Trail and wildlife cameras are commonly available nowadays, but the Wild Eye project aims to go beyond simply taking digital snapshots of critters. [Brenda Armour] uses a Raspberry Pi to not only take photos of wildlife who wander into the camera’s field of view, but to also automatically identify and categorize the animals seen using a visual recognition API from IBM via the Node-RED infrastructure. The result is a system that captures an image when motion is detected, sends the image to the visual recognition API, and attempts to identify any wildlife based on the returned data.
The visual recognition isn’t flawless, but a recent proof of concept shows promising results with crows, a cat, and a dog having been successfully identified. Perhaps when the project is ready to move deeper into the woods, elements from these solar-powered networked birdhouses (which also use the Raspberry Pi) could help cut some cords.
We’re still not sure exactly how [connornishijima]’s motion detector works, though many readers offered plausible explanations in the comments the last time we covered it. It works well enough, though, and he’s gone and doubled down on the Arduino way and bundled it up nicely into a library.
In the previous article we covered [connor] demonstrating the motion detector. Something about the way the ADC circuit for the Arduino is wired up makes it work. The least likely theory so far involves life force, or more specifically, the Force… from Star Wars. The most likely theories are arguing between capacitance and electrostatic charge.
Either way, it was reliable enough a phenomenon that he put the promised time in and wrote a library. There’s even documentation on the GitHub. To initialize the library simply tell it which analog pin is hooked up, what the local AC frequency is (so its noise can be filtered out), and a final value that tells the Arduino how long to average values before reporting an event.
It seems to work well and might be fun to play with or wow the younger hackers in your life with your wizarding magics.
It is likely that many of us will at some time have experimented with motion detectors. Our Arduinos, Raspberry Pis, Beaglebones or whatever will have been hooked up to ultrasonic or PIR boards which will have been queried for their view of what is in front of them.
[Connornishijima] has stumbled on a different way to detect motion with an Arduino, he’s polling an ADC pin with a simple length of twisted pair hooked up to it and earth, and reliably generating readings indicating when he (or his cat) is in its vicinity. He’s calling the effect “Capacitive turbulence”, and he’s open to suggestions as to its mechanism. He can only make it work on the Arduino, other boards with ADCs don’t cut it.
Frequent Hackaday featuree [Mitxela] may have also discovered something similar, and we’ve hesitated to write about it because we didn’t understand it, but now it’s becoming unavoidable.
It’s always dangerous in these situations to confidently state your opinion as “It must be…” without experimental investigation of your own. Those of us who initially scoffed at the idea of the Raspberry Pi 2 being light sensitive and later had to eat their words have particular cause to remember this. But this is an interesting effect that bears understanding. We would guess that the Arduino’s fairly high input impedance might make it sensitive to mains hum, if you did the same thing to an audio amplifier with a phono input you might well hear significant hum in the speaker as your hand approached the wire. It would be interesting to try the experiment at an off-grid cabin in the woods, in the absence of mains hum.
If you’d like to give his experiment a try, he’s posted his sketch on Pastebin. And he’s put up the video below the break demonstrating the effect in action, complete with cats.
Continue reading “Arduino Motion Detection With A Bit Of Wire”
We’ve been seeing a lot of garage door opener hacks, whether it’s because one person inspired everyone else to build their own Internet-connected GDO or because there’s something in the water that’s caused the simultaneous building of one specific type of project, we’re not sure. However, the latest one we’ve seen adds a little something extra: motion-based security.
[DeckerEgo] really went all out with this one, too. The core of the project is a Raspberry Pi hardwired to a universal garage door remote. The Pi also handles a small webcam and runs a program called motion, which is a Linux program that allows for all kinds of webcam fun including motion detection. While the other builds we see usually use a button or limit switch to tell whether the door is open or closed, this one just watches the door with the webcam so [DeckerEgo] can actually see what’s going on in the garage. As a bonus, the motion software can be configured to alert him if anything suspicious is going on in the garage.
The build is full-featured as well, with an interesting user interface overlaid on the live picture of the garage door. According to [DeckerEgo] the camera is a necessity because he wouldn’t trust a simple status indicator, but if you wanted to try one of those before breaking out the Raspberry Pi, we’ve featured one recently that you can check out.
Fans of the bouncing lamp from the Pixar corporate logo will enjoy [Daniel]’s latest project. It’s a motion controlled desk lamp that uses ultrasonic sensors to control its physical position.
The core of the project is an Arduino and the three ultrasonic sensors. The sensors act as range finders, and when they are all working together under the direction of the microcontroller they can tell which direction a hand was moving when it passed by. This information is used to drive two servos, one in the base and one on the lamp’s arm.
The project requires an articulating desk lamp of some sort (others besides the specific one [Daniel] used shouldn’t be much of a problem as long as they bend in the same way). Most hackers will have the rest of the parts on hand, with the possible exception of the rangefinder. The code is up on the project site for a look-see or in case you want to build your own.
The only problem that [Daniel] had when putting this all together was that the base was a little wobbly. He was able to fix that with some thumbtacks, and we think the next step for the project should be switching the light on and off over the internet.
[Gil] sent in an awesome paper from this year’s SIGGRAPH. It’s a way to detect subtle changes in a video feed from [Hao-Yu Wu, et al.] at the MIT CS and AI lab and Quanta Research. To get a feel for what this paper is about, check out the video and come back when you pick your jaw off the floor.
The project works by detecting and amplifying very small changes in color occurring in several frames of video. From the demo, the researchers were able to detect someone’s pulse by noting the very minute changes in the color of their skin whenever their face is pumped full of blood.
A neat side effect of detecting small changes in color is the ability to also detect motion. In the video, there’s an example of detecting someone’s pulse by exaggerating the expanding artery in someone’s wrist, and the change in a shadow produced by the sun over the course of 15 seconds. This is Batman-level tech here, and we can’t wait to see an OpenCV library for this.
Even though the researchers have shown an extremely limited use case – just pulses and breathing – we’re seeing a whole lot of potential applications. We’d love to see an open source version of this tech turned into a lie detector for the upcoming US presidential debates, and the motion exaggeration is perfect for showing why every sports referee is blind as a bat.
If you want to read the actual paper, here’s the PDF. As always, video after the break.
Continue reading “Tracking small changes in video to see someone’s pulse”