Review: Vizy Linux-Powered AI Camera

April 11, 2022 by Donald Papp 14 Comments

Vizy is a Linux-based “AI camera” based on the Raspberry Pi 4 that uses machine learning and machine vision to pull off some neat tricks, and has a design centered around hackability. I found it ridiculously simple to get up and running, and it was just as easy to make changes of my own, and start getting ideas.

Person and cat with machine-generated tags identifying them — Out of the box, Vizy is only a couple lines of Python away from being a functional Cat Detector project.

I was running pre-installed examples written in Python within minutes, and editing that very same code in about 30 seconds more. Even better, I did it all without installing a development environment, or even leaving my web browser, for that matter. I have to say, it made for a very hacker-friendly experience.

Vizy comes from the folks at Charmed Labs; this isn’t their first stab at smart cameras, and it shows. They also created the Pixy and Pixy 2 cameras, of which I happen to own several. I have always devoured anything that makes machine vision more accessible and easier to integrate into projects, so when Charmed Labs kindly offered to send me one of their newest devices, I was eager to see what was new.

I found Vizy to be a highly-polished platform with a number of truly useful hardware and software features, and a focus on accessibility and ease of use that I really hope to see more of in future embedded products. Let’s take a closer look.

Continue reading “Review: Vizy Linux-Powered AI Camera” →

Solving Wordle By Adding Machine Vision To A 3D Printer

February 26, 2022 by Dan Maloney 19 Comments

Truth be told, we haven’t jumped on the Wordle bandwagon yet, mainly because we don’t need to be provided with yet another diversion — we’re more than capable of finding our own rabbit holes to fall down, thank you very much. But the word puzzle does look intriguing, and since the rules and the interface are pretty simple, it’s no wonder we’ve seen a few efforts like this automated Wordle solver crop up lately.

The goal of Wordle is to find a specific five-letter, more-or-less-common English word in as few guesses as possible. Clues are given at each turn in the form of color-coding the letters to indicate whether they appear in the word and in what order. [iamflimflam1]’s approach was to attach a Raspberry Pi camera over the bed of a 3D printer and attach a phone stylus in place of the print head. A phone running Wordle is placed on the printer bed, and Open CV is used to find both the screen of the phone, as well as the position of the phone on the printer bed. From there, the robot uses the stylus to enter an opening word, analyzes the colors of the boxes, and narrows in on a solution.

The video below shows the bot in use, and source code is available if you want to try it yourself. If you need a deeper dive into Wordle solving algorithms, and indeed other variant puzzles in the *dle space, check out this recent article on reverse engineering the popular game.

Continue reading “Solving Wordle By Adding Machine Vision To A 3D Printer” →

Invisible 3D Printed Codes Make Objects Interactive

February 8, 2022 by Donald Papp 18 Comments

An interesting research project out of MIT shows that it’s possible to embed machine-readable labels into 3D printed objects using nothing more than an FDM printer and filament that is transparent to IR. The method is being called InfraredTags; by embedding something like a QR code or ArUco markers into an object’s structure, that label can be detected by a camera and interactive possibilities open up.

One simple proof of concept is a wireless router with its SSID embedded into the side of the device, and the password embedded into a different code on the bottom to ensure that physical access is required to obtain the password. Mundane objects can have metadata embedded into them, or provide markers for augmented reality functionality, like tracking the object in 3D.

How are the codes actually embedded? The process is straightforward with the right tools. The team used a specialty filament from vendor 3dk.berlin that looks nearly opaque in the visible spectrum, but transmits roughly 45% in IR. The machine-readable label gets embedded within the walls of a printed object either by using a combination of IR PLA and air gaps to represent the geometry of the code, or by making a multi-material print using IR PLA and regular (non-IR transmitting) PLA. Both provide enough contrast for an IR-sensitive camera to detect the label, although the multi-material version works a little better overall. Sadly, the average mobile phone camera by itself isn’t sufficiently IR-sensitive to passively read these embedded tags, so the research used easily available cameras with no IR-blocking filters, like the Raspberry Pi NoIR.

The PDF has deeper details of the implementation for those of you who want to know more, and you can see a demonstration of a few different applications in the video, embedded below. Determining the provenance of 3D printed objects is a topic of some debate in the industry, and it’s not hard to see how technology like this could be used to covertly identify objects without compromising their appearance.

Continue reading “Invisible 3D Printed Codes Make Objects Interactive” →

Spatial AI And CV Hack Chat

November 29, 2021 by Dan Maloney No comments

Join us on Wednesday, December 1 at noon Pacific for the Spatial AI and CV Hack Chat with Erik Kokalj!

A lot of what we take for granted these days existed only in the realm of science fiction not all that long ago. And perhaps nowhere is this more true than in the field of machine vision. The little bounding box that pops up around everyone’s face when you go to take a picture with your cell phone is a perfect example; it seems so trivial now, but just think about what’s involved in putting that little yellow box on the screen, and how it would not have been plausible just 20 years ago.

Perhaps even more exciting than the development of computer vision systems is their accessibility to anyone, as well as their move into the third dimension. No longer confined to flat images, spatial AI and CV systems seek to extract information from the position of objects relative to others in the scene. It’s a huge leap forward in making machines see like we see and make decisions based on that information.

To help us along the road to incorporating spatial AI into our projects, Erik Kokalj will stop by the Hack Chat. Erik does technical documentation and support at Luxonis, a company working on the edge of spatial AI and computer vision. Join us as we explore the depths of spatial AI.

Our Hack Chats are live community events in the Hackaday.io Hack Chat group messaging. This week we’ll be sitting down on Wednesday, December 1st at 12:00 PM Pacific time. If time zones have you tied up, we have a handy time zone converter.

Silky Smooth Resin Printer Timelapses Thanks To Machine Vision

September 18, 2021 by Dan Maloney 19 Comments

The fascination of watching a 3D printer go through its paces does tend to wear off after you spent a few hours doing it, in which case those cool time-lapse videos come in handy. Trouble is they tend to look choppy and unpleasant unless the exposures are synchronized to the motion of the gantry. That’s easy enough to do on FDM printers, but resin printers are another thing altogether.

Or are they? [Alex] found a way to make gorgeous time-lapse videos of resin printers that have to be seen to be believed. The advantage of his method is that it’ll work with any camera and requires no hardware other than a little LED throwie attached to the build platform of the printer. The LED acts as a fiducial that OpenCV can easily find in each frame, one that indicates the Z-axis position of the stage when the photo was taken. A Python program then sorts the frames, so it looks like the resin print is being pulled out of the vat in one smooth pull.

To smooth things out further, [Alex] also used frame interpolation to fill in the gaps where the build platform appears to jump between frames using real-time intermediate flow estimation, or RIFE. The details of that technique alone were worth the price of admission, and the results are spectacular. Alex kindly provides his code if you want to give this a whack; it’s almost worth buying a resin printer just to try.

Is there a resin printer in your future? If so, you might want to look over [Donald Papp]’s guide to the pros and cons of SLA compared to FDM printers.

Continue reading “Silky Smooth Resin Printer Timelapses Thanks To Machine Vision” →

RealSense No Longer Makes Sense For Intel

August 20, 2021 by Roger Cheng 15 Comments

We love depth-sensing cameras and every neat hack they enabled, but this technological novelty has yet to break through to high volume commercial success. So it was sad but not surprising when CRN reported that Intel has decided to wind down their RealSense product line.

As of this writing, one of the better confirmations for this report can be found on the RealSense SDK GitHub repository README. The good news is that core depth-sensing RealSense products will continue business as usual for the foreseeable future, balanced by the bad news that some interesting offshoots (facial authentication, motion tracking) will be declared “End of Life” immediately and phased out over the next six months.

This information tells us while those living out on the bleeding edge will have to scramble, there is no immediate crisis for everyone else, whether they be researchers, hobbyists, or product planners. But this also means there will be no future RealSense cameras, kicking off many “What’s Next?” discussions in various communities. Like this thread on ROS (Robot Operating System) Discourse.

Three popular alternatives offer distinctly different tradeoffs. The “Been Around The Block” name is Occipital, with their more expensive Structure Pro sensor. The “Old Name, New Face” option is Microsoft Azure Kinect, the latest non-gaming-focused successor to the gaming peripheral that started it all. And let’s not forget OAK-D as the “New Kid On The Block” that started with a crowdfunding campaign and building an user community by doing things like holding contests. Each of these will appeal to a different niche, and we’ll keep our eye open in the future. Let’s see if any of them find the success that eluded the original Kinect, Google’s Tango, and now Intel’s RealSense.

[via Engadget]

Machine-Vision Archer Makes You The Target, If You Dare

June 30, 2021 by Dan Maloney 6 Comments

We’ll state right up front that it’s a really, really bad idea to let a robotic archer shoot an apple off of your head. You absolutely should not repeat what you’ll see in the video below, and if you do, the results are all on you.

That said, [Kamal Carter]’s build is pretty darn cool. He wisely chose to use just about the weakest bows you can get, the kind with strings that are basically big, floppy elastic bands that shoot arrows with suction-cup tips and are so harmless that they’re intended for children to play with and you just know they’re going to shoot each other the minute you turn your back no matter what you told them. Target acquisition is the job of an Intel RealSense depth camera, which was used to find targets and calculate the distance to them. An aluminum extrusion frame holds the bow and adjusts its elevation, while a long leadscrew and a servo draw and release the string.

With the running gear sorted, [Kamal] turned to high school physics for calculations such as the spring constant of the bow to determine the arrow’s initial velocity, and the ballistics formula to determine the angle needed to hit the target. And hit it he does — mostly. We’re actually surprised how many on-target shots he got. And yes, he did eventually get it to pull a [William Tell] apple trick — although we couldn’t help but notice from his, ahem, hand posture that he wasn’t exactly filled with self-confidence about where the arrow would end up.

[Kamal] says he drew inspiration both from [Mark Rober]’s dart-catching dartboard and [Shane Wighton]’s self-dunking basketball hoop for this build. We’d say his results put in him good standing with the skill-optional sports community.

Continue reading “Machine-Vision Archer Makes You The Target, If You Dare” →