Vizy The AI Camera Aims To Ease Machine Vision

mature casting hdCameras are getting smarter and more capable than ever, able to run embedded machine vision algorithms and pull off tricks far beyond what something like a serial camera and microcontroller board would be capable of, and the upcoming Vizy aims to be even smarter and easier to use yet. Vizy is the work of Charmed Labs, and this isn’t their first foray into accessible machine vision. Charmed Labs are the same folks behind the Pixy and Pixy 2 cameras. Vizy’s main goal is to make object detection and classification easy, with thoughtful hardware features and a browser-based interface.

Vizy can identify common birds with “Birdfeeder”, one of the several built-in applications that uses local processing only.

mature casting hdThe usual way to do machine vision is to get a USB camera and run something like OpenCV on a desktop machine to handle the processing. But Vizy leverages a Raspberry Pi 4 to provide a tightly-integrated unit in a small package with a variety of ready-to-run applications. For example, the “Birdfeeder” application comes ready to take snapshots of and identify common species of bird, while also identifying party-crashers like squirrels.

The demonstration video on their page shows off using the built-in high-current I/O header to control a sprinkler, repelling non-bird intruders with a splash of water while uploading pictures and video clips. The hardware design also looks well thought out; not only is there a safe shutdown and low-power mode for the Raspberry Pi-based hardware, but the lens can be swapped and the camera unit itself even contains an electrically-switched IR filter.

Vizy has a Kickstarter campaign planned, but like many others, Charmed Labs is still adjusting to the changes the COVID-19 pandemic has brought. You can sign up to be notified when Vizy launches; we know we’ll be keen for a closer look once it does. Easier machine vision is always a good thing, because it helps free people to focus on clever ideas like machine vision-based tool alignment.

OAK Vision Modules Help You See The Forest And The Trees

OpenCV is an open source library of computer vision algorithms, its power and flexibility made many machine vision projects possible. But even with code highly optimized for maximum performance, we always wish for more. Which is why our ears perk up whenever we hear about a hardware accelerated vision module, and the latest buzz is coming out of the OpenCV AI Kit (OAK) Kickstarter campaign.

There are two vision modules launched with this campaign. The OAK-1 with a single color camera for two dimensional vision applications, and the OAK-D which adds stereo cameras for that third dimension. The onboard brain is a Movidius Myriad X processor which, according to team members who have dug through its datasheet, have been massively underutilized in other products. They believe OAK modules will help the chip fulfill its potential for vision applications, delivering high performance while consuming low power in a small form factor. Reading over the spec sheet, we think it’s fair to call these “Ultimate Myriad X Dev Boards” but we must concede “OpenCV AI Kit” sounds better. It does not provide hardware acceleration for the entire OpenCV library (likely an impossible task) but it does cover the highly demanding subset suitable for Myriad X acceleration.

Since the campaign launched a few weeks ago, some additional information have been released to help assure backers that this project has real substance. It turns out OAK is an evolution of a project we’ve covered almost exactly one year ago that became a real product DepthAI, so at least this is not their first rodeo. It is also encouraging that their invitation to the open hardware community has already borne fruit. Check out this thread discussing OAK for robot vision, where a question was met with an honest “we don’t have expertise there” from the OAK team, but then ArduCam pitched in with their camera module experience to help.

We wish them success for their planned December 2020 delivery. They have already far surpassed their funding goals, they’ve shipped hardware before, and we see a good start to a development community. We look forward to the OAK-1 and OAK-D joining the ranks of other hacking friendly vision modules like OpenMV, JeVois, StereoPi, and AIY Vision.

Tales (and Advice) From Setting Up A Product Line

Making something that has to get into others’ hands involves solving a lot of different problems, many of which have nothing at all to do with actually building the dang things. [Conor Patrick] encountered them when he ran a successful Kickstarter campaign for an open-source USB security key that was not only shipped to backers, but also made available as an ongoing product for sale. There was a lot of manual and tedious work that could have been avoided, and so [Conor] laid out all the things he wishes he had done when first setting up a product line.

Turning these unprogrammed boards into finished products then shipping them is a big job.

If the whole process is a river, then the more “upstream” an issue is, the bigger its potential impact on everything that comes afterwards. One example is the product itself: the simplest and most easily managed product line is one that has only one product with no variations. That not only minimizes errors but makes supply, production, and shipping more straightforward. Striving for a minimum number of products and variations is also an example of something [Conor] didn’t do. In their crowdfunding campaign they offered the SoloKeys USB device — an implementation of the FIDO2 authentication token — as either USB-A or USB-C. There were also two types of key: NFC-capable (for tapping to a smartphone) and USB only. That is four products so far.

Offering keys in an unlocked state for those who want to tamper makes it eight different products. On top of that, they offered color choices which not only adds complexity to production, but also makes it harder to keep track of what everyone ordered. [Conor] also observed that the Kickstarter platform and back end are really not set up like a store, and it is clunky at best to try to offer (and manage) different products and variations from within it.

Another major point is fulfillment and in [Conor]’s opinion, unless the quantities are small, an order fulfillment company is worth partnering with. He says there are a lot of such companies out there, and it can be very time consuming to find the right one, but it will be nothing compared to the time and effort needed to handle, package, address, and ship several hundreds (or thousands!) of orders personally. His team did their own fulfillment for a total of over 2000 units, and found it a long and tedious process filled with hidden costs and challenges.

There’s good advice and background in [Conor]’s writeup, and this isn’t his first rodeo. He also shared his thoughts on taking electronics from design to production and the more general advice remains the same for it all: be honest and be open. Under-promise and over-deliver, especially when it comes to time estimates.

Hackaday Links: December 29, 2019

The retrocomputing crowd will go to great lengths to recreate the computers of yesteryear, and no matter which species of computer is being restored, getting it just right is a badge of honor in the community. The case and keyboard obviously playing a big part in that look, so when a crowdfunding campaign to create new keycaps for the C64 was announced, Commodore fans jumped to fund it. Sadly, more than four years later, the promised keycaps haven’t been delivered. One disappointed backer, Jim Drew, decided he was sick of waiting, so he delved into the world of keycaps injection molding and started his own competing campaign. Jim details his adventures in his Kickstarter Indiegogo campaign, which makes for good reading even if you’re not into Commodore refurbishment. Here’s hoping Jim has better luck than the competition did.

Looking for anonymity in our increasingly surveilled world? You’re not alone, and in fact, we predict facial recognition spoofing products and methods will be a growth industry in the new decade. Aside from the obvious – and often illegal – approach of wearing a mask that blocks most of the features machine learning algorithms use to quantify your face, one now has another option, in the form of a colorful pattern that makes you invisible to the YOLOv2 algorithm. The pattern, which looks like a soft-focus crowd scene rendered in Mardi Gras colors, won’t make the algorithm think you’re someone else, but it will prevent you from being classified as a person. It won’t work with any other AI algorithm, but it’s still an interesting phenomenon.

We saw a great hack come this week about using an RTL-SDR to track down a water leak. Clayton’s water bill suddenly skyrocketed, and he wanted to track down the source. Luckily, his water meter uses the encoder receive-transmit (ERT) protocol on the 900 MHz ISM band to report his usage, so he threw an SDR dongle and rtlamr at the problem. After logging his data, massaging it a bit with some Python code, and graphing water consumption over time, he found that water was being used even when nobody was home. That helped him find the culprit – leaky flap valves in the toilets resulting in a slow drip that ran up the bill. There were probably other ways to attack the problem, but we like this approach just fine.

Are your flex PCBs making you cry? Friend of Hackaday Drew Fustini sent us a tip on teardrop pads to reduce the mechanical stress on traces when the board flexes. The trouble is that KiCad can’t natively create teardrop pads. Thankfully an action plugin makes teardrops a snap. Drew goes into a bit of detail on how the plugin works and shows the results of some test PCBs he made with them. It’s a nice trick to keep in mind for your flexible design work.

ATX2AT Makes Retrocomputing Safer, Heads To Kickstarter

It’s easy to take power supplies for granted in modern computing, but powering vintage hardware is not always so simple or worry-free. The power supplies for old electronics are themselves vintage, and the hardware being powered can be quite precious. A power problem can easily cause fried components and burned traces on a board. As [Doc TB] observes, by the time you hear crackling, it’s already far too late.

To address this, [Doc TB] designed the ATX2AT Smart Converter as an open source project and recently decided to make it available through a Kickstarter campaign. ATX2AT is a way to safely and securely replace some vintage power supplies with a standard PC ATX power supply, and adds a large number of protection features such as current monitoring and programmable reaction time for overcurrent protection. All of this can help prevent a retrocomputer enthusiast’s precious vintage hardware from being damaged in the event of a problem. It’s not just for powering known-good hardware; it can be invaluable when testing or repairing hardware that might be in an unknown state.

When we first came across [Doc TB]’s ATX2AT project we recognized it as a well-made device to address a specific niche, and to do it well. Assessing risk takes into account not only the probability of a problem occurring, but also just how bad things would be if it did happen. If your old hardware is precious enough to warrant the extra protection, or you are into repairing or assessing old hardware, then an ATX2AT might be just what you need. You can see it in action in the video embedded below.

Continue reading “ATX2AT Makes Retrocomputing Safer, Heads To Kickstarter”

Trill: Easy Positional Touch Sensors For Your Projects

Creating capacitive touch-sensitive buttons is easy these days; many microcontrollers have cap-sense hardware built-in. This will work for simple on/off control, but what if you want a linear, position-sensitive input, like you’d find on a computer touchpad or your smartphone screen? Not so easy — at least until now. Trill is a family of capacitive touch sensors you can add to your projects as a linear slider, a square touchpad, or by creating your own touch surface.

Trill was created by the same team that designed Bela, an embedded platform for low-latency interactive applications, especially with audio. The new trio of Trill sensors rely on capacitive sensing to track finger movement, and communicate over I2C with your microcontroller or development board of choice. The Trill I2C library targets Arduino and Bela, but should be easy to port to any I2C host.

The hardware and software are both open-source — or will be as the Kickstarter that launched this morning has already met its goal. The firmware for the Cypress CY8C20636A (PDF) controller that powers these sensors will be released CC-BY-NC-SA. But, starting with the controller itself sounds like a lot of work that Trill has already done for you, so let’s have a look at what we know so far, along with a healthy dose of speculation.

Continue reading “Trill: Easy Positional Touch Sensors For Your Projects”

Hackaday Links: September 15, 2019

It’s probably one of the first lessons learned by new drivers: if you see a big, red fire truck parked by the side of the road, don’t run into it. Such a lesson appears not to have been in the Tesla Autopilot’s driver education curriculum, though – a Tesla Model S managed to ram into the rear of a fire truck parked at the scene of an accident on a southern California freeway. Crash analysis reveals that the Tesla was on Autopilot and following another vehicle; the driver of the lead vehicle noticed the obstruction and changed lanes. Apparently the Tesla reacted to that by speeding up, but failed to notice the stationary fire truck. One would think that the person driving the car would have stepped in to control the vehicle, but alas. Aside from beating up on Tesla, whose AutoPilot feature seems intent on keeping the market for batteries from junked vehicles fully stocked, this just points out how far engineers have to go before self-driving vehicles are as safe as even the worst human drivers.

The tech press is abuzz today with stories about potential union-busting at Kickstarter. Back in March, Kickstarter employees announced their intent to organize under the Office and Professional Employees International Union (OPEIU). On Thursday, two of the union organizers were fired. Clarissa Redwine, who recently hosted a Hack Chat, was one of those released; both she and Taylor Moore are protesting their terminations as an illegal attempt to intimidate Kickstarter employees and keep them from voting for the union. For their part, Kickstarter management says that both employees and two more were released as a result of documented performance issues during the normal review cycle, and that fourteen employees who are in favor of the union were given raises during this cycle, with three of them having been promoted. There will no doubt be plenty more news about this to come.

Would you pay $900 for a Nixie clock? We wouldn’t, but if you choose to buy into Millclock’s high-end timepiece, it may help soften the blow if you think about it being an investment in the future of Nixie tubes. You see, Millclock isn’t just putting together an overpriced clock that uses surplus Russian Nixies – they’re actually making brand new tubes. Techmoan recently reviewed the new clock and learned that the ZIN18 tubes are not coming from Czech Republic-based Dalibor Farn?, but rather are being manufactured in-house. That’s exciting news for Nixie builders everywhere; while Dalibor’s tubes are high-quality products, it can’t hurt to have a little competition in the market. Nixies as a growth industry in 2019 – who’da thunk it?

We ran across an interesting project on Hackaday.io the other day, one that qualifies as a true hack. How much house can you afford? A simple question, but the answer can be very difficult to arrive at with the certainty needed to sign papers that put you on the hook for the next 30 years. Mike Ferarra and his son decided to answer this question – in a circuit simulator? As it turns out, circuit simulators are great at solving the kinds of non-linear simultaneous equations needed to factor in principle, interest, insurance, taxes, wages, and a host of other inflows and outflows. Current sources represent money in, current sinks money paid out. Whatever is left is what you can afford. Is this how Kirchoff bought his house?

And finally, is your parts inventory a bit of a mystery? Nikhil Dabas decided that rather than trying to remember what he had and risk duplicating orders, he’d build an application to do it for him. Called WhatDidIBuy, it does exactly what you’d think; it scrapes the order history pages of sites like Adafruit, Digi-Key, and Mouser and compiles a list of your orders as CSV files. It’s only semi-automated, leaving the login process to the user, but something like this could save a ton of time. And it’s modular, so adding support for new suppliers is a simple as writing a new scraper. Forgot what you ordered from McMaster, eBay, or even Amazon? Now there’s an app for that.