This Camera Produces A Picture, Using The Scene Before It

February 25, 2023 by Jenny List 23 Comments

It’s the most basic of functions for a camera, that when you point it at a scene, it produces a photograph of what it sees. [Jasper van Loenen] has created a camera that does just that, but not perhaps in the way we might expect. Instead of committing pixels to memory it takes a picture, uses AI to generate a text description of what is in the picture, and then uses another AI to generate an image from that picture. It’s a curiously beautiful artwork as well as an ultimate expression of the current obsession with the technology, and we rather like it.

The camera itself is a black box with a simple twin-lens reflex viewfinder. Inside is a Raspberry Pi that takes the photo and sends it through the various AI services, and a Fuji Instax Mini printer. Of particular interest is the connection to the printer which we think may be of interest to quite a few others, he’s reverse engineered the Bluetooth protocols it uses and created Python code allowing easy printing. The images it produces are like so many such AI-generated pieces of content, pretty to look at but otherworldly, and weird parallels of the scenes they represent.

It’s inevitable that consumer cameras will before long offer AI augmentation features for less-competent photographers, meanwhile we’re pleased to see Jasper getting there first.

How To Roll Your Own Custom Object Detection Neural Network

February 13, 2023 by Donald Papp 2 Comments

Real-time object detection, which uses neural networks and deep learning to rapidly identify and tag objects of interest in a video feed, is a handy feature with great hacker potential. Happily, it’s also possible to make customized CNNs (convolutional neural networks) tailored for one’s own needs, and that process just got easier thanks to some new documentation for the Vizy “AI camera” by Charmed Labs.

Charmed Labs has been making hacker-friendly machine vision devices for a long time, and the Vizy camera impressed us mightily when we checked it out last year. Out of the box, Vizy has a perfectly functional object detector application that runs locally on the device, and can detect and tag many common everyday objects in real time. But what if that default application doesn’t quite meet one’s project needs? Good news, because it’s possible to create a custom-trained CNN, and that process got a lot more accessible thanks to step-by-step examples of training a model to recognize hands doing rock-paper-scissors.

Person and cat with machine-generated tags identifying them — Default object detection works well, but sometimes one needs custom results.

The basic process is this: Start with a variety of images that show the item of interest. Then identify and label the item of interest in each photo. These photos (a “training set”) are then sent to Google Colab, which will be used to generate a neural network. The resulting CNN model can then be downloaded and used, to see how well it performs.

Of course things rarely work perfectly the first time around, so at this point it’s pretty common for some refinement to be needed to increase accuracy. Luckily there are a number of tools to help do this without creating a new model from scratch, so it’s just a matter of tweaking until things perform acceptably.

Google Colab is free and the resulting CNNs are implemented in the TensorFlow Lite framework, meaning it’s possible to use them elsewhere. So if custom object detection has been holding up a project idea of yours, this might be what gets you over that hump.

An Instant Camera Using E-Paper As Film

February 10, 2023 by Jenny List 16 Comments

The original Polaroid cameras were a huge hit not just for their instant delivery, but for the convenient size of the permanent images they delivered. It’s something that digital cameras haven’t been able to replicate, which drew [Cameron] to produce a modern alternative. In the place of the chemical film of the original, it uses a removable e-paper display in a frame. The image is stored in the pixels of the e-paper, which can be kept as a digital version of the photograph until reattached and replaced with another freshly taken picture.

At its heart is an ESP32 with a camera, and the “film” is a Waveshare NFC e-paper module. The device is 3D printed, and manages a very creditable early-1970s aesthetic redolent of the more upmarket Polaroids of the day. Using it is as simple as pressing the button and deciding whether you like what’s on the screen. You can see it in action in the video below the break.

We like his project for its aesthetics, as well as for the very idea of using e-paper as a medium. There’s also something to be said for not having to put a Polaroid print in a clip under your armpit while it develops. Meanwhile if you do hanker for the real thing, it’s a subject we’ve looked at in the past.

Continue reading “An Instant Camera Using E-Paper As Film” →

Do You Need The Raspberry Pi Camera Module V3?

January 26, 2023 by Jenny List 22 Comments

This month came the announcement of some new camera modules from Raspberry Pi. All eyes were on version 3 of their standard camera module, but they also sneaked out a new version of their high quality camera with an M12 lens mount. The version 3 module is definitely worth a look, so I jumped on a train to Cambridge for the Raspberry Pi Store, and bought myself one for review.

There’s nothing new about a Pi camera module as they’ve been available for years in both official and third party forms, so to be noteworthy the new one has to offer something a bit special. It uses a 12 megapixel sensor, and is available both in autofocus and wide angle versions in both standard and NoIR variants. Wide angle and autofocus modules may be new in the official cameras, but these are both things which have been on the third-party market for years.

So if an autofocus camera module for your Pi isn’t that new, what can we bring to a review that isn’t simply exclaiming over the small things? Perhaps it’s better instead to view the new camera in the context of the state of the Pi camera ecosystem, and what better way to do that than to turn a Pi and some modules into a usable camera! Continue reading “Do You Need The Raspberry Pi Camera Module V3?” →

Better Macro Images With Arduino Focus Stacking

January 26, 2023 by Al Williams 17 Comments

If you’ve ever played around with macro photography, you’ve likely noticed that the higher the lens magnification, the less the depth of field. One way around this issue is to take several slices at different focus points, and then stitch the photos together digitally. As [Curious Scientist] demonstrates, this is a relatively simple motion control project and well within the reach of a garden-variety Arduino.

You can move the camera or move the subject. Either way, you really only need one axis of motion, which makes it quite simple. This build relies on a solid-looking lead screw to move a carriage up or down. An Arduino Nano acts as the brains, a stepper motor drives the lead screw, and a small display shows stats such as current progress and total distance to move.

The stepper motor uses a conventional stepper driver “stick” as you find in many 3D printers. In fact, we wondered if you couldn’t just grab a 3D printer board and modify it for this service without spinning a custom PCB. Fittingly, the example subject is another Arduino Nano. Skip ahead to 32:22 in the video below to see the final result.

We’ve seen similar projects, of course. You can build for tiny subjects. You can also adapt an existing motion control device like a CNC machine.

Continue reading “Better Macro Images With Arduino Focus Stacking” →

A red and blue Lytro camera with a serial port soldered onto one

Unlocking Hidden Features Of An Unusual Camera

January 25, 2023 by Robin Kearey 65 Comments

Back in 2012, technology websites were abuzz with news of the Lytro: a camera that was going to revolutionize photography thanks to its innovative light field technology. An array of microlenses in front of the sensor let it capture a 3D image of a scene from one point, allowing the user to extract depth information and to change the focus of an image even after capturing it.

The technology turned out to be a commercial failure however, and the company faded into obscurity. Lytro cameras can now be had for as little as $20 on the second-hand market, as [ea] found out when he started to investigate light field photography. They still work just as well as they ever did, but since the accompanying PC software is now definitely starting to show its age, [ea] decided to reverse-engineer the camera’s firmware so he could write his own application.

[ea] started by examining the camera’s hardware. The main CPU turned out to be a MIPS processor similar to those used in various cheap camera gadgets, next to what looked like an unpopulated socket for a serial port and a set of JTAG test points. The serial port was sending out a bootup sequence and a command prompt, but didn’t seem to respond to any inputs. Continue reading “Unlocking Hidden Features Of An Unusual Camera” →

Floppy Photog: Making An IR Filter From A 3.5″ Disk

January 21, 2023 by Al Williams 15 Comments

Sony used to sell digital cameras that recorded on actual floppy disks. We’ve come a long way, but [Mathieu] put a floppy in a digital camera recently for an entirely different reason. First, though, he had to modify the camera to work on the full spectrum, something he covered in an earlier video. You can see both videos, below.

As you might expect, he didn’t actually put an entire floppy inside the camera. He used the internal disk portion as an infrared filter to obtain some striking photos. In all honestly, the results were not as nice as what you get from a very expensive professional filter. But the pictures looked great and the difference was not as much as you’d expect compared to the cost difference.

The real work, though, is converting the camera to full spectrum as seen in the second video. A normal camera has an IR filter to prevent the sensor from seeing IR light. This prevents the image sensor from capturing things your eyes don’t see. The modification replaces the filter with a clear filter.

We’ve covered this kind of conversion before. You can even do it with a Raspberry Pi, if you like.

Continue reading “Floppy Photog: Making An IR Filter From A 3.5″ Disk” →