B, Scheunders P, Ghamisi P, Licciardi G, Chanussot J. Noise reduction in hyperspectral imagery: Overview and application. Remote Sensing 2018; 10 (3) 482-510. doi: 10.3390/rs10030482
[11] Chen Z, Li X, Zheng H, Gao H, Wang H. Domain adaptation and adaptive information fusion for object detection on foggy days. Sensors 2018; 18 (10) 3286. doi: 10.3390/s18103286
[12] Liu X, Hardeberg JY. Fog removal algorithms: Survey and perceptual evaluation. In: IEEE 2013 European Workshop on Visual Information Processing; Paris, France; 2013. pp. 118-123.
[13] Lu Y, xiang Huang Q. Object detection algorithm in underground mine based on sparse representation. International Journal of Advancements in Technology 2018; 9 (1). doi: 10.4172/0976-4860.1000210
[14] Fiaz M, Mahmood A, Soon Ki Jung. Tracking noisy targets: A review of recent object tracking approaches. ArXiv abs/1802.03098 (2018).
[15] Kowalski M, Kastek M, Palka N, Polakowski H, Szustakowski M et al. Investigations of concealed objects detec- tion in visible, infrared and terahertz ranges. PHOTONICS LETTERS OF POLAND 2018; 5 (4) 167-169. doi: 10.4302/plp.2013.4.16
[16] Narasimhan S, Nayar S. Vision and the atmosphere. International Journal of Computer Vision 2002; 48 (3) 233-254. doi: 10.1145/1508044.1508113
[17] Chavez PS. An improved dark-object subtraction technique for atmospheric scattering correction of multispectral data. Remote Sensing of Environment 1998; 24 (3) 459-479. doi: 10.1016/0034-4257(88)90019-3
[18] Liang J, Ren L, Ju H, Qu E, Wang Y. Visibility enhancement of hazy images based on a universal polarimetric imaging method. Journal of Applied Physics 2014; 116 (17) 173107. doi: 10.1063/1.4901244
[19] Kermani E, Asemani D. A robust adaptive algorithm of moving object detection for video surveillance. EURASIP Journal on Image and Video Processing 2014; 2014 (1):27. doi: 10.1186/1687-5281-2014-27
[20] Ozaki M, Kakimuma K, Hashimoto M, Takahashi K. Laser-based pedestrian tracking in outdoor environments by multiple mobile robots. Sensors 2012; 12 (11) 14489-507. doi: 10.3390/s121114489
[21] Tan R. Visibility in bad weather from a single image. In: IEEE 2008 Conference on Computer Vision and Pattern Recognition; Anchorage, AK, USA; 2008. pp. 1-8.
[22] Fattal R. Single image dehazing. ACM Transactions on Graphics 2008; 27 (3) 1-9. doi: 10.1145/1399504.1360671
[23] Cai B, Xu X, Jia K, Qing C, Tao D. Dehazenet: An end-to-end system for single image haze removal. IEEE Transactions on Image Processing; 2016, 25(11) 5187-5198. doi: 10.1109/TIP.2016.2598681
[24] Ren W, Liu S, Zhang H, Pan J, Cao X et al. Single image dehazing via multi-scale convolutional neural networks. Computer Vision – ECCV 2016; Cham, Switzerland: Springer International Publishing, 2016, pp. 154-169.
[25] Yang D, Sun J. Proximal dehaze-net: A prior learning-based deep network for single image dehazing. Computer Vision – ECCV 2018; Cham: Springer International Publishing, 2018, pp. 729-746.
[26] Cantor A. Optics of the atmosphere–scattering by molecules and particles. IEEE Journal of Quantum Electronics 1978; 14 (9) 698-699. doi: 10.1109/JQE.1978.1069864
[27] Nayar SK, Narasimhan SG. Vision in bad weather. In: Proceedings of the Seventh IEEE International Conference on Computer Vision; Kerkyra, Greece, Greece; 1999 pp. 820-827.
[28] Narasimhan SG, Nayar SK. Contrast restoration of weather degraded images. IEEE Transactions on Pattern Analysis and Machine Intelligence 2003; 25 (6) 713-724. doi: 10.1109/TPAMI.2003.1201821
[29] Sulami M, Glatzer I, Fattal R, Werman M. Automatic recovery of the atmospheric light in hazy images. In: IEEE 2014 International Conference on Computational Photography; Santa Clara, CA, USA; 2014 pp. 1-11.
[30] Zhu Q, Mai J, Shao L. A fast single image haze removal algorithm using color attenuation prior. IEEE Transactions on Image Processing 2015; 24 (11) 3522-3533. doi: 10.1109/TIP.2015.2446191
[31] Meng G, Wang Y, Duan J, Xiang S, Pan C. Eﬀicient image dehazing with boundary constraint and contextual regularization. In: 2013 IEEE International Conference on Computer Vision; Sydney, NSW, Australia; 2013 pp. 617-624.
[32] Jeong S, Lee S. The single image dehazing based on eﬀicient transmission estimation. In: IEEE 2013 International Conference on Consumer Electronics; Las Vegas, NV, USA; 2013 pp. 376-377.
[33] Hulburt EO. Optics of atmospheric haze. Journal of the Optical Society of America 1941; 31 (7) 467-476. doi: 10.1364/JOSA.31.000467
[34] Huang S, Chen B, Wang W. Visibility restoration of single hazy images captured in real-world weather con- ditions. IEEE Transactions on Circuits and Systems for Video Technology 2014; 24 (10) 1814-1824. doi: 10.1109/TCSVT.2014.2317854
[35] Cheng Y, Chen B, Huang S, Kuo S, Kopylov A. Visibility enhancement of single hazy images using hybrid dark channel prior. In: IEEE 2013 International Conference on Systems, Man, and Cybernetics; Manchester, UK; 2013 pp. 3627-3632.
[36] Yang H, Wang J. Color image contrast enhancement by co-occurrence histogram equalization and dark channel prior. In: Proceedings - 2010 3rd International Congress on Image and Signal Processing; Yantai, China; 2010 pp. 659-663.
[37] Long J, Shi Z, Tang W. Fast haze removal for a single remote sensing image using dark channel prior. In: 2012 International Conference on Computer Vision in Remote Sensing; Xiamen, China; 2012 pp. 132-135.
[38] Xu H, Guo J, Liu Q, Ye L. Fast image dehazing using improved dark channel prior. In: Proceedings of International Conference on Information Science and Technology; Hubei, China; 2012 pp. 663-667. doi: 10.1109/ICIST.2012.6221729
[39] Yu J, Xiao C, Li D. Physics-based fast single image fog removal. In: IEEE 2010 International Conference on Signal Processing Proceedings; Beijing, China; 2010, pp. 1048-1052. [40] Xiao C, Gan J. Fast image dehazing using guided joint bilateral filter. The Visual Computer 2012; 28 (6) 713-721. doi: 10.1007/s00371-012-0679-y
[41] Lv X, Chen W, Shen I. Real-time dehazing for image and video. In: 2010 18th Pacific Conference on Computer Graphics and Applications; NW Washington, DC, United States; 2010, pp. 62-69.
[42] Linan Y, Yan P, Xiaoyuan Y. Video defogging based on adaptive tolerance. TELKOMNIKA Indonesian Journal of Electrical Engineering 2012; 10 (7) 1644-1654. doi: 10.11591/telkomnika.v10i7.155
43] Zhang Y, Ding Y, Xiao J, Liu J, Guo Z. Visibility enhancement using an image filtering approach. EURASIP Journal on Advances in Signal Processing 2012; 2012 (220) pp. 1-6, 10. doi: 10.1186/1687-6180-2012-220
[44] Lan X, Zhang L, Shen H, Yuan Q, Li H. Single image haze removal considering sensor blur and noise. EURASIP Journal on Advances in Signal Processing 2013; 86. doi: 10.1186/1687-6180-2013-86
[45] Wang JB, He N, Zhang LL, Lu K. Single image dehazing with a physical model and dark channel prior. Neurocom- puting 2015; 149 (B) 718-728. doi: 10.1016/j.neucom.2014.08.005
[46] Kil T, Lee S, Cho N. Single image dehazing based on reliability map of dark channel prior. In: IEEE 2013 International Conference on Image Processing; Melbourne, VIC, Australia; 2013 pp. 882-885. doi: 10.1109/ICIP.2013.6738182
[47] Zhang S, Qing C, Xu X, Jin J, Qin H. Dehazing with improved heterogeneous atmosphere light estima- tion and a nonlinear color attenuation prior model. In: 2016 10th International Symposium on Communica- tion Systems, Networks and Digital Signal Processing (CSNDSP), Prague, Czech Republic; 2016, pp. 1-6. doi: 10.1109/CSNDSP.2016.7573967
[48] Ngo D, Lee GD, Kang B. Improved color attenuation prior for single-image haze removal. Applied Sciences 2019; 9 (19) 4011. doi: 10.3390/app9194011
[49] Kansal I, Kasana SS. Improved color attenuation prior based image de-fogging technique. Multimedia Tools and Applications; 2020, 01. doi: 10.1007/s11042-019-08240-6
[50] Ju M, Ding C, Guo YJ, Zhang D. Idgcp: Image dehazing based on gamma correction prior. IEEE Transactions on Image Processing 2020, 29 3104-3118. doi: 10.1109/TIP.2019.2957852
[51] Liu C, Zhao J, Shen Y, Zhou Y, Wang X et al. Texture filtering based physically plausible image dehazing. The Visual Computer 2016, 32 (6-8). doi: 10.1007/s00371-016-1259-3
[52] Ancuti CO, Ancuti C, Hermans C, Bekaert P. A fast semi-inverse approach to detect and remove the haze from a single image. In: ACCV 2010 - 10th Asian Conference on Computer Vision; Queenstown, New Zealand; 2011. pp. 501-514