Hackaday Prize Entry: Automated Wildlife Recognition

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.

Want Gesture-Tracking? All You Have To Do Is Lift Your Finger.

Watching Tony Stark wave his hands to manipulate projected constructs is an ever-approaching reality — at least in terms of gesture-tracking. Lift — a prototype built by a team from UC Irvine and FX Palo Alto Laboratory — is able to track up to ten fingers with 1.7 mm accuracy!

Lift’s gesture-tracking is achieved by using a DLP projector, two Arduino MKR1000s, and a light sensor for each digit. Lift’s design allows it to work on virtually any flat surface; the projected image acts as a grid and work area for the user. As their fingers move across the projected surface, the light sensors feed the information from the image to the Arduinos, which infers the location of each finger and translate it into a digital workspace. Sensors may also be mounted on other objects to add functionality.

So far, the team has used Lift as an input device for drawing, as well as using it to feign gesture controls on a standard laptop screen. The next step would be two or more projectors which would allow Lift to function fully and efficiently in three dimensions and directly interacting with projected media content. Can it also operate wirelessly? Yes. Yes, it can.

While we don’t have Tony Stark’s hologram workstation quite yet, we can still play Tetris, fly drones, and mess around with surgical robots.

Turn that Pi Zero into a Streaming Camera, Step-by-Step

What makes [mwagner1]’s Raspberry Pi Zero-based WiFi camera project noteworthy isn’t so much the fact that he’s used the hardware to make a streaming camera, but that he’s taken care to document every step in the process from soldering to software installation. Having everything in one place makes it easier for curious hobbyists to get those Pi units out of a drawer and into a project. In fact, with the release of the Pi Zero W, [mwagner1]’s guide has become even simpler since the Pi Zero W now includes WiFi.

Using a Raspberry Pi as the basis for a WiFi camera isn’t new, but it is a project that combines many different areas of knowledge that can be easy for more experienced people to take for granted. That’s what makes it a good candidate for a step-by-step guide; a hobbyist looking to use their Pi Zero in a project may have incomplete knowledge of any number of the different elements involved in embedding a Pi such as basic soldering, how to provide appropriate battery power, or how to install and configure the required software. [mwagner1] plans to use the camera as part of a home security system, so stay tuned.

If Pi Zero camera projects catch your interest but you want something more involved, be sure to check out the PolaPi project for a fun, well-designed take on a Pi Zero based Polaroid-inspired camera.

Your Arm Is The Ideal Controller

With interest and accessibility to both wearable tech and virtual reality approaching an all-time high, three students from Cornell University — [Daryl Sew, Emma Wang, and Zachary Zimmerman] — seek to turn your body into the perfect controller.

That is the end goal, at least. Their prototype consists of three Kionix tri-axis accelerometer, gyroscope and magnetometer sensors (at the hand, elbow, and shoulder) to trace the arm’s movement. Relying on a PC to do most of the computational heavy lifting, a PIC32 in a t-shirt canister — hey, it’s a prototype! — receives data from the three joint positions, transmitting them to said PC via serial, which renders a useable 3D model in a virtual environment. After a brief calibration, the setup tracks the arm movement with only a little drift in readings over a few minutes.

Continue reading “Your Arm Is The Ideal Controller”

Ikea Desk Lamp That Will Defend Your Lungs

While some people may enjoy the occasional whiff of noxious smells — gasoline, axe body spray, etc — prolonged exposure to fumes is not good for your health. This goes for soldering too, isn’t it about time you added some abatement to your bench tools?

Inspired by some of the fume hoods we’ve featured before — take note, ye who art lacking projects — [Georg Sluyterman] put together his own Ikea lamp fume extractor.

The most striking feature is that it’s mounted on an Ikea desk lamp making for convenient positioning and minimal clutter. A NeoPixels strip lights up your soldering space while the PIR sensor activates the fan when it detects movement. A WeMos D1 Mini is included for WiFi connectivity but that feature still down the road a little bit. The functionality that is in place is still quite impressive; more on that after the break.

Continue reading “Ikea Desk Lamp That Will Defend Your Lungs”

Slow Dance Appears to Make Time Run In Slow Motion

Rendering something in slow-motion is an often-used technique that attempts to add some ‘wow’ or ‘cool’ factor. Seeing something out in the world move in slow motion is marginally rarer — rarer still if it’s in your own home. But do it right and that kind of novelty turns a lot of heads. Enough to go 8x on a Kickstarter goal.

Slow Dance, a picture frame ringed with strobe lights, generates the surreal effect of turning small, everyday objects into languid kinetic sculptures. It’s an intriguing example of kinetic art done in a novel way.

[Jeff Lieberman], a veteran of high-speed photography, takes advantage of ‘persistence of vision’ by synchronizing the vibrations of an object — say, a feather — with a strobe light blinking 80 times per second. An electromagnet inside the frame is used to vibrate the objects, while the strobe lights are housed inside the thick frame.

Continue reading “Slow Dance Appears to Make Time Run In Slow Motion”

Multi Sensor Security Camera Has You Covered

Security in the home — especially a new home — is a primary concern for many. There are many options for security systems on the market, but for those will the skills, taking matters into your own hands can add peace of mind when protected by a system of one’s own design. [Armagan C.] has created  their near-ideal multi-sensor security module to keep a watchful eye out for would-be burglars.

Upgrading from their previous Arduino + Ethernet camera — which loved to trigger false alarms — [Armagan] opted for a used Raspberry Pi model B+ camera module and WiFi connection this time around. They also upgraded the unit with a thermal sensor, LPG & CO2 gas sensor, and a motion tracking alarm. [Armagan] has also set up a live streaming  feature that records video in 1hr segments — deleting them daily — and circumvented an issue with file descriptor leak by using a crashed drone’s flight controller to route the sensor data via serial port. It is also proving superior to conventional alarms because the custom software negates the need to disarm security zones during midnight trips to the washroom.

Continue reading “Multi Sensor Security Camera Has You Covered”