A 18.42 times faster video encoder based on Retinex theory

Because of the limitation in the imaging system, videos captured by mobile devices are usually noisy. In this paper, a noise robust fast video encoding scheme is proposed based on Retinex theory. The reflectance image is estimated in a co-analysis module by Retinex theory, within which the content similarity is detected to conduct the encoding process. Experimental results demonstrate that the proposed encoding scheme provides an average of 18.42 times higher encoding speed relative to the existing approaches without sacrificing the subjective quality.