In these turbulent times, journalists fearmonger and honest citizens fear for the safety of their homes and themselves. Adding some security features can allay these fears, and with the advent of cheap technology, front door cameras have become popular. There’s a wide array of options on the market, but short of watching hours of logged video, they’re not always super useful. Adding some smarts can really help – as [Peter Quinn] has done.
For this project, [Peter] decided on a JeVois smart camera. More than just a USB webcam, it also packs a quad-core processor running machine vision algorithms. This allows object recognition and other tasks to be run on the camera itself. In this setup, [Peter] configured the JeVois camera to detect people. When a human is detected upon the doorstep, the camera sends a message to the connected Raspberry Pi over serial. The Raspberry Pi then captures a JPEG still from the camera over the USB connection, and, using Twilio, sends a notification to [Peter]’s phone.
It’s a well-integrated system that automatically photographs visitors to [Peter]’s home, requiring little to no interaction from the user. We’ve seen other integrated machine vision platforms, too – such as the OpenMV, which got its start as a Hackaday Prize entry, way back in 2017.
In Ningbo, cameras oversee the intersections, and use facial-recognition to shame offenders by putting their faces up on large displays for all to see, and presumably mutter “tsk-tsk”. So it shocked Dong Mingzhu, the chairwoman of China’s largest air conditioner firm, to see her own face on the wall of shame when she’d done nothing wrong. The AIs had picked up her face off of an ad on a passing bus.
False positives in detecting jaywalkers are mostly harmless and maybe even amusing, for now. But the city of Shenzhen has a deal in the works with cellphone service providers to identify the offenders personally and send them a text message, and eventually a fine, directly to their cell phone. One can imagine this getting Orwellian pretty fast.
Facial recognition has been explored for decades, and it is now reaching a tipping point where the impacts of the technology are starting to have real consequences for people, and not just in the ways dystopian sci-fi has portrayed. Whether it’s racist, inaccurate, or easily spoofed, getting computers to pick out faces correctly has been fraught with problems from the beginning. With more and more companies and governments using it, and having increasing impact on the public, the stakes are getting higher.
The hottest new trend in photography is manipulating Depth of Field, or DOF. It’s how you get those wonderful portraits with the subject in focus and the background ever so artfully blurred out. In years past, it was achieved with intelligent use of lenses and settings on an SLR film camera, but now, it’s all in the software.
For the Pixel 2 smartphone, Google had used some tricky phase-detection autofocus (PDAF) tricks to compute depth data in images, and used this to decide which parts of images to blur. Distant areas would be blurred more, while the subject in the foreground would be left sharp.
This was good, but for the Pixel 3, further development was in order. A 3D-printed phone case was developed to hold five phones in one giant brick. The idea was to take five photos of the same scene at the same time, from slightly different perspectives. This was then used to generate depth data which was fed into a neural network. This neural network was trained on how the individual photos relate to the real-world depth of the scene.
With a trained neural network, this could then be used to generate more realistic depth data from photos taken with a single camera. Now, machine learning is being used to help your phone decide which parts of an image to blur to make your beautiful subjects pop out from the background.
[Enginoor] is on a quest. He wants to get into the world of 3D printing, but isn’t content to run off little toys and trinkets. If he’s going to print something, he wants it to be something practical and ideally be something he couldn’t have made quickly and easily with more traditional methods. Accordingly, he’s come out the gate with a fairly strong showing: a magnetic Maxwell kinematic coupling camera mount.
If you only recognized some of those terms, don’t feel bad. Named for its creator James Clerk Maxwell who came up with the design in 1871, the Maxwell kinematic coupling is self-orienting connection that lends itself to applications that need a positive connection while still being quick and easy to remove. Certainly that sounds like a good way to stick a camera on a tripod to us.
But the Maxwell design, which consists of three groves and matching hemispheres, is only half of the equation. It allows [enginoor] to accurately and repeatably line the camera up, but it doesn’t have any holding power of its own. That’s where the magnets come in. By designing pockets into both parts, he was able to install strong magnets in the mating faces. This gives the mount a satisfying “snap” when attaching that he trusts it enough to hold his Canon EOS 70D and lens.
[enginoor] says he could have made the holes a bit tighter for the magnets (thereby skipping the glue he’s using currently), but otherwise his first 3D printed design was a complete success. He sent this one off to Shapeways to be printed, but in the future he’s considering taking the reins himself if he can keep coming up with ideas worth committing to plastic.
With surface-mount technology pushing the size of components ever smaller, even the most eagle-eyed among us needs some kind of optical assistance to do PCB work. Lots of microscopes have digital cameras too, which can be a big help – unless the camera fights you.
Faced with a camera whose idea of autofocus targets on didn’t quite coincide with his, [Scott M. Baker] took matters into his own hands – foot, actually – by replacing mouse inputs to the camera with an outboard controller. His particular camera’s autofocus can be turned off, but only via mouse clicks on the camera’s GUI. That’s disruptive while soldering, so [Scott] used an Arduino Pro Micro and a small keypad to mimic the mouse movements needed to control the camera.
At the press of a key, the Arduino forces the mouse cursor up to the top left corner of the screen, pulls down the camera menu, and steps down the proper distance to toggle autofocus. The controller can also run the manual focus in and out or to take a screenshot. There’s even a footswitch that forces the camera to refocus if the field of view changes. It looks really handy, and as usual [Scott] provides a great walkthrough in the video below.
A Raspberry Pi with a camera is nothing new. But the Pixy2 camera can interface with a variety of microcontrollers and has enough smarts to detect objects, follow lines, or even read barcodes without help from the host computer. [DroneBot Workshop] has a review of the device and he’s very enthused about the camera. You can see the video below.
When you watch the video, you might wonder how much this camera will cost. Turns out it is about $60 which isn’t cheap but for the capabilities it offers it isn’t that much, either. The camera can detect lines, intersections, and barcodes plus any objects you want to train it to recognize. The camera also sports its own light source and dual servo motor drive meant for a pan and tilt mounting arrangement.
The engineers and product designers at [moovel lab] have created the Open Data Cam – an AI camera platform that can identify and count objects as they move through its field of view – along with an open source guide for making your own.
Step one: get out your ruler and utility knife. In this world of ubiquitous 3D-printers they’ve taken a decidedly low-tech approach to the project’s enclosure: a cut, folded, and zip-tied plastic box, with a cardboard frame inside to hold the electronic bits. It’s “splash proof” and certainly cheap to make, but we’re a little worried about cooling and physical protection for the electronics inside, as they’re not exactly cheap and rugged components.
So what’s inside? An Nvidia Jetson TX2 board, a LiPo battery with some charging circuitry, and a standard webcam. The special sauce, however, is the software, which is available on GitHub. [Moovel lab]’s engineers have put together a nice-looking wifi-accessible mobile UI for marking the areas where you’d like the software to identify and tally objects. The actual object detection and identification tasks are performed by the speedy YOLO neural network, a task the Nvidia board’s GPU is of course well suited for.
As the Open Data Cam’s unblinking glass eye gazes upon our urban environments, it will log its observations in an ancient and mysterious language: CSV. It’s up to you, human, to interpret this information and use it for good.
A summary video and build time lapse are embedded after the break.