Researchers find a new algorithm to improve video streaming technology – tech
Streaming platforms like Netflix, Amazon, YouTube and others recently confirmed that they will be downgrading the video resolution for viewers in order to keep the servers free from overloading. But a team of researchers have found a solution to this problem.The team has unveiled a new algorithm called Fugu that is said to significantly improve the streaming video quality.
The algorithm was developed with the help of volunteer viewers who watched a stream of video, served up by computer scientists. The scientists used machine learning to scrutinize the data flow in real-time, looking for ways to reduce glitches and stalls.
In a study, the researchers describe how they created an algorithm that pushes out only as much data as the viewer’s internet connection can receive without degrading quality.
“In streaming, avoiding stalls depends heavily on these algorithms,” said study first author Francis Yan from Stanford University in the US. it has been reported that many of the prevailing systems for streaming video are based on Buffer-Based Algorithm, which is also known as BBA.
What BBA does is to ask the viewer’s device how much video it has in its buffer. If the device has less than 5 seconds stored, the algorithm sends lower quality footage for low interruptions. If the buffer has more than 15 seconds stored, the algorithm sends high quality video. If the number falls in between, the algorithm adjusts the quality accordingly.
The study adds that Fugu performed better than BBA in trials, making it something of an interest for streaming companies. “By the end of the trial, however, Fugu had outperformed the other algorithms — including BBA — in terms of least interruption time, highest image resolution and the consistency of video quality,” said the study. “What’s more, those improvements appear to have the power to keep viewers tuned in. Viewers watching Fugu-fed video streams lingered an average of 5–9% longer than other tested algorithms.”
With inputs from IANS