An Enhancement Algorithm for Video Surveillance Image Based on Multi-scale Retinex

Aiming at the similarity of adjacent frame image's background and light in video surveillance, it legitimately uses of the information between frames and builds an enhancement algorithm for video surveillance image based on multi-scale Retinex. This algorithm uses different scales and parameters Gauss low pass filter to filter each frame image, takes Minimum operation for filter results, extracts each frame background's information, By taking the maximum operation, fuses multi frames of image's background, obtains the video image's accurate background for that moment, Using Retinex algorithm enhances the background. The experimental results show that after the image enhancement, the image detail information is richer and obtains more comfortable visual effect.

[1]  E. Land,et al.  Lightness and retinex theory. , 1971, Journal of the Optical Society of America.

[2]  John J. McCann,et al.  Lessons Learned from Mondrians Applied to Real Images and Color Gamuts , 1999, CIC.

[3]  Sangkeun Lee,et al.  An Efficient Content-Based Image Enhancement in the Compressed Domain Using Retinex Theory , 2007, IEEE Transactions on Circuits and Systems for Video Technology.

[4]  Zia-ur Rahman,et al.  Properties and performance of a center/surround retinex , 1997, IEEE Trans. Image Process..

[5]  Michael Elad,et al.  Reduced complexity Retinex algorithm via the variational approach , 2003, J. Vis. Commun. Image Represent..

[6]  Zia-ur Rahman,et al.  A multiscale retinex for bridging the gap between color images and the human observation of scenes , 1997, IEEE Trans. Image Process..