摘要
Images/videos captured in low-light conditions often present low luminance and contrast.Although the existing low-light enhancement algorithms can improve the subjective perception, color distortion and over-enhancement are extremely obvious, which will disturb the subsequent intelligent analysis. Therefore,a naturalness-preserved low-light enhancement algorithm for intelligent analysis is proposed in this paper. An enhancement model is established in RGB color space.Images of ColorChecker color chart are captured under a series of light conditions. To preserve the naturalness,the factors of the proposed enhancement model are estimated by the images captured in practical illumination environment. Experimental results demonstrate that the proposed algorithm can produce natural enhanced results and improve the performance of vehicle license plate localization and skin color detection compared to the existing algorithms. Furthermore, the proposed algorithm can process the 720p videos at the speed of 28.3 fps on average.
Images/videos captured in low-light conditions often present low luminance and contrast.Although the existing low-light enhancement algorithms can improve the subjective perception, color distortion and over-enhancement are extremely obvious, which will disturb the subsequent intelligent analysis. Therefore,a naturalness-preserved low-light enhancement algorithm for intelligent analysis is proposed in this paper. An enhancement model is established in RGB color space.Images of ColorChecker color chart are captured under a series of light conditions. To preserve the naturalness,the factors of the proposed enhancement model are estimated by the images captured in practical illumination environment. Experimental results demonstrate that the proposed algorithm can produce natural enhanced results and improve the performance of vehicle license plate localization and skin color detection compared to the existing algorithms. Furthermore, the proposed algorithm can process the 720p videos at the speed of 28.3 fps on average.
引文
[1]R.C.Gonzalez and P.Wintz,Digital image processing,3rd ed.,(Beijing Publishing House of Electronics Industry,2002).
[2]N.Sengee,A.Sengee and H.K.Choi,“Image contrast enhancement using bi-histogram equalization with neighborhood metrics”,IEEE Transactions on Consumer Electronics,Vol.4,pp.2727-2734 2010.
[3]Y.C.Zeng,“Automatic local contrast enhancement using adaptive histogram adjustment”,IEEE International Conference on Multimedia&Expo,pp.1318-1321,2009.
[4]C.M.Wu,“Studies on mathematical model of histogram equalization”,Acta Electronica Sinica,2013,Vol.41,pp.598-602.(in Chinese)
[5]C.Ding,L.Dong,X.Weihua,“Image details Enhancement by gradient field bi-interval equalization”,Acta Electronica Sinica,vol.45,pp.1165-1174,2017.(in Chinese)
[6]D.J.Jobson,Z.U.Rahman and G.A.Woodell,“Properties and performance of a center/surround retinex”,IEEETransactions on Image Processing,Vol.3,pp.451-462,1997.
[7]D.J.Jobson,Z.U.Rahman and G.A.Woodell,“A multiscale retinex for bridging the gap between color images and the human observation of scenes”,IEEE Transactions on Image Processing,Vol.7,pp.965-976,1997.
[8]X.Fu,Y.Sun,M.Liwang and Y.Huang,“A novel retinex based approach for image enhancement with illumination adjustment”,IEEE International Conference on Acoustics,Speech&Signal Processing,pp.1190-1194,2014.
[9]C.H.Lee,J.L.Shih,C.C.Lien and C.C.Han,“Adaptive multiscale retinex for image contrast enhancement”,International Conference on Signal-image Technology&Internetbased Systems,pp.43-50,2013.
[10]K.Kawasaki and A.Taguchi,“A multiscale retinex with low computational cost”,International Symposium on Communications&Information Technologies,pp.787-790,2013.
[11]A.B.Petro,C.Sbert and J.M.Morel,“Multiscale Retinex”,Image Processing on Line,Vol.4,pp.71-88,2014.
[12]G.Y.Zhang,et al.“A new PSLIP model and its application in edge detection and image enhancement”,Acta Electronica Sinica,Vol.43,pp.377-382,2015.
[13]R.K.Jha,R.Chouhan,“Dark and low-contrast image enhancement using dynamic stochastic resonance in discrete cosine transform domain”,Apsipa Transactions on Signal&Information Processing,vol.2,pp.1-8,2013.
[14]N.Gupta and R Jha,“Enhancement of high dynamic range dark images using internal noise in DWT domain”,Intelligent Interactive Technologies and Multimedia,Vol.276of the series Communications in Computer and Information Science,pp.66-74,2013.
[15]K.He,J.Sun and X.Tang,“Single image haze removal using dark channel prior”,IEEE Transactions on Pattern Analysis&Machine Intelligence,Vol.12,pp.2341-2353,2011.
[16]X.Dong,G.Wang,Y.Pang,W.Li,J.Wen,W.Meng and et al.,“Fast efficient algorithm for enhancement of low lighting video”,IEEE International Conference on Multimedia&Expo,pp.1-6,2011.
[17]X.Jiang,H.Yao,et al.“Night video enhancement using improved dark channel prior”,IEEE International Conference on Image Processing,pp.553-557,2013.
[18]H.Pan,“One rapid location method of vehicle license plate based on RGB color space”,Guide of SciTech Magazine,Vol.35,pp.56-57,2010.
[19]A.Hajraoui and M.Sabri,“Face detection algorithm based on skin detection,watershed method and gabor filters”,International Journal of Computer Applications,Vol.6,pp.33-39,2014.
[20]S.Wang,J.Zheng,H.M.Hu,B.Li,“Naturalness preserved enhancement algorithm for non-uniform illumination images”,IEEE Transactions on Image Processing,Vol.22,pp.3538-3548,2013.