A raw colored video takes up around three times more memory size than it’s grayscale version. We can exploit this fact and send the grayscale version of a colored video along with a colorization model instead of the colored video to save bandwidth usage while transmission. In this paper, we tackle the problem of colorization of grayscale videos to reduce bandwidth usage. For this task, we use some colored keyframes as reference images from the colored version of the grayscale video. We propose a model that extracts keyframes from a colored video and trains a Convolutional Network from scratch on these colored frames. Through the extracted keyframes we get a good knowledge of the colors that have been used in the video which helps us in colorizing the grayscale version of the video efficiently.
CITATION STYLE
Singh, A., Chanani, A., & Karnick, H. (2020). Video colorization using CNNs and keyframes extraction: An application in saving bandwidth. In Communications in Computer and Information Science (Vol. 1148 CCIS, pp. 190–198). Springer. https://doi.org/10.1007/978-981-15-4018-9_18
Mendeley helps you to discover research relevant for your work.