Netflix needed a way to improve video streaming quality for consumers in emerging economies watching movies and TV shows on the go. The company came up with a new method for video encoding called Dynamic Optimizer that reduces the amount of data in the video file without losing image quality. The Netflix team trained an AI to compress the video specifically based on the complexity of a given scene. The Dynamic Optimizer system expected to roll out in the coming months.
The need for this new encoding technology grew out of the viewing habits of Netflix customers in countries like India, Japan, and South Korea. People actually stream video on their phones and tablets more frequently than they do on a television set, reports Quartz. Many viewers watch TV dramas on the go, similar to the way people bring books around with them.
The Dynamic Optimizer makes it easier for those customers to watch videos without rebuffering. At the Mobile World Congress, Netflix demonstrated the new technology, showing that the image quality doesn’t decrease drastically at different bandwidths.
Netflix partnered with the University of Southern California and the University of Nantes to create the new technology. Participants rated the image quality of thousands of shots, and the data helped train the AI. The AI optimizes each scene, so that colorful, action-packed sequences get more bandwidth than the lingering shots.
Dynamic Optimizer will not only improve the video quality for mobile viewers; it will also help free up capacity on carriers’ networks, which could improve the mobile experience for everyone.