Video enhancement is a very challenging work, which is a much more difficult task than image enhancement. Video enhancement is aimed to not only improve the visual quality of videos but also do not produce some side problems. It is not a good solution to directly apply the existing image enhancement method to processing video frames one by one. Because this kind of operation maybe result in flickering among the frames in the considered video. In order to obtain better-enhanced results for videos, we proposed a temporally consistent contrast enhancement method. Firstly, the video frames are converted from the RGB color space to the YUV color space. Then, the Y channel of each frame is enhanced by both global adaptive enhancement method and local adaptive enhancement method. The key technique is that temporally consistent is considered in the global method since global enhancement methods often produce flickering when they are used to enhance each frame independently. After that, a fusion enhanced Y channel is obtained with the global results and the local results. Finally, the enhanced color image is produced via YUV-RGB color space conversion. Experiments demonstrate the proposed method outperforms other algorithms in terms of contrast improvement, color image visual quality, and flickering suppression.

The comparison algorithms include Arici et al.'s contrast enhancement method using Histogram Modification Framework (Arici’09) [1], Rivera et al.'s content-aware enhancement via channel division (Rivera’12) [2], and Ying et al.'s Bio-Inspired Multi-Exposure Fusion framework for image enhancement (Ying'17) [3].

Some examples are shown to subjectively compare the performances of these enhancement algorithms. The contrast improvement and detailed information preservation are considered in the comparisons.

[1]T. Arici, S. Dikbas, Y. Altunbasak, A histogram modification framework and its application for image contrast enhancement, IEEE Transactions on Image Processing, 18 (9) (2009) 1921–1935.

[2] A.R. Rivera, B. Ryu, and O. Chae. Content-aware dark image enhancement through channel division. IEEE Transactions on Image Processing, 21(9) (2012) 3967–3980.

[3]Z. Ying, G. Li, W. Gao, A bio-inspired multi-exposure fusion framework for lowlight image enhancement, arXiv preprint (2017) arXiv:1711.00591.