Seeking to crack the code on video quality measurement, a small but swiftly growing Canadian video analytics firm is attempting to ape human perception in order to track a viewer's experience (QoE) more accurately than before.
Known as SSIMWAVE Inc., the five-year tech startup has already made waves in the pay-TV, OTT video and content markets with its pioneering video compression techniques and analytic metrics for measuring and monitoring video signals. SSIMWAVE officials say these techniques and metrics, designed to match how the human visual system works, enable the company's software probes to closely track a viewer's actual quality-of-experience (QoE), rather than just the quality of the video signals themselves.
The original video compression algorithm developed by SSIMWAVE, which is called SSIM (for Structural Similarity), has already become the most widely cited video QoE algorithm in the world, generating more than 44,000 academic citations as of July. More pertinent to the company's bottom line, the technology has been adopted by at least seven US and international pay-TV providers, including Telefónica and some other big players, putting SSIM in tens of millions of TV homes globally.
Thanks to such burgeoning industry acceptance, SSIMWAVE has shown strong growth over its short lifespan, especially over the last year or so. Operating out of cramped quarters in an office building near the University of Waterloo campus in southwestern Ontario, the firm now has 53 full-time employees, up from just seven in the fall of 2017. The company’s plans call for expanding to as many as 100 employees over the next year as it moves into larger offices nearby.
Still privately owned, SSIMWAVE does not disclose its revenue and profit figures. Company executives said revenues are now in the "double digit millions" but declined to specify. SSIMWAVE competes in an increasingly crowded market against such other video QoE specialists as Conviva Inc. , Qwilt Inc. , Nice People at Work, Interra Systems and Mux.
Besides generating new business, SSIM has earned Dr. Zhou Wang, SSIMWAVE's chief science officer and one of its three co-founders, an engineering Emmy Award from the Academy of Television Arts and Science. Wang, an engineering professor at the University of Waterloo who now also holds a research chair there, has taken home other prestigious awards for the technology as well.
"It was a big surprise for me," said Wang, who won the Emmy back in 2015. "I didn’t even know there was a technical Emmy Award."
What SSIMWAVE's technology does is try to march the viewing ability of its software probes with human perception as closely as possible. After observing Waterloo students and other volunteer viewers watching programs in a specially designed TV lab, Wang's research team crafts "objective" QoE monitoring probes. Each of these probes is designed to “see” and “behave” just like a pair of human eyes, perceiving each pixel exactly as TV viewers would.
"What we do is replace humans with SSIMWAVE probes," said Wang, who presented the SSIM technology in a paper at SCTE|ISBE Cable-Tec Expo in October. "They [the probes] all speak the same language and are not as expensive as humans."
Wang's team then assigns a unique quality score to each video stream as it travels down the transmission path. If a stream's QoE score happens to drop at any point along the way, engineers can easily locate the issue and fix it, hopefully even before any viewers notice the problem.
While this may sound simple, it's a lot easier said than done. In fact, Wang has been working on the thorny video quality measurement issue for 20 years, dating back to his days as a young PhD student at the University of Texas in Austin. In a 1998 research paper on video quality assessment, he argued that the quality of a video should be determined by how well viewers can actually see the video, not by how strong the video signal is. That idea stirred up a hornet's nest back then, when most video experts still viewed network quality-of-service (QoS) as the best way to measure video quality and sought to solve the problem by pumping in more bandwidth.
"Bandwidth doesn't equal quality," Wang said. "In this industry, people have a pretty bad habit. They [wrongly] equate bit-rate with quality."
In fact, Wang said, with the use of a powerful QoE metric, pay-TV and content providers can actually cut down on the bandwidth needed to deliver a superior video experience to viewers. That's because the technology enables them to make more efficient use of the bandwidth they have by striking a balance between perceptual quality and video compression.
"It allows us to gain huge bandwidth savings over typical video coding standards," Wang said. "Overall, you can give people a much better experience. At the same time, you save bandwidth and save money."
But Wang and his two SSIMWAVE co-founders, Dr. Abdul Rehman and Dr. Kai Zeng, are not exactly resting on their laurels now. Encouraged by the success of the original SSIM technology, they have developed a more advanced version of the video compression algorithm, known as SSIMPLUS. It attempts to go even further than SSIM in delivering a unified, end-to-end framework for measuring the QoE of a video program.
"[The Emmy award is] nice in that it means that we’ve had some impact on the industry," Wang said. "But compared to what we’re aiming for now, that’s nothing."
Recently inducted into the Royal Society of Canada for his work, Wang continues to refine the SSIM technology to make it more efficient and effective. For him, it's a never-ending battle against video buffering, freezing, stuttering, blurriness, artifacts, low resolution and other quality issues
"There are a lot more challenges," he said. "This is not an easy job. But it's quite exciting."
— Alan Breznick, Cable/Video Practice Leader, Light Reading