WEBVTT - How Eye Tracking Tech Works 0:00:04.480 --> 0:00:12.800 Technology with tech Stuff from stuff dot Com. Hey there, 0:00:12.840 --> 0:00:16.759 and welcome to Tech Stuff. I'm your host, Jonathan Strickland, 0:00:16.880 --> 0:00:21.840 podcaster extraordinaire with how stuff works. And as you guys know, 0:00:22.400 --> 0:00:25.520 I loves me some technologies and that's what I'd like 0:00:25.640 --> 0:00:29.160 to cover on this show. And in the past I've 0:00:29.200 --> 0:00:33.280 covered concepts like Moore's law, and that can tend to 0:00:33.440 --> 0:00:37.440 lead people into thinking that, because computer processing power effectively 0:00:37.600 --> 0:00:41.400 doubles every two years or so, that the entire world 0:00:41.440 --> 0:00:44.440 is going to be transformed into a crazy techno wizard 0:00:44.440 --> 0:00:47.760 world that you'd see in an imaginative science fiction film. 0:00:47.800 --> 0:00:50.280 It's gonna happen any day now, and we're all headed 0:00:50.320 --> 0:00:53.720 that way. It's a foregone conclusion. However, from a day 0:00:53.720 --> 0:00:56.280 to day perspective, it doesn't seem like we're going all 0:00:56.360 --> 0:01:00.560 that quickly, despite that amazing progress and computer process using power. 0:01:00.880 --> 0:01:04.280 And one of the reasons there are many, but one 0:01:04.280 --> 0:01:06.679 of the reasons for this is that while computer processing 0:01:06.720 --> 0:01:09.880 power tends to follow that pathway that Gordon Moore observed 0:01:09.920 --> 0:01:13.840 several decades ago, other aspects of technology aren't on quite 0:01:13.880 --> 0:01:17.440 as predictable a path, nor do they advance at such 0:01:17.560 --> 0:01:22.280 a reliable accelerated rate. And because of that, because some 0:01:22.480 --> 0:01:27.199 aspects of technology lag behind the development of processing power, 0:01:27.840 --> 0:01:31.560 we don't get that crazy future that we've been promised 0:01:31.560 --> 0:01:35.360 since say the nineteen fifties. Now, one of those aspects, 0:01:35.480 --> 0:01:38.480 one of the things that does not evolve as quickly 0:01:38.520 --> 0:01:43.319 as processing power, would be user interfaces. Now, these are 0:01:43.360 --> 0:01:46.600 the ways that we interact with our devices, such as 0:01:46.600 --> 0:01:52.800 our computers. So the typical computer user, they're usually relying 0:01:52.880 --> 0:01:57.880 upon your basic keyboard and mouse combination. It's the same 0:01:57.920 --> 0:02:01.520 thing that's been in place, say the nineteen eighties and 0:02:01.600 --> 0:02:05.120 personal computers. Xerox Park was introducing things like the mouse 0:02:05.120 --> 0:02:08.360 and the graphic user interface much earlier than that, but 0:02:08.400 --> 0:02:11.480 it was really the Apple Macintosh that brought the graphic 0:02:11.520 --> 0:02:14.600 user interface and the mouse along with the keyboard to 0:02:14.680 --> 0:02:19.040 the personal computing space. The keyboard, of course, had already existed. Uh, 0:02:19.360 --> 0:02:22.120 there's a problem with this type of interface. There's actually 0:02:22.120 --> 0:02:25.040 a couple. But one is that it requires users to 0:02:25.080 --> 0:02:28.760 be both able to manipulate the input devices, which would 0:02:28.760 --> 0:02:30.600 be the keyboard and mouse. You have to actually be 0:02:30.639 --> 0:02:33.840 able to move them in order to interact with your computer. 0:02:34.639 --> 0:02:37.440 And the other problem is that there's a learning curve. 0:02:37.480 --> 0:02:40.960 You actually have to learn how to use those devices 0:02:41.040 --> 0:02:44.240 in order to interact with your computer properly. It's not 0:02:44.320 --> 0:02:47.840 a natural way to interact with a machine, or with 0:02:47.919 --> 0:02:50.280 anything else. It's not the way we tend to interact 0:02:50.320 --> 0:02:53.240 with the stuff in our everyday world. We don't have 0:02:53.360 --> 0:02:57.880 to type out codes or move a random part of 0:02:57.880 --> 0:03:01.240 an object in order to make something else move. We 0:03:01.360 --> 0:03:05.200 are much more direct with our input whenever we are 0:03:05.240 --> 0:03:09.040 interacting with our environment. So in order to learn how 0:03:09.040 --> 0:03:11.040 to use a computer, we actually have to go through 0:03:11.040 --> 0:03:17.200 this process of learning how keyboards and computer mices work. 0:03:17.760 --> 0:03:22.519 Otherwise nothing much gets done. Now that's not to say 0:03:22.560 --> 0:03:25.960 that once the keyboard and mouse combo came out we 0:03:26.000 --> 0:03:28.840 stopped trying to find ways to interact with technology, because 0:03:28.840 --> 0:03:32.079 engineers have been working on everything from light pens to 0:03:32.280 --> 0:03:36.280 touch screens, to gesture controls to voice commands all the 0:03:36.320 --> 0:03:38.400 way back to when the keyboard and mouse started to 0:03:38.440 --> 0:03:40.960 become a thing. And this is all in an effort 0:03:41.000 --> 0:03:44.760 to broaden the way we control computers and electronics. And 0:03:44.800 --> 0:03:47.840 I've covered some of those technologies in earlier episodes of 0:03:47.840 --> 0:03:50.720 Tech Stuff, and I've explained that many of them, like 0:03:50.840 --> 0:03:54.880 voice recognition do not follow a path that's nearly as 0:03:54.920 --> 0:03:59.160 accelerated as processing power. We've gotten really good with voice 0:03:59.160 --> 0:04:02.760 recognition over the last say, five or six years, but 0:04:02.880 --> 0:04:07.000 for many years it was lagging behind other technologies. And 0:04:07.080 --> 0:04:10.160 this is the problem with making those big promises about 0:04:10.200 --> 0:04:13.040 what the future is going to be like. Often that 0:04:13.200 --> 0:04:16.600 is based on an assumption that everything is moving forward 0:04:16.640 --> 0:04:20.320 at the same speed, and that's just not true. Well, 0:04:20.360 --> 0:04:25.640 today I wanted to cover a specific type of technology 0:04:25.720 --> 0:04:28.760 that can be used in user interfaces, although that's only 0:04:28.839 --> 0:04:33.840 one application of this technology, and that is eye tracking technology. 0:04:34.000 --> 0:04:36.799 A bit later in this episode, I'm going to play 0:04:36.800 --> 0:04:40.160 an interview I had with Oscar Werner of Toby Tech, 0:04:40.520 --> 0:04:43.680 and Toby Tech is a business unit of a company, 0:04:43.760 --> 0:04:48.520 Toby that is pioneering eye tracking technology for all sorts 0:04:48.560 --> 0:04:52.360 of applications, both on the business to business side and 0:04:52.480 --> 0:04:55.760 the business to consumer side. But before I get to 0:04:55.800 --> 0:04:58.000 that interview, I thought it might be interesting to talk 0:04:58.040 --> 0:05:01.920 about the evolution of eye tracking in general, because it's 0:05:01.920 --> 0:05:06.239 actually a really cool story, and you I learned stuff 0:05:06.240 --> 0:05:09.080 I just didn't know, including stuff that schemed me out 0:05:09.120 --> 0:05:13.080 a little bit. So I want to share my skiviness 0:05:13.160 --> 0:05:15.320 with you. Wait, no, that's not right. I want to 0:05:15.320 --> 0:05:18.159 share the stuff that schemed me out with you. My 0:05:18.279 --> 0:05:22.520 skiviness is a matter for my own personal life. Back 0:05:22.560 --> 0:05:26.360 off alright, To begin with, eye tracking technology is the 0:05:26.400 --> 0:05:30.680 product of a few different disciplines, and they originate from 0:05:31.120 --> 0:05:36.320 different perspectives. You've got philosophical approaches, you have technical approaches, 0:05:36.440 --> 0:05:41.479 you have biological approaches, and you also have human behavior 0:05:42.080 --> 0:05:46.480 along with psychology and physiology. So in the eighteenth century, 0:05:46.560 --> 0:05:49.080 which I feel I need to point out, was an 0:05:49.080 --> 0:05:52.520 era that had very few personal computers in it because 0:05:52.520 --> 0:05:55.440 they had not yet been invented. There was a guy 0:05:55.560 --> 0:06:00.760 named William Porterfield, who should not be confused with professional 0:06:00.880 --> 0:06:06.000 cricket player from Ireland, totally different person. This was William 0:06:06.040 --> 0:06:09.520 Porterfield in the eighteenth century, an Englishman who made some 0:06:09.640 --> 0:06:14.119 general notes about oculomotor behavior and reading, in other words, 0:06:14.279 --> 0:06:19.240 how our eyes behave as we read text. Now, Porterfield's 0:06:19.279 --> 0:06:23.240 work was not based off empirical evidence, but rather casual 0:06:23.400 --> 0:06:29.240 observations and some hypotheses. But later scientists would study this 0:06:30.480 --> 0:06:35.560 behavior in greater detail and with more rigorous scientific approaches. 0:06:36.640 --> 0:06:40.320 So some of them looked at it from a physiological standpoint, 0:06:40.480 --> 0:06:43.000 some looked at it from a philosophical standpoint. Some of 0:06:43.000 --> 0:06:47.080 them combined the two, and a man named Louis Emil 0:06:47.440 --> 0:06:51.840 Javal conducted a study of how our eyes behave when 0:06:51.880 --> 0:06:55.880 we read text. He was working in the late nineteenth century, 0:06:55.920 --> 0:06:58.960 around the eighteen sixties and eighteen seventies. He published his 0:06:59.040 --> 0:07:02.200 work about the US in eighteen seventy eight, and he 0:07:02.320 --> 0:07:06.280 made his observations by directly watching people's eyes as they 0:07:06.279 --> 0:07:09.960 read lines of text. And he saw that when you 0:07:10.040 --> 0:07:14.680 do that, your eyes don't just glide seamlessly across a page. Instead, 0:07:15.280 --> 0:07:19.120 your eyes have lots of stops and starts. Those motions 0:07:19.160 --> 0:07:22.640 he gave names, so he called every time you stopped, 0:07:22.840 --> 0:07:25.640 when you would your eyes would pause as they went across, 0:07:25.720 --> 0:07:29.680 he called those fixations. And he would call all the 0:07:29.680 --> 0:07:35.240 bits where your eyes would move across rapidly Saccadays, those 0:07:35.280 --> 0:07:38.200 would be the starts. Now, saccad comes from a French 0:07:38.280 --> 0:07:42.840 word that was originally used to describe horse movements, and 0:07:42.880 --> 0:07:46.560 a rough translation into English might be jerk, as in 0:07:46.600 --> 0:07:49.960 the motion, not as in some jerk face who's giving 0:07:49.960 --> 0:07:53.960 you a hard time. So Javal's work was interesting in that, 0:07:54.080 --> 0:07:56.880 for the most part. The only studies in oculu motor 0:07:57.040 --> 0:08:00.400 function up to that time were limited to diagnos sing 0:08:00.440 --> 0:08:05.960 and perhaps treating dysfunction, so the work wasn't all about 0:08:06.200 --> 0:08:10.360 learning more of what typical behavior is like. In other words, 0:08:10.400 --> 0:08:12.960 doctors normally didn't think to look into the way our 0:08:13.040 --> 0:08:17.840 eyes move unless something atypical was going on with the patient. 0:08:18.600 --> 0:08:22.360 Javal started a movement in medicine and biology that, pardon 0:08:22.480 --> 0:08:27.800 the pun, shifted the focus. Other scientists observed similar similar 0:08:27.840 --> 0:08:31.880 oculomotor behavior, so this was all emerging around the same time. 0:08:32.200 --> 0:08:34.439 There are actually quite a few people who were looking 0:08:34.480 --> 0:08:37.920 into it, so to speak. Javal just became the most 0:08:37.960 --> 0:08:40.120 famous of all those people. So I don't mean to 0:08:40.160 --> 0:08:43.240 suggest he was the only one, but rather he's the 0:08:43.240 --> 0:08:45.199 one that gets most of the credit, and that is 0:08:45.240 --> 0:08:48.320 because of another person named Edmund Huey, who was a 0:08:48.360 --> 0:08:51.880 clever fellow from the late nineteenth and early twenty centuries. 0:08:51.920 --> 0:08:55.280 He made more progress in this study by creating an 0:08:55.280 --> 0:08:58.160 invention that sounds like it came straight out of a 0:08:58.200 --> 0:09:02.840 clockwork orange. It consisted of a plaster I cup that 0:09:02.880 --> 0:09:07.240 would fit over a subject's I so it would go 0:09:07.440 --> 0:09:10.160 right up against the person's eye, and the cup had 0:09:10.200 --> 0:09:12.880 a lever attached to it that went off to the side. 0:09:13.240 --> 0:09:15.680 At the other end of the lever there was a pen, 0:09:16.720 --> 0:09:21.000 and the pen could move across a rotating smoked drum, 0:09:21.040 --> 0:09:23.960 and thus the pen would make marks across the smoked 0:09:24.640 --> 0:09:28.840 surface of this drum that rotated around. And the idea 0:09:28.920 --> 0:09:31.840 was that this would allow you to look at those 0:09:31.880 --> 0:09:35.360 marks and map that to I've movements that are happening 0:09:35.400 --> 0:09:38.120 while you're actually giving the subject a test. So as 0:09:38.160 --> 0:09:42.240 the subject's eyes would scan text, the movements of those 0:09:42.240 --> 0:09:45.559 eyes would make the plaster cup move, which would transfer 0:09:45.600 --> 0:09:48.120 that motion to the lever and ultimately to the pen 0:09:48.240 --> 0:09:51.840 that was resting against the rotating drum. And this sounds 0:09:51.880 --> 0:09:56.520 absolutely ghastly to me, but it gave valuable information to 0:09:56.600 --> 0:10:01.600 Hueie about how people's eyes move when they're reading. Now, 0:10:01.640 --> 0:10:06.040 in his papers on the subject, hue would refer back 0:10:06.080 --> 0:10:11.360 to Javal's work and his research on the physiology of reading. 0:10:11.880 --> 0:10:14.199 There were other scientists who are looking into this subject 0:10:14.200 --> 0:10:16.679 as well, but Huey's work and the citation of Javel 0:10:16.800 --> 0:10:19.920 have led many to simplify history and just say they're 0:10:19.920 --> 0:10:22.520 the ones responsible for the research. On i've movements in 0:10:22.559 --> 0:10:27.080 the early days. Later on, another scientist, George Malcolm Stratton, 0:10:27.400 --> 0:10:29.920 would start to study how we move our eyes as 0:10:29.920 --> 0:10:34.439 we perceive illusions. Now, this is really interesting. Optical illusions 0:10:34.480 --> 0:10:38.760 depend upon our eyes perceiving something that is either not 0:10:39.000 --> 0:10:42.079 there or is there in a way that is different 0:10:42.440 --> 0:10:48.000 from the actual physical thing that we are perceiving, and 0:10:48.040 --> 0:10:51.080 therefore the way our eyes behave is very important to 0:10:51.320 --> 0:10:53.600 how those illusions work. What is it that's going on 0:10:53.720 --> 0:10:57.120 physiologically with our eyes, how much of that is dependent 0:10:57.200 --> 0:11:01.760 upon my behavior versus what's going on in our brains. 0:11:01.760 --> 0:11:06.520 This would slowly lead scientists to the conclusion that our 0:11:06.600 --> 0:11:09.440 eyes are really an extension of our brains, and that 0:11:09.559 --> 0:11:15.000 the process of thinking is very closely, if not synonymously, 0:11:15.120 --> 0:11:19.040 connected with the process of seeing. And I think that's 0:11:19.080 --> 0:11:22.720 pretty cool too. Stratton's work would publish in the early 0:11:22.760 --> 0:11:28.520 twentieth century and also help inform scientists and others about 0:11:28.600 --> 0:11:31.600 the nature of our eyes. All of this is to say, 0:11:31.640 --> 0:11:34.520 these early studies began to coalesce around that concept of 0:11:34.559 --> 0:11:37.720 not just how our eyes move as we perceive, but 0:11:37.880 --> 0:11:41.839 also where our focus tends to be directed. Knowing about 0:11:42.000 --> 0:11:45.880 focus is important for lots of different fields, some of 0:11:45.920 --> 0:11:50.120 which appear to be completely independent of technology and user interfaces. 0:11:50.360 --> 0:11:54.400 For example, let's say that you are a graphics designer 0:11:55.000 --> 0:11:57.760 and you have a job. You're given a contract, and 0:11:57.800 --> 0:12:01.360 your job is to create a sign that will warn 0:12:01.440 --> 0:12:05.080 people to potential danger. Maybe it's a warning sign for 0:12:05.280 --> 0:12:08.800 let's say radioactive material, and you want to make sure 0:12:08.920 --> 0:12:12.480 you get across to people that anything beyond that sign 0:12:12.800 --> 0:12:16.719 could pose as a threat to that person's health. There 0:12:16.720 --> 0:12:19.200 are many things you would have to consider before you 0:12:19.240 --> 0:12:23.640 start making that sign. For example, which colors should you use. 0:12:24.080 --> 0:12:26.320 You're gonna want something that's going to have a good 0:12:26.400 --> 0:12:29.520 level of contrast, so that whatever the message is that 0:12:29.559 --> 0:12:33.199 you're trying to convey will be easy for people to perceive, 0:12:33.320 --> 0:12:36.520 even if people might have some form of color blindness. 0:12:37.280 --> 0:12:38.600 Then you have to ask, all right, well, if there 0:12:38.600 --> 0:12:41.480 are any words on there, what typeface should you use? 0:12:41.520 --> 0:12:45.000 I mean, it needs to be easily legible, and where 0:12:45.000 --> 0:12:48.160 do you draw the focus on this sign so that 0:12:48.240 --> 0:12:51.760 the message you are sending gets to your audience and 0:12:51.760 --> 0:12:54.600 they actually get the point. Being able to track eye 0:12:54.640 --> 0:12:58.040 movement gives us more information about how we humans work, 0:12:58.120 --> 0:13:01.600 not just how we can interact with stuff. As for 0:13:01.760 --> 0:13:06.160 eye tracking technology, it thankfully evolved beyond the need for 0:13:06.240 --> 0:13:09.320 eye cups and mechanical levers. Otherwise I would just be 0:13:09.440 --> 0:13:13.320 running around screaming inside of the studio because I have 0:13:13.400 --> 0:13:17.600 a thing about eyes. But one methodology still relied on 0:13:17.640 --> 0:13:21.000 the subject wearing special equipment, and it was a system 0:13:21.000 --> 0:13:25.080 consisting of a pair of contact lenses with a sort 0:13:25.080 --> 0:13:28.839 of special feature, which is dependent upon the actual implementation 0:13:28.880 --> 0:13:32.320 of the technology. Some versions would use contact lenses that 0:13:32.480 --> 0:13:36.840 had a magnetic field sensor connected to them, or they 0:13:36.920 --> 0:13:39.680 might have an embedded mirror that would reflect light, and 0:13:39.679 --> 0:13:42.960 then you would have an external system that has partnered 0:13:43.000 --> 0:13:46.160 with these contact lenses and that would help monitor the 0:13:46.200 --> 0:13:49.920 movement of the special component of those contact lenses in 0:13:50.080 --> 0:13:53.600 turn that would track eye motion. This typically would provide 0:13:53.600 --> 0:13:56.200 a really accurate indication of what the eye is doing 0:13:56.240 --> 0:13:59.680 at any given time, assuming that the contact lens fits 0:13:59.720 --> 0:14:03.600 properly and doesn't itself slide a bit across the surface 0:14:03.640 --> 0:14:07.000 of the eye. Obviously, if that happens, then it's messing 0:14:07.080 --> 0:14:10.280 up your metrics because you're looking at the movement of 0:14:10.320 --> 0:14:13.800 the contact lens, not necessarily the movement of the eye itself. 0:14:14.160 --> 0:14:17.440 But for something like a computer or a mobile device 0:14:17.600 --> 0:14:21.200 that a consumer might purchase and you want an interface 0:14:21.240 --> 0:14:24.040 for that, you probably don't want to deal with putting 0:14:24.040 --> 0:14:28.080 in special contacts. So the interfaces that we're finding with 0:14:28.200 --> 0:14:34.440 personal electronics and computers typically rely upon optical tracking. And 0:14:34.520 --> 0:14:37.600 that means exactly what you think. It means. You're using 0:14:37.680 --> 0:14:42.400 some form of camera to monitor where you are looking. 0:14:42.480 --> 0:14:46.840 The device uses cameras that can detect your eyes using 0:14:46.880 --> 0:14:51.280 software that has image recognition algorithms running in it, So 0:14:51.320 --> 0:14:55.480 it's looking for different aspects of eyes that are common 0:14:55.600 --> 0:14:59.600 across many people. And once it identifies, all right, that's 0:14:59.600 --> 0:15:02.400 an eye, then it starts to try and track where 0:15:02.440 --> 0:15:06.520 the eye is looking. Typically, you have to end up 0:15:06.640 --> 0:15:11.760 using a system to set a baseline for this. You 0:15:11.800 --> 0:15:14.160 can't just turn it on and start looking. You have 0:15:14.240 --> 0:15:17.080 to calibrate it. So you calibrate the system so it 0:15:17.120 --> 0:15:20.240 knows where you're looking. It might guide you into looking 0:15:20.280 --> 0:15:23.240 at specific regions of a screen, whether it's a mobile 0:15:23.240 --> 0:15:26.680 device or a computer or whatever it might be. And 0:15:26.760 --> 0:15:29.560 that way, once it knows quote unquote that you are 0:15:29.600 --> 0:15:34.200 looking where you're supposed to, it can then uh interpret 0:15:34.640 --> 0:15:37.440 where your eye is looking from that point forward, because 0:15:37.480 --> 0:15:43.440 it's calibrated from a known set of standards. And from 0:15:43.480 --> 0:15:47.120 that point forward, assuming that everything is working properly, every 0:15:47.120 --> 0:15:49.040 time you look at some other part of the screen, 0:15:49.120 --> 0:15:52.040 the eye tracking software can track your gaze and know 0:15:52.160 --> 0:15:57.800 exactly where you are looking. That's the basic idea behind it. Now, 0:15:58.160 --> 0:16:00.520 when we listen to in on an interview in just 0:16:00.560 --> 0:16:04.400 a few minutes, Mr Werner will explain how Toby's technology 0:16:04.440 --> 0:16:08.520 accomplishes this. In particular, they have a specific kind of 0:16:08.680 --> 0:16:12.360 approach to using cameras to track eye movements. It's not 0:16:12.480 --> 0:16:15.600 that different from the way motion sensors like the Microsoft 0:16:15.640 --> 0:16:20.359 Connect work, only obviously, eye tracking technology is more precisely 0:16:20.400 --> 0:16:23.880 tuned to look at the movement of your eyeballs, not 0:16:24.040 --> 0:16:29.280 your overall body. Now, this technology allows for all sorts 0:16:29.280 --> 0:16:32.800 of potential applications, and some of them are passive, which 0:16:32.840 --> 0:16:35.320 means that people can use the eye tracking data to 0:16:35.360 --> 0:16:38.080 get an idea of where people direct their focus for 0:16:38.160 --> 0:16:41.720 any given situation. So that might be when someone is 0:16:41.760 --> 0:16:44.920 looking at an advertisement, or looking at a web page, 0:16:45.000 --> 0:16:48.320 or playing a game. It can be more active. It 0:16:48.360 --> 0:16:51.480 doesn't have to be a passive implementation, it can allow 0:16:51.520 --> 0:16:55.400 people the chance to send input into a computer by 0:16:55.440 --> 0:16:58.480 staring at specific parts of a screen. This is useful 0:16:58.480 --> 0:17:01.640 for those people who may otherwise be unable to move. 0:17:02.080 --> 0:17:04.959 They can use these kind of interfaces in order to communicate. 0:17:05.160 --> 0:17:09.240 And there are countless other applications that exist now and 0:17:09.280 --> 0:17:13.040 even more that we haven't even thought of yet. To 0:17:13.080 --> 0:17:15.120 get a better idea of what this tech is all 0:17:15.160 --> 0:17:18.119 about and how it might be used in the future, 0:17:18.440 --> 0:17:21.480 I talked with Oscar Warner. He's the business unit president 0:17:21.520 --> 0:17:24.320 of Toby Tech, and we'll hear that interview right after 0:17:24.359 --> 0:17:34.000 we take this quick break to thank our sponsor. Let's 0:17:34.040 --> 0:17:38.480 serve by you introducing yourself and your title and the company. 0:17:39.680 --> 0:17:42.560 So my name is Oscar Warner. I'm president of Toby Tech, 0:17:43.000 --> 0:17:46.919 and Toby Tech is basically one of three business units 0:17:46.960 --> 0:17:52.159 in Toby U in Toby Group, so um Toby there 0:17:52.160 --> 0:17:56.600 are three business units. Toby Dinox is providing solutions for 0:17:56.640 --> 0:17:59.720 people with disabilities. Someone with a S who cannot move, 0:18:00.800 --> 0:18:07.240 any who cannot move at all can basically communicate via 0:18:07.320 --> 0:18:10.000 looking at a computer or send emails via just looking 0:18:10.000 --> 0:18:13.120 at the computer, or somebody with CP who is pastic 0:18:13.320 --> 0:18:17.000 can type emails and write on a thesis or or 0:18:17.080 --> 0:18:19.439 or or write on a computer and use a computer 0:18:19.520 --> 0:18:22.920 just with the rice. And then it's Toby Toby Pro 0:18:23.440 --> 0:18:27.800 which is focusing on selling research people's solutions to to 0:18:27.960 --> 0:18:32.359 universities and to companies like Proper and gaming the U 0:18:32.400 --> 0:18:35.600 in the level to understand human behavior. And then it's 0:18:35.640 --> 0:18:39.879 Toby Tech who is the developer of all the core 0:18:39.920 --> 0:18:43.280 eye tracking technology and is selling this to the consumer markets, 0:18:43.800 --> 0:18:47.920 which may be PIEC, gaming, the PC industry, smartphone industry, 0:18:48.080 --> 0:18:50.200 v R, a R industry, so selling to the big 0:18:50.359 --> 0:18:53.639 big o emsum of which you know pretty much all 0:18:53.680 --> 0:18:58.240 the names. Right, So let's start just by kind of 0:18:58.280 --> 0:19:02.760 explaining what I track tracking technology does in general, so 0:19:03.000 --> 0:19:07.639 without getting into the mechanics of it, what exactly is 0:19:07.800 --> 0:19:12.720 its purpose as far as as a technology goes. So, 0:19:12.880 --> 0:19:18.960 eye tracking does two things, um um. It basically makes 0:19:19.359 --> 0:19:25.000 technology understand you as a human being, and it does 0:19:25.080 --> 0:19:27.640 that in two different ways. You know. The first one 0:19:27.720 --> 0:19:32.200 is what we in already call insight. It makes devices 0:19:32.560 --> 0:19:35.840 know what you're paying attention to, and when you think 0:19:35.880 --> 0:19:39.400 about it, what you're paying attention to is your interest 0:19:39.760 --> 0:19:42.879 or your intent at that given point in time. So 0:19:43.080 --> 0:19:45.719 a computer with eye tracking know what your intention is 0:19:47.080 --> 0:19:50.240 and when you think about it is if you think 0:19:50.280 --> 0:19:52.600 on your in front of computer, you're looking at an 0:19:52.800 --> 0:19:55.160 icon that you want to click on. The first thing 0:19:55.160 --> 0:19:56.840 you do is you look at it. The second thing 0:19:56.840 --> 0:19:59.560 you do is you take your mouse and drag the 0:19:59.600 --> 0:20:01.679 mouse and throw over it. And the third thing you 0:20:01.720 --> 0:20:04.040 do is you click on your mouth or in your 0:20:04.040 --> 0:20:07.840 touchpad or in your control or whatever. But a computer 0:20:07.840 --> 0:20:10.240 with an eye tracker already know that you're looking at something, 0:20:10.440 --> 0:20:12.240 so that it knows what you want to click on 0:20:12.320 --> 0:20:15.240 before you touch your mouth. So that could come in 0:20:15.320 --> 0:20:19.359 really handy for anyone who's designing something to have a 0:20:19.960 --> 0:20:23.480 process where you run the test and you have eye 0:20:23.480 --> 0:20:26.840 tracking technology, you can see what elements of your design 0:20:26.880 --> 0:20:30.879 are actually working or maybe are distracting to your to 0:20:31.000 --> 0:20:35.359 your potential user. Yes, that is exactly what to be 0:20:35.440 --> 0:20:38.320 pro that their entire business models is centered around that. 0:20:38.840 --> 0:20:41.879 For example, you know they're creating glasses eye tracking, a 0:20:42.080 --> 0:20:44.080 set of glasses and they send a test group through 0:20:44.160 --> 0:20:47.679 a store, a retail store, and then big retail companies 0:20:47.680 --> 0:20:49.800 such as Propering annulal unit level that would test the 0:20:49.880 --> 0:20:52.280 store layout and see what package did I look at? 0:20:52.400 --> 0:20:54.480 What package did I not see? And how do I 0:20:54.560 --> 0:20:57.520 reconfigure the store layout. It can also be done on 0:20:57.600 --> 0:21:01.320 websites or pack research, etcetera. But US excellent and it 0:21:01.359 --> 0:21:04.640 can also be used not just to see where our 0:21:05.560 --> 0:21:08.200 attention is, but it can go a step further and 0:21:08.320 --> 0:21:13.639 become a direct interface with some other technology. For example, 0:21:13.800 --> 0:21:17.359 you can use it so that you are creating an action, 0:21:17.480 --> 0:21:21.880 you're removing that need to move and click correct. Yes. 0:21:22.359 --> 0:21:24.520 So the first thing, the first category is just it 0:21:24.680 --> 0:21:29.600 gives computers or it gives devices insight of what you're 0:21:29.680 --> 0:21:32.960 looking at. If you're in front of the computer, are 0:21:33.000 --> 0:21:35.520 you're focusing on the screen, or you're leaving the screen, 0:21:36.160 --> 0:21:39.000 what you saw, what you did not see. It can 0:21:39.040 --> 0:21:41.480 be presence and identity in all these things. It gives 0:21:41.520 --> 0:21:44.200 you that it gives you another knowledge about the human. 0:21:44.560 --> 0:21:46.840 And the second thing is you can use it for 0:21:47.040 --> 0:21:51.680 interaction like taking an example from VR. For example, if 0:21:51.760 --> 0:21:55.920 you imagine you pick up something in something in your 0:21:56.000 --> 0:21:58.520 hand and you want to throw it, and if you 0:21:58.600 --> 0:22:00.280 do this, you throw it aim at the a's in 0:22:00.320 --> 0:22:02.760 your room. You want to throw it. When you as 0:22:02.760 --> 0:22:05.120 a human aim at that place, you are looking at 0:22:05.160 --> 0:22:08.359 the place with your eyes and then you give the 0:22:08.480 --> 0:22:11.200 command to your body to throw the thing with your hand. 0:22:12.359 --> 0:22:15.600 But the VR headset in order to tell where you 0:22:15.720 --> 0:22:18.840 want to throw the object, you either need to point 0:22:19.359 --> 0:22:21.520 at the area you want to throw it it with 0:22:21.600 --> 0:22:25.960 your forehead or you need to point at the area 0:22:26.040 --> 0:22:27.639 you want to throw at it with your hand or 0:22:27.680 --> 0:22:30.640 do a gesture, and that's very very hard to get 0:22:30.720 --> 0:22:34.560 exact basically, So this is kind of replicating the human 0:22:34.640 --> 0:22:36.560 behavior when you pick up pick up something and you 0:22:36.600 --> 0:22:39.400 want to throw at something, you look at the point 0:22:39.480 --> 0:22:41.960 you want to throw at and that's how you do 0:22:42.040 --> 0:22:46.399 your aim. And headsets with eye tracking would suddenly understand 0:22:46.520 --> 0:22:49.240 your intention. They would understand what you are trying to 0:22:49.359 --> 0:22:52.400 hit because you're looking at that point. So those devices 0:22:52.440 --> 0:22:55.159 are much smarter, and we give developers the freedom to 0:22:55.280 --> 0:22:59.520 use that and it removes that barrier from a user 0:22:59.640 --> 0:23:03.520 perspect active that any time you have any kind of 0:23:03.640 --> 0:23:08.920 interface with a machine, the more levels of of abstraction 0:23:09.000 --> 0:23:12.200 that there are between you and what you're trying to do, 0:23:12.680 --> 0:23:14.720 the more there's a learning curve, right that you have 0:23:14.880 --> 0:23:19.040 to actually train yourself how to use that device, so 0:23:19.200 --> 0:23:21.359 that the device does what you wanted to do, whereas 0:23:21.400 --> 0:23:23.520 this is kind of stripping that away quite a bit. 0:23:24.160 --> 0:23:27.200 We're trying to make it. We're trying to make it natural. 0:23:27.560 --> 0:23:30.760 That is exactly how you behave in the real world. 0:23:30.960 --> 0:23:32.720 You want to throw an object at something, you pick 0:23:32.760 --> 0:23:34.479 it up, you look, that's how you aim and then 0:23:34.520 --> 0:23:37.320 you throw, while in VR you would have to do 0:23:37.440 --> 0:23:42.080 something else. So so we're trying to make it as natural. Yeah, 0:23:42.160 --> 0:23:45.840 So what we think when you think about what devices 0:23:46.000 --> 0:23:50.560 are as of today, devices have and I'm talking about 0:23:50.560 --> 0:23:53.800 devices a community or a or smartphones or computers. But 0:23:53.960 --> 0:23:57.840 they they they know if you push the buttons or 0:23:57.960 --> 0:24:01.040 push them right. They listened to you because they have 0:24:01.200 --> 0:24:05.760 cortona or they have different types of voice input and microphones. 0:24:06.359 --> 0:24:10.280 They know where you are because they may have a GPS. 0:24:10.560 --> 0:24:13.280 They know if you turn them around because they have 0:24:13.320 --> 0:24:16.479 a gyro, etcetera. They know all these things, but they 0:24:16.560 --> 0:24:20.920 have no concept, no idea of of the human in 0:24:20.960 --> 0:24:23.879 front of them. They don't know if there's there's anyone 0:24:23.960 --> 0:24:26.560 in front of them. So we typically say that devices 0:24:26.600 --> 0:24:30.359 as of today are blind. They can listen, they can feel, 0:24:30.720 --> 0:24:32.920 they know where they are, they know in what direction 0:24:32.960 --> 0:24:35.720 they are, but they are blind. They have no concept 0:24:35.840 --> 0:24:37.639