Hey there. Hi there. Hello there, everybody. It is Thursday. It’s 9:00 a.m. You know what that means? It’s time once again for Open CV Live. We’re so happy to have you all here today. It’s going to be an educational episode with our friend Dennis Baldwin here from Drone Blocks. We’ll give you all a few minutes to get situated, get on all your various platforms. We’re live on Twitch, LinkedIn live video, YouTube, and now on live streaming on our Patreon, which is pretty exciting um to be able to bring this stuff straight to patrons. So, if you want to see OpenCV Live live without any of those pesky YouTube ads, you can become an OpenCV patron at patreon.com. I’ll talk a little bit more about that later in the episode. Great. got some nice stuff happening already over on uh YouTube and uh let’s see how see how our folks on Zoom are making it happen today. Indeed, we’ve got Carlos Carlos Nav says nice. Yes, Vamos Mexico uh 3-0 yesterday. A very exciting game in the World Cup. I hope that all of your teams are moving on to the from the group round, but if not, uh there’s always next time. They say it’s the hope that kills you, you know, but sometimes the hope is all we got. So, yeah, thanks. We’ve got uh Stefan SA checking in from Vancouver, Canada. So, as you join us today, wherever you’re watching, wherever you’re joining us from, uh let us know where you’re joining us from. We’d love to see the global OpenCV community chiming in on these Thursday live streams. I’m coming to you from beautiful, far too sunny for my pasty white skin Tana, Mexico. However, uh it was it has been super great to be able to be here in Mexico and watch the World Cup with uh the the people of Mexico and the excitement is so the excite it’s always you know with with these countries that are very very into uh you know soccer. It’s the it’s always excitement tempered with realism. Like they know that they’re not favorites, right? But and they know that they’re very hard on the team, but it’s just because they care so much and it’s it’s been it’s been really fun. You you you you clearly have not seen the ad where it says uh American you cannot smell spell American without I can. [laughter] Um well I I think they’re going to win. You have not seen the miracle ad, have you? No, you have not been seeing all that. I haven’t. But in Mexico it’s uh it’s Cis. Yes, we can. Um, we’ve got uh Madagascar, we’ve got Houston, uh, Edward Bragg says, “Uh, Merry Mryland.” I assume that’s Maryland, but I like that. Uh, we’ve got, uh, Axel Tracy says, “Kickoff time for the Sakaroos in 10 hours.” Hello from Australia. Good luck to the Aussies. We’ve got Petro from Saudi Arabia. We’ve got quite a few of the AI assistants today. We’ve got Doug chiming in from uh Pmpano Beach. That’s a that’s a fun name to say. And we’ve got uh Carlos from Bueno Buenoseries over on YouTube. Welcome, Carlos. Got Parker from Tampa, Florida. And we’ve got India, of course. What would OpenCV be without India? And we’ve got John D from Austin. We’ve got uh Clinton says he’s coming in from New Zealand at 4 am. Thanks for making time for us in your early early morning or late late evening. Uh we appreciate it. Phil, may I may I jump in on Clinton? He’s one of our team. So uh hi Clinton, welcome. Thank you for making the time. He’s up at the craziest hours of the day. So [clears throat] wow, dedicated team you guys got over there. We’re excited to hear about what you’ve been working on. Got Picass Singh from Dusseldorf, Germany. We’ve got Mthagoram from Nevada, Texas. We’ve got uh Pamu from Sri Lanka. We’ve got uh Penny from Charlotte, North Carolina, the Queen City. We’ve got uh uh Jirona from uh close to Barcelona, they say. I I think we we are ready to uh represent there. this one representative uh from all the you know all the teams uh [laughter] we got Spain, we got Argentina, we got US, Mexico. You’re you’re Mexican now. Yeah. No, I’m team Yeah. See, Vamos Mexico. Uh team Mexico all the way over here. Um for sure. Definitely better odds than the US. Uh just from a cynical perspective. I I I don’t believe so. We can have a debate [laughter] about that. Okay. Okay. Well, I mean hopefully they will meet. That will be a hell of a game. We’ve got Muhammad from Dubai. We’ve got uh Jose from Chile. We’ve got uh Nidal from Iraq. Rene is joining us from the Philippines at 12 a.m. Thank you, Renee. We really appreciate it. And uh Clinton says, “Always a pleasure. Couldn’t give my computer or drones eyes without open CV.” Thanks so much, dude. Uh we’ve got Pakistan joining us here. Excellent. Excellent. I see there’s a bit of an issue on the Zoom, so I’ll fix that. W Sati is doing his intro. I think now is a great time to get started. You ready, boss? Yeah. Hello everybody. Welcome to OpenCV Live. At OpenCV, education is very important to us and we have our own education platform through OpenCV University. And today because of that connection, I’m very happy to invite Dennis Baldwin from drone blocks which is an educational platform for drone learning. It is uh what I call an all-in platform. So, uh we’ll go to Dennis and learn more about the platform and how it works and what kids can learn from it. But first, as always, is with me Phil Nelson who is the director of content and creative at OpenCV. Phil produces the show and if anything goes wrong, it’s his fault. Hi, Phil. Hey there, everybody. Yes, it’s me. It’s me. It’s PHIL. I am your co-host with the co-host, The Second Banana, who’s second to none. I’m also your plus one and only. You know it’s Mr. Nelson if you’re nasty, but you, my dear friends here, can call me Phil. And I’m here to remind you of a few things that we do on every single episode of this here program that you’re currently watching. The first of which is a giveaway to you out there in the audience. Stay tuned. Later on in the episode, I will be asking a trivia question based on the presentation and chat with our guest today. And the very first person to answer that question correctly in the chat wherever you’re watching. We’re live on Twitch, LinkedIn Live video, YouTube, and on Patreon will win the OpenCV University course of their choosing. You can see what courses are on offer by going to opencv.org/university.
And while you’re there, don’t forget to check out OpenCV5, our biggest release ever, which is available right now on GitHub. I think before we get started uh with the presentation proper today um Satia can you tell the folks a little bit about how important OpenCV5 is and I’ll remind you guys we are taking questions from you in the audience during the whole show post those in the chat wherever you’re watching I think Vleta outside has a question for us [laughter] you can you can ask that question wherever you’re watching at any time and we will do our absolute best to answer those questions live during the show and we’ll save some time at the end for any of those we don’t get to during the show. But boss, tell the folks what’s so awesome about OpenCV 5. Well, OpenCV 5 is the biggest release of OpenCV in many years. I think it is seven or eight years since we released OpenCV 4. Um, and OpenCV 5 it’s it’s not a minor release. It’s a major major upgrade especially the DNN engine has been rewritten from scratch. And the reason is that when we started writing the DNN engine, Onyx standard was not a standard and we didn’t want to layer you know code after code just to support the standard. So we wrote everything from scratch. It has a new uh you know under the hood even though it will work uh similarly as the old one but it will support 80% of uh the onyx layers etc. So because of that pretty much every any pretty much any uh you know any uh model you can think of for image classification segmentation detection it is going to run on uh OpenCV transformers everything is supported right. Uh not only that it has something called a hardware acceleration layer which means that different hardware uh you could be running it on Intel CPU, it could be AMD CPU, different kinds of or or ARM and based on what configuration your uh your machine is, it will automatically pick the best optimization. So every function even things like resize uh get optimized and they will under the hood uh things will run much faster sometimes 40 50% faster than uh than previous versions [clears throat] and we are also working on the new GPU HAL which will support uh you know GPU operations all these operations will be supported through the GPU HAL so very exciting release and uh you know uh we are uh we are looking forward to getting your feedback uh on how you like it. A lot of uh things which were legacy uh have been removed. For example, we do not have the C API anymore and uh we uh you know that that makes the library slightly lighter than before and uh it also becomes easier to maintain. So please check out the library and if you have any comments, suggestions, please let us know. Yeah, thanks for that boss. And I’ll remind people so you can scan that QR code at the bottom of the screen there to go to the uh in-depth blog post about everything that’s new in OpenCV5 including a link to the migration document. There are some breaking changes there. Um you know you can’t make an omelette without breaking a few eggs and we’ve broken a few eggs with this one for the first time in a long time in fact and so it may be a little bit tough for you guys to start out but the performance gains the ease of uh writing code gains are so so very worth it. And uh we should have the uh the pip package should be updated I think imminently, right? It’s it’s coming pretty pretty fast, right, Doc? Yeah, it should be uh it should be ready very quickly. All right, that’s great to hear. And uh so before we get started with our presentation, we got one more piece of business to remind you all about. Open CV is open-source software that is produced by a nonprofit organization and as such we depend on the support of our sponsors and partners all of which are listed here on opencv.org. We’d like to take this moment to thank ARM, Futureway Technologies, Google Summer of Code, Rooflow, Orbec, the British Machine Vision Association, Jet Brains, The Edgei and Vision Alliance, Open MV, Tangram Vision, AMP Software, Tuivo, Weer.io, Intrinsic, Bears Dev, and Big Vision because every company needs a big vision. Um, I know the guy that runs that. He’s he’s pretty good at his job. [laughter] Okay, I think now is a great time to get started with our guest. Let’s bring Let’s bring Thank you, Hilda. Let’s bring our uh guest Dennis. We We had a thunderclap to to bring our guest on here. Welcome, Dennis. Tell the people who you are there. Thank you, Phil. Thank you, Satcha. I’m Dennis Baldwin from Drone Blocks and uh really excited to to be on the podcast. You know, I I was telling Satia earlier earlier, Drone Blocks is sort of centered around open-source community and we really focus on enabling uh young learners to get into uh drone technology, robotics, hardware and software. And a lot of uh the foundation that we built the business on has been uh open source and learn open CV. There’s a lot of articles that I’ve read from Satia that have enabled us as as Clinton um who’s so uh gracious gracious with his 4 a.m. time to uh mention that uh we give the ability for drones and computers to see. So, um, thank you guys for for having me. And a just a a short small shout out to Ramon from the Drone Code Foundation. He’s the one who connected us. Really excited to be here. Uh, share a little bit about our history, um, what we’re up to today and answer any questions you guys might might have. Yes, indeed. Shout out to uh, Mr. Puyo, who’s also out here in Tijuana. Mr. Pooyo. Nice. Mr. [clears throat] Poo, the chicken man. That’s his handle on uh on Twitter. Yeah, there’s a there’s actually a sign there’s here in here in Tijuana, Mr. Puyo. Um so yeah, Dennis, I think uh take it away. Tell us about what Drone Blocks has been working on. We’re really excited to hear about it. Go ahead and bring up your your screen share and we’ll uh Absolutely. under the learning tree. Absolutely. Feel free to jump in with any questions. It will start with a bit of a hardware background because what we talk about on our team is the software enablement of hardware and a lot of what makes this possible right is CPU GPU vision those type of tasks and in the early days I’m going to begin my screen share now we had the the luxury when I say we the uh developer community um drone blocks and and where we started we didn’t have to be as concerned with um the hardware platform. So this started I’d say almost uh 14 years ago just as my passion my background is in electrical engineering. I got into software and really saw uh the beauty of open source with cutting my teeth on Linux some of the uh old C++ libraries diving in and learning OpenCV but at the time [snorts] we had access to DJI hardware and we still do today. don’t you know don’t don’t rule DJI DJI I out ever. It’s just we need to be able to for our market bring this technology to the classroom. So, it started with a open-source project called drone pan, which was just a simple app built on the DJI SDK for uh the camera to be able to grab photos at different perspectives, uh angles, attitudes, and then being able to run those through a pro post-processing uh pipeline. And so at the time I was using uh DJI with drone pan and KR pano to generate some really cool uh 3D panoramas to give a a great aerial perspective. And that what we learned and I encourage all of you developers that might be um whether you’re doing stuff for the good of the community or good doing stuff to monetize it’s very easy for a neat idea an application like this to become a fe a feature in a future roll out of an OS or a software update. So, drone pan ult ultimately became obsolete because DJI introduced a click of a button panorama feature in their um DJI Fly app. So, moving forward, one of the things that was really interesting to me was mapping, you know, because at the end of the day, there’s a lot of uh landscape and construction changes that happen on a daily basis and and being able to get a drone in the air to acquire that imagery. So, I had shared on YouTube basically how to get the different altitude and aerial perspectives of that imagery and once again running it through a post-processing pipeline. At the time there was SFM, the structure from motion libraries that would allow us to stitch them, would allow us to basically create map tiles. And I’ll just uh jump in really quick to this link. There’s kind of this historic uh view of the stadium near our house. I’m just outside of Austin in Dripping Springs. And so over time, football country. You’re saying Austin or Texas in general? Friday night in general. Yeah, exactly. So you can see here that a pre-planned flight, this existed of uh consisted of about 300 to 400 images with each flight. brought them down, were able to process process them. And and just getting back to the whole theme of, you know, a drone, having sensors, having high-res cameras, being able to do something that becomes the platform, right? I I know there is a whole market out there of enthusiasts, myself included, that love to fly, that love to solder, tinker, but it becomes basically a a flying platform to acquire imagery and do something interesting with it. So that was sort of my foray into maybe the the world of open source for drones. And then moving that forward, I got involved with our um afterchool program. One of my co-founders, Marissa Vickery, she was at Walnut Springs Elementary here in in Dripping Springs. And my daughter, sorry for the ads that you know they’re going to follow you wherever wherever you go, but uh indeed, she she was running a after school program called Tech Team. And so we taught the the students how to 3D print the frame and then build their own drone. And it wasn’t long before the kids were like, “Well, let’s put a camera on this thing. What can we do with this thing other than just fly it?” So this was sort of the genesis of drone blocks, right? Being able to then take what you built and have a uh let’s say a programmatic layer. So that led us down the path of um at the time I like to I like to say that uh a drone without a camera is a toy, right? And with a camera it is a sensor. Well said. That that’s actually a theme uh one of our team members uses when we talk about we we talk to a lot of different schools and um we get compared to a lot of different hardware and we like to lean on our stuff is open source. You can build on it. you can, you know, do interesting things with it. And when we try to compete with the $50 drone from China on Amazon, we lose every time, right? So sharing that that vision and and the capabilities of what you’re you’re talking about, Satia, is very important to us. Yeah, totally. I think we lost your screen share there, Dennis. Let me bring it back. You’re back. I’m back. Okay. So, moving forward, I don’t know. Sorry, I’m not a privy to what’s being if you can see my camera as well as my screen. Sure can. Okay. Thank you. This is the T. Many of you may or may not be familiar with it, but it was an incredible platform for us to build uh programming interface, right? Visual programming is important to us because we deal with students at the youngest ages, elementary school, right? to be able to simulate something then fly a drone, take photos and um learn about the aspects of drone flight and uh programming is is is a powerful thing. So we rolled out a course using Aruko markers open CV contrib and it was met with great uh fanfare. I will say we were able to get the camera images streaming over UDP to Python and then being able to simulate or when I say simulate I should use the term emulate a lot of what DJI was to do able to do in more expensive drones the tap to fly um you know being able to do pose estimation right to use hand gestures and navigate a drone with a sub $200 piece of hardware was uh pretty incredible. Very nice. So that that shift and when I say shift we had built a lot of content knowledge understanding around uh TE platform but we had seen through many conversations with DJI where that was headed right so DJI being very uh proumer industrial military you know enterprise um hardware that that’s where a majority of their business was and we really worked hard to figure out could we perhaps take over manufacturing and as crazy as that sounds, right? But TE ultimately was sunset and at the time we had done a lot of just our own R&D around Crazy Fly. If you’re not familiar with CrazyFly, a bit craze out of Sweden, they do incredible um hardware platform. They’re very involved in the Ross community. We saw that as a opportunity for us to to pivot a little bit to make um our programming interface available to those users. And so this is our our simulator. And the the really cool thing about simulation here is we have curriculum and these different environments that students can can engage with, learn math concepts, programming concepts. But I think it’s important. I know guys, you had um I forget the gentleman’s name, but he did Pi Simverse, right? You guys had him on the podcast. And that simulation is incredible. And for us, the step that we want to take is to be able to then have parody with not only simulation, but real hardware. So that’s where we have the ability that what you’re doing here, right, with with a simulated Crazy Fly, you then could power up your Crazy Fly, connect over Bluetooth, and be able to see your your real code take flight. And I think that’s an interesting thing that I tried to reiterate as a as a developer. If you’re doing a let’s say an iOS or Android, whatever platform that you’re developing for, especially now that we have we’ll say, you know, these flying sensors, right? You want to understand that simulation does not mean 100% par with real life because of environmental conditions, lighting, wind, all of that and crazy. All that pesky entropy in real life [laughter] without a doubt. Battery’s a great example, right? It’s like, oh, here you can run it. Click connect, your battery’s dead. Right? So, all those little things um that lead to sort of the complexity, but those are teaching moments for us, right? Being able to to share that. So, moving forward, we So, this uh also has a Python interface, right? I’m looking at the blocks. Uh but it has a pure Python. It does. And unfortunately for I I don’t want to say unfortunately the thing that we have to battle with in in the classroom right everything we do is web- based right because Chromebooks and all of that so when we get to Python we’ve tried to emulate sort of fake Python in a browser right but what we really want to encourage is you know like VS code or whatever IDE so crazy bit crates has their own CF lib Python on and and we have a separate curriculum around that, but that is not um directly accessible in the browser. Okay. So, moving I love this little uh I love this little anime classroom here, by the way. This assets delightful. Yeah. [laughter] All in full, you know, transparency, a lot of what we do is we just find assets. We have a young man who’s at a university here in in in Dallas and he does a lot of uh importing and modifying the assets for us to to create this from scratch. You guys know it’s it’s it’s quite the undertaking. Yeah. Right. So I I’ll move forward to Dex C3. So we have a larger version but I’m sharing Dex C3 just because I think it’s more relevant to the conversation today. And I was telling Satia at the beginning beginning of the call. [clears throat] It it’s it’s a challenge to to to manufacture hardware, right? Especially at this level where we’re trying to solve for, you know, the educational component, right, in in classrooms, you know, we’re once again up against, hey, I can buy this toy for $50 off of Amazon or you can buy the Dexi C3, which we’re going to retail for $750. And people are like, “Whoa, you’re you’re crazy. How are we that that doesn’t make any sense, right?” And so what we reinforce is that we’re giving them a whole learning platform. And I’ll I’ll jump to that in a minute. But this drone is 3D printable. We make the STLs for all the accessories, oh, available in GitHub, right? So you can print it, you can build it, understand it, modify it so that it can, you know, suit the needs. There’s there’s the manufacturing component, there’s the build component, programming, all of that. So uh sorry, sorry to interrupt. I’m I’m because I have kids too, too. And you know, u my wife actually just signed uh my son up for some robotics thing. I unfortunately ashamed to say that. I don’t know which which one it is. uh but she signed uh so I’m very interested in uh which means that you know when she signs my son up it means that she has signed me up for [laughter] right so I’m going to be involved uh that’s why I’m interested uh like uh my question was that this uh this uh the 3D printable parts right how what percentage or what are the components that are 3D printable because uh you know when we had the uh previous drone uh which u went out of you know the DJI and uh they stopped uh they stopped producing it uh the components right the parts etc they they break frequently right it is uh it’s just the nature you have to make it light so they are not very sturdy so they break frequently uh but just to order everything from Amazon one more time it’s just a pain right so to be able to download and 3D print at home that’s uh that would be exciting But thank you for [clears throat] validating what we believe to to be true and valuable. So, uh, this to to answer your question, Satia, as you know, electronics, we’re not there yet, right? You’re not going to be able to say, “Hey, I’m going to click a button and and print a flight controller and then put it in and solder it.” But all the peripherals, I I’ll just show you the the Dexi. This is our Dexi3. We have the the top plate, the bottom plate, we have the camera mount, a battery mount, we have an LED ring. I don’t know if the viewers can see the LED animating in the background here on our larger drone, but we want to make all of that accessible so that you can replace anything at any point in time. And um we also do sell a carbon fiber version. And and that’s what I wanted to share a little bit of just if we for for the audience who are I think very technical in nature we we call it our developer kit right so we’re proponents of uh PX4 right that’s our go-to flight stack and so PX4 is where we’re running you know the the flight firmware the IMU all the attitude all that information is being handled by open source with with some light modifications from us and then we add basically what we call our our code stack. So this ships with a CM5. We’ve designed our own carrier board for breakout, you know, for the LED or any GPIO that you might want. And then we have a a bunch of content and I I’ll I’ll jump into that here in a minute related to doing vision tasks. We we started as I mentioned with the TE and Aruko markers and more recently we’ve been shifting to doing um for the audience solving the problem of of drone positioning outdoors I’d say is significantly easier right than solving it for indoors. Outdoors you you plug in your GPS receiver. Now I’m not talking about drone light show. We’ve all seen that. That’s that technology is amazing. high-end GPS and accuracy, but a standard GPS, you have the ability to just get your position, right, 3D position, and then program your drone. So indoors we make use of optical flow and a distance sensor, but really the higher fidelity or higher accuracy positioning in my mind has to come from something like fiducials either like April tags or ruko markers you know um around the environment or Satia I know you’re you’re you’re a slam guy right so we’re we’re look looking at doing some pre preliminary vio with slam Right. Moninocular slam with a single camera would be amazing. Yeah. But I could ramble on and on about the complexities, but the thing that we want to do is sort of help solve for, you know, giving students the ability to build these technologies, understand them, right, and then jump into any of the repos, right, that we provide, our April tag, our YOLO, all of that. We make it available. We bundle that into just a we call Dexios. Dexi is our drone for exploration and innovation. But that that bundle th those packages are just, you know, Raspberry Pi OS with Ross 2 and all of the different libraries and packages built into it. Quick question. Have uh do any of the drones have speakers on them? And have you made any of them play Come on Eileen by Dexis Midnight Runners? [laughter] So, uh, no, but here’s what I will say with the carrier. I’m going to, um, just hold this up to the screen, Phil. I hope that the audience can see this. We have some breakout ports, right, that sit on the sides here. Sorry if that’s not visible. Yeah, you can see it. You would have the ability to whether it’s I squared C or whatever the interface of that speaker. The the the problem with the speaker is that the drone is also fairly loud, right? So, yeah, that that that great sound. Yeah, exactly. [snorts] Okay. So, I’m going to share this last [snorts] um piece that is I I would say near and dear to our team. It’s called AVR, Advanced Vertical Robotics. So when you come into the drone blocks ecosystem, you have the ability to go through the the different tiers, but one of them is a drone competition that started out of Bell Helicopter and in the DFW Fort Worth area, but now they’re known as Del Bell Flight, right? You you guys might be familiar with the Osprey. It’s a really cool aircraft, vertical takeoff and landing. Bell gener uh initiated this competition eight years ago and we got involved about four or five where we started bringing our own uh hardware to to the to the competition. So you have the ability in the platform to spin up the simulator and I’m just going to show a little example. So this is the simulator on the left and this is the 2025 game field, right? And so the student that keep in mind just for for the audience’s benefit that all of this existed physically before were teams from all over the country predominantly USA would compete in regional events and then the top let’s say 15 end up in Dallas and there’s a finals where they’re learning how to build solder program and and solve uh various challenges for time if you will Right. And so what is the team size? Usually it’s it the cool thing about it Satia is like so I don’t you mentioned your your your son or your daughter doing the the camp. Yeah. Those generally, you know, are probably first robotics. That’s my guess, right? FRC. And so what Ron Olsen, he’s the um guy that created the competition and just has a very uh creative mindset was like, “Hey, this competition needs to be different by including more uh players of the team. So a team should be a minimum of eight students, right? Because there’s a ground robotics part where they’re navigating a maze. um there’s somebody who’s sort of overseeing the team captain and then there’s multiple pilots. In this scenario, there’s just the one dexi, but in the real world competition, there’s a large dexi and and this smaller one and the kids the competition is by the age or how does it it it’s generally targeted at high school. But what we’ve tried to do with the simulation is expose it to a younger audience, right? because you you know in simulation for example I’ll just you know navigate around and I’m going to show you guys that we have a few April tags spread out through throughout the course there’s some images so it just scan the April tag and I I have code running in the background this is all node red on the on the right that that layers into a ROSS 2 kind of uh foundation [snorts] but those you know students we want to make it accessible at a younger age so that they just get the experience of learning how to fly, learning the different concepts and you know you don’t have the maybe the overhead of uh understanding all the electronics initially right if if the competition and the programming sort of piqus your interest I believe that just my own kind of mindset is as an engineer if I if I have some level of success at a higher level write some code and it does something then I dive in a little bit deeper if that makes sense. Right. Right. So, I’m going to just jump over really quickly. So, we have these inside these cabins. There’s a whole story behind this game. There’s stranded animals and then you look in here and you sort of scan for the animals and that’s all doing yolo um detection. So, we have this, you know, Onyx model that we’ve uh did some transfer learning on. Guess I’m I’m probably not doing a good job of flying here, but okay. Yeah. So there there’s the bird, right? And so gosh, apologize to you guys. Target scanned. And so what happens is we have all these ROSS nodes running. And I want to I want to wrap with this really quickly. And one of them is um a YOLO detection node. So we have our April tags and then YOLO detections. So, we’re teaching, you know, students, right, to to be able to to scan, to wire up their logic, right, to determine the confidence level. And then they want to go deeper in the future. It’s like, hey, we’re going to put completely new objects out there. You need to use whatever model you decide to use. uh fine-tune it to to detect some new or add new objects to the to the model to be able to train.
Very nice documentation. Nice. [snorts]
All right. So, yeah. Um we got some good questions here, but I think and you you you your timing is is just about right. We’re at 37 minutes here. So, not not bad at all. We got quite a few questions here. We’ll get to Sorry if there’s a little bit of background noise. Um, I’m going to quickly do our trivia giveaway here. Um, a little bit early in the show. So, solo myself. So, if you’re joining us for the first time or you just need a little reminder, one of the things that we do on every episode of Open CV is a giveaway to you in the audience. I am about to ask a trivia question based on today’s presentation and a little bit of the stuff we talked about. And the first person to answer that question in the chat wherever you’re watching on Twitch, LinkedIn, YouTube, Patreon, or on Zoom will win a free OpenCV university course. These are awesome industrial strength courses created by people from the industry to help you improve your understanding uh level up your career or uh get a better job, get a new career. Um so check it out at opencv.org/university.
And here comes our trivia question. If you have won in the last couple of months, please don’t answer. Give someone else a chance to win that free course. I’m looking at you, Martha.
So, in what year was OpenCV 4.0.0 released? We talked about this at the beginning of the show that it’s been quite a few years since major releases of OpenCV. In what year was OpenCV4 first released? Answer in the chat now.
Oh, wow. Axel Tracy just boom out of the gate. You get out of my head, Axel. Uh the answer we were looking for there was 2018. The answer was 2018 2018. So it has been quite some time. Uh congrats Axel. Were you just guessing? [laughter] He says in in chat. Wow. He says yes. I just guessed. [laughter] Hey, it still counts. Um uh congratulations. We will uh so please go to opencb.org/university and choose one of those courses. Then send exactly one email to me, philopencv.org. That’s philopencv.org. And we will make sure that you get that course unlocked in your OpenCV University dashboard. Uh, congrats, Axel. He says he uses he used context clues. Satia said seven or eight years ago, and there we are. Yeah. So, congrats. Um, and I think let me go ahead and remove our thing here. Okay. So, we’ve got uh quite a few questions here. Let me pull up pull up the best one. A couple pe couple people were close. You you’re lost by maybe three five seconds. Uh cat 5Dev on YouTube. Um Penny on YouTube and Emmanuel on uh LinkedIn. Uh better luck next time, guys. Um so questions. Our first one here, uh, we’ve got, uh, YouTube asks, “Can you connect to the drone from the web, uh, or do you need to install an app on a smartphone?” Dennis, that that is a I wish there was a simple answer. So, I will say that if you’re flying with a TE, uh, definitely that was native because we had to use a Wi-Fi bridge. So that would have been an iPad, an iOS, or even our Android app for Chromebook for Crazy Fly. We use uh the Bluetooth web API, and you’re able to connect to that drone uh via web browser. And then now here we are with our own hardware with Dexi. When you boot Dexios, given the fact that it runs on a Raspberry Pi, what happens is that we bring up all the ROS services, we bring up the April tag, the YOLO detections node, we broadcast a hotspot, you connect to the drone over the hotspot or you put the drone on your network and all of that runs uh in your web browser or on your mobile device. We we aim to make our web interfaces as responsive as possible. what what we’ve struggled with I think the the the difference is you know being a developer doing sort of commercial stuff before drone blocks was oh we’ll just make you know native apps right and generally that becomes a bigger challenge at least in the US education market to allow third-party apps to be installed um on student devices and so that’s where if we can make our technology web accessible. Uh that that wins every time. Yeah, they tend to keep those Chromebooks locked down pretty hard for, you know, for obvious reasons. I It makes a lot of sense. Uh kids are going to kid. They’re going to they’re going to figure out ways around whatever blocks you put in front of them. I I’ll tell I’ll tell Phil, I got to share this. Please do. Side story. It’s It’s not going to be 100% accurate, but it’ll Ryan from our team supported this use case. So we have a native I’ll say a chrome app right so you used to be able to develop chrome apps that you install from the chrome web store uh chromebooks and so we used the standard uh Google authentication right to log in and some way shape or form during the on the off screen there was like a privacy policy or whatever and kids figured out how to click that took you to a page and all of a sudden you got to like unfettered use of the unrestricted use of the web and some kid made a Tik Tok video and then all of a sudden we saw inst installs spike and we were kind of like well maybe we’re in the wrong market right maybe we need to help kids figure out [laughter] how to get online so it was I love that pretty wild life finds a way you know totally that’s that’s what I love about our audience though even the the drone AVR sim that I was showing you kids are finding ways to to find loopholes Right. And I think that that ingenuity, that creativity, creativity is necessary. So, yeah, definitely. I mean, I think about when like back to when I was a kid, you know, we were figuring out how to install like uh, you know, Doom and uh, Sim City and stuff on the school PCs and and how to like, you know, set up the toggle so you could just like alt tab quickly over to the, you know, the Microsoft Word doc to make it look like you were actually doing your assignment and stuff, right? And I think about that like, you know, back then sometimes the teachers didn’t, you know, we knew more than the teachers. And I think that’s that’s definitely still the case, you know, today, especially today because technology moves so much faster now that the kids just instinctively know this. And so if you’re trying to, you know, any constraints you put in front of them, they’re going to figure out a way around it. And I love that. I think it’s a good sign like uh just the yeah as you said ingenuity and uh you know it’s it’s something that we reward in adults and sometimes unfortunately punish in children. Yeah. And uh yeah, they they find ways like uh my my wife uh you know uh closes down the Wi-Fi for my kids laptops, right? Uh to restrict time and uh even the younger one, he uh thought about it, how to bypass this problem. And so he swapped the names of his MacBook Pro like when he had the access to her phone, he swapped the names of his MacBook Pro and uh you know some some random thing like the water heater or something like that which is also connected to right and it shows up as the water heater, right? Swap out the name. So when she pauses the water heater, it’s paused. He’s still on his [laughter] right. That’s fantastic. So his MacBook Pro, the name is swapped. So, uh, they do all these, uh, things to, you know, I love that. If you’ve got any similar stories in the chat, please, uh, drop them in there. We’ll bring them up on screen because I I love that kind of stuff. Um, we got some more questions here. Um, let me go ahead and bring up the chat again. Um so uh Jurgen Fay asks I think a really good question here and especially this is I think a thing in you know in the United States where education is is vastly underfunded especially public education. Um Jurgen asks how do school folks deal with the cost even five or 10 per class are an investment for most. What would be the best age for starters? So I think these are just two questions but these are really good questions. Yeah. Well, h thank you th those are those those the first one makes my my head hurt but and I and part of it is because being a co-founder engineer evangelist whenever I’m faced with the question of how much it costs I like defer to someone like Lindsay or somebody else on our team sales is not my forte but I will share a little bit of what we’ve learned over the years at least here in the state so one there’s there’s Perkins grants right? There’s a Perkins grant, you know, from the federal government and that gets allocated to to schools that apply. So that that’s one, you know, grant funding that exists and we’ve actually worked in the past to sort of say, “Hey, school, we we will help you um with the grant application process. Marissa and our team has experience writing grants.” So, so that’s one thing. The um other thing is we’re part of this u I don’t know if it’s movement shift in education to this whole CTE uh space where it’s career and technical education maybe you know less students who are graduating or going off to university but they’re actually finding their calling maybe sooner or maybe they don’t know what they want to do but they’re not ready to invest you know what what a a college college college education cost nowadays. So, the career and technical education in computer science, there’s a lot of um funding and programs available, grants available in that market. And the other thing, the the final point I will make just based on what I know, there is a sweet spot for a purchase that’s maybe right under the the threshold of $5,000, right? Which is still a lot of money. I I understand that, right? But if you break things down, that’s sort of where we’re trying to to package our technology and and software. And and the thing that I will reiterate and the thing that I believe is is is tough for us to overcome is that we’re constantly being compared. Once again, getting getting back to someone’s gonna go put a programmable drone in their Amazon shopping cart that’s like less than $200, right? And so if you’re like, “Hey, I can get five of those for a,000 versus five Dexi3s for 4,000, it if it’s just a numbers or a math game, we’re going to lose every time.” So that’s where we have to reinforce just like you guys do with the platform and the education. uh the the soft skills, the the learning that you’re going to have access to when you don’t have hardware on your desk and in your hands. But um great question. And the the second one, what would be the best age for starters? Um if if I may, Phil, may I may I share again? Absolutely. Okay. So, part of what how we’re positioning this now is we have ground school, right? And and that’s where we’re focusing on like the the K through five, right? So you have we have our flight academy which is just a you know a simple hey here’s here’s how you might interface with with Dexi. Um well this is how you interface with Dexi before you actually have one, right? So you have all these challenges, right? You learn how to arm and disarm fly. So we try to make that accessible in the browser before they get to real hardware. So, we have a bunch of content and challenges around um simulated drones being able to do different uh tasks. This flying curves course is is incredible. This is from a advocate in um Italy, Luigi. He’s always sending us really cool content, right? Stuff that you can do with these lessons. And so, you’re learning, you know, different concepts of programming as well as math and you’re able to apply that in the simulation. So, our hope is that we make this accessible at at a at an age, ground school, K through five, that piqus their interest. So, when they get to middle school, getting their hands on the real hardware um becomes a lot uh more accessible and easier to understand.
Yeah. Um great great answer there. Thanks for that context. Um more questions we’ve got. So, let’s’ll take a break from questions here for one second. Um, uh, Satia, I want to give the folks a little can we give them a little sneak peek of the pretty big announcement we’re we’re going to be doing in the next week or so um about the next OpenCV competition. Uh, without giving it too much away, I think we should uh clue them in a little bit. Yeah. So we are this close to signing a contract with uh one of the big u you know um big uh hyperscalers let’s call them um and we are working with them to create uh for a competition where you will build um applications just like our previous competitions we we will uh ask you to build applications and it could be in two stages. We are still deciding on the exact format of the competition but uh typically we do uh competitions in two stages. In the first stage we ask you to uh to basically propose a solution or propose an idea for a problem that you want to solve and based on that we select a few and then we will give them some credits on this hyperscaler and based on that you will build the final solution. So it’s uh it’s going to be interesting because you know a lot of folks would be using OpenCV5 in the process uh and we love that because you know it’s getting so much faster and uh we have divided the competition that we’ll we’ll let you know there are a few use cases that we are very interested in right if you want to use it um as an agent uh that would be that would be great if you create an MCP server that kind of thing uh it would uh there will be a few categories uh where you can compete Those are suggestions and you can pretty much compete in any category. Right? So a new competition is coming. It would be uh based on one of the hyperscalers and we will uh basically make some credits available to you for people who qualify the first round. So as exciting as always uh we’ll you know uh it’s it’s going to be fun
indeed and I’m really looking forward to this one. Uh, as Satia said, we’re pretty close to being able to formally announce it and it’s going to be uh a little bit different than some of the previous competitions because of the uh the partner we have this time and it’s I think maybe more accessible than ever for for people to participate especially in countries where it’s hard to get the hardware or it’s difficult to access compute and and stuff like that. So, uh we’re really looking forward to it. Um, I’m also going to take this moment to remind folks that uh OpenCV has our official merch store um at opencv.mmyspreadshop.com and we just released a brand new t-shirt which I am going to bring the QR code up on screen for you guys. I think you’re going to like this one. It’s uh near and dear to our hearts. I will cover up Dennis’s face briefly, but you can buy official OpenCV gear on the OpenCV merch shop at opencv.mmyspreadshop.com. We’ve got a brand new shirt there. Says open- source, nonprofit, no [ ] That is the OpenCV credo. Uh we’re we’re leaning into it. We can uh get away with things that maybe some of the larger organizations out there cannot. And uh that’s part of the power of open source nonprofit software is that Phil’s allowed to say [ ] on official merchandise and on our live stream. [laughter] You you said worse things in in videos. That’s right. I’ve said worse things to you about you. [laughter] But please scan please scan that QR code and check it out. We’ve got hats, t-shirts, the OpenCV logo on all of that good stuff. We’ve got little bandanas that you can adorn your pets or small children with, as well as stickers and pins and all that good stuff. So, please check out the official OpenCV merch store. And if you buy something from the shop, take a picture of yourself wearing it. Take a picture of wherever you stick that OpenCV sticker and we’ll share it here on OpenCV Live with your permission, of course. Okay. And we’ve got a few more questions here and a little bit of time to answer them. Let me pull open the chat once more. Uh, we’ve got a question from Clinton Evans, who I think knows the answer, but uh, we’ll we’ll allow this uh, putting the thumb on the scale a little bit about how long should a drone kit last in the classroom on average, Dennis, this is a good question for those educators out there. Uh, a drone from drone blocks. Yes, I would say from others. We we want to we want to create longevity. So, uh, our our kind of phrase or tagline is elevating K through life, right? Get bringing them on the continuum. And so, in our scenario, if you’re introduced to the Dexi3, we we we bring that in around middle school, that should electronics wise, battery, you know, uh, motors wise, whatever. I don’t really it it’s hard to put a shelf life. I would say 3 to 5 years maybe on the electronics batteries depending on use, right? But the thing that I want to reinforce is that you have the ability to 3D print as we discussed earlier and add modifications. So we we’ve had some really cool contributions from the community on like claws and grabbers that you can attach uh bring up a servo, right? you know, wire it up with Node Red, Python, whatever your your interface of choosing and extend it, right? So, I would say, you know, a three-year time frame is what I would feel comfortable just, you know, off the cuff saying from from an electronic standpoint, but the the repeatability of printing and modifying, you know, can exist uh indefinitely. Yeah, that’s one of the really nice things I think about the platform you’ve built here is I mean you basically can you know if a servo burns out put a new one on there right that’s uh that’s very nice [snorts] what is the difference between a developer kit and the single build kit good question Satia like one of the things that we have been doing I I have a I’ll just call it the the flight kit it it’s just our our flight controller with optical flow and so there’s There’s no true programming, if you will. It’s learning how to fly, learning your different flight modes, navigating around. And then the the developer kit is where we introduced um the the Raspberry Pi CM5. Uh the carrier for more breakout and expansibility. One of the things that we do have uh for a larger drone and we’re trying to bring this down to a smaller scale is the ability to um add in this case we have a hat with a this Halo accelerator, right? So we we we right today that most of the YOLO that we do and vision stuff runs on CPU and that’s as you guys know constrained for a Raspberry Pi and we can slow we’ll slow the frame rate down but with acceleration we can um you know obviously run more uh frames for inference and so really the the flight kit is sort of the standard you you have to learn how to build and fly Right. So, if you that’s that’s what we reinforce and then when you get into the programming um that’s where you have the the add-ons with the compute and accelerator. Got it. Got it. Very nice. Um got another question here from Zoom. Um Zoom asks, “What’s the possibility of having a few different cameras facing down on one of these drones?” That’s a I wish I could untether from my headphones, but we have actually I might be able to do this in real time to um I I I understand the question. A few cameras. I’m going to share my screen if that’s okay. Phil, can I do that? All right. Here we go. And so, um this is for the downward. Let me just say down. Okay. Yeah. So we have a downward camera mount that that sort of mounts in the frame. We right now run py cam V2 and V3. And so you [snorts] there are two ports two camera ports on the I’ll say DEXC5 that’s the larger drone 5- in propellers that you can basically uh run through the the camera stack. Right. So you can do t two simultaneous cameras with the DEX3. Right now, we just support one and with with a tilt modification, right? So, you have the ability for the forward facing or the downward. And we’re working to uh have multicam support for the smaller drone, but it doesn’t exist today. Got it. Yeah, thanks for that. Um, I’ve actually got a question from me, which is I’m always really interested in the thermal issues for this this kind of embedded compute because it’s always an issue and and even with like the Raspberry Pi, especially with the Pi 5 uh and and the the CM5, they get a lot hotter than previous way hotter than previous versions. And so, uh, what I’d like to know is do you notice a like what are the differences in the thermal temp with say a drone at rest versus a drone moving around up in the air? Uh, if if you would have told me that question were coming, I could show I I would I’d spend the rest of this call trying to trying [laughter] to find that chart, right? But so CM5 is crazy hot, right? Right. And so we’re we advocate if you’re doing development, one of the things we do is advocate do your development in the simulation, right? Like that we have code VS code in the cloud, whatever. When you’re ready, bring that over to the drone. But I’m guilty of just testing on real hardware sitting on the bench. So we have like, you know, a cheap USBC CPU fan or GPU fan that just keeps it cool. Now, I would say under rest, we’re probably at 80 to 90C, right? And and we’re not really taxing the CPU very hard uh with our out of the box OS. But what you’ll observe is that the minute you arm the motors and because of all that, you know, propw wash we call it, as you get up, we’re we’re we’re down to 50C or less, right? While it that’s a huge drop. And I would there’s ever an opportunity to to share in the future. I I’ll I’ll send you a link just because you asked, you’ll see that just dip so quickly. Much faster than, you know, obviously a CPU fan sitting on the bench, right? It’s um Yeah, great great question. Oh, thanks. We’re we’re I think about at time here. Um, if we’ve got any last minute questions, let me go ahead and check out Zoom. Um, looks like I think we got to everything here. Um, thanks so much for joining us this week, Dennis. This was a lot of fun. I I’m really uh you you all have built a what looks like to be a a really thoughtful and uh well-made platform for for education and for especially I’m I love that what you’ve the thought you’ve put into you know the repairability and the the DIYness of it all because that’s also part of the education process like there’s something really exciting about uh oh you know one of the propellers broke well okay just go 3D print another one right like figure out the slicer and go 3D print another one like I I love that. Um, Phil, I know we’re running on time. I’ll just No, it’s all good, man. We We can The dream would be to 3D print and not have to injection mold propellers. Um, we’re still at the place from efficiency standpoint. I know you were using that example I’m getting hung up on. We would love to 3D print propellers that that were very efficient, didn’t kill battery life, and um but uh yes, everything but I’ll say that. Gotcha. Gotcha. So, the one example I chose was the wrong [laughter] one. But guess what? We have a gentleman that does a lot of CAD work and I’m going to tell his name is Aziz. Does incredible. He designed all our frame and everything. I’m going to say, “Hey, the Open CV Live guys uh said you couldn’t design and print a efficient propeller.” And we’ll see what he says. Oh yeah, sure. Blame me. I um Satia, we’ve got an awesome episode coming up next week with our friend France. Um I hopefully he’ll be wearing his raspberry beret. There’s another little musical reference for you guys out there. Um do you want to talk about cloud optimized OpenCV which will be our topic next week? Yeah. So uh next week we are going to talk about you know cloud optimized OpenCV. We some of you may have already heard about it. This is our uh optimized version of OpenCV on AWS Graviton. So uh Graviton’s new version Graviton 4 is out and so we are going to see how OpenCV performs on these processors. A ton of other things that France uh will is more more uh capable of uh explaining. So we’ll have that episode next time. So tune in. Uh it’s it’s going to be great. Yeah. Scan that QR code I just put up on screen. That’ll take you to the Amazon Web Services Marketplace listing for cloud optimized OpenCV. And you can join us next week to learn all about that. Um, I’m also going to remind you OpenCV has a Patreon. You can join us for just $2 a month and get OpenCV live streams over on Patreon as well as DRM free downloadable episodes of every new episode of OpenCV Live. Watch them however and whenever you want for just two bucks a month. There’s also a $7 a month tier. We appreciate all of your support. Everybody that gives us a dollar, $5. It really means a lot to us. Everybody working at OpenCV, not just myself, not just Satia, but the whole team out there. And uh we’ll be talking with a couple more of them. You guys have gotten pretty familiar with Gersomer and Abashek. and I I think they’ll be uh possibly uh be joining us a little bit next week as well to talk about cloud optimized OpenCV. But scan that QR code, join us on Patreon. You can sign up on the Patreon for free, but you won’t get those downloadables. You will, however, get um all of the Patreon posts and stuff like that as part of your uh free subscription on Patreon. We’re going to be trying to leverage this a little bit more. And hopefully in the future, we’ll also be now that Apple podcasts has video podcast support, we’re looking into uh setting up uh video podcast on Apple Podcast as well. That’ll probably be a paid thing, but it it won’t be expensive, I promise. So, please join us on Patreon and uh of course, subscribe to the OpenCV newsletter. Um follow us on the various social media platforms. We’re on Masttodon, Blue Sky, LinkedIn, uh YouTube, uh pretty much everywhere. And uh last but not least, thank you all for joining us this week and thank you Dennis for the presentation. Take care of yourselves out there, folks. And take care of somebody else if you can. And vamos Mexico. Adios.