Hackaday Prize 2023: Eye Tracking On A Budget

May 2, 2023 by 4 Comments

There is a lot to be learned from the experience of building something functional, and even better if doing so doesn’t break the bank. [Sergej Stoetzer]’s 20€ DIY-Eyetracker aims to be an educational process that covers everything from hardware to functional software in an accessible way.

Hardware based on an economical USB endoscope, and can be used as-is or repackaged with IR illumination.

The eye tracker is based on an economical USB endoscope, which is a small camera optimized for up-close applications. By attaching the camera to a pair of common safety glasses so that it looks at one’s eye, some OpenCV and Python code can do simple tracking and interfacing with other projects.

Basic eye tracking — like determining whether a user is looking up, down, left, or right — can be all that’s needed depending on one’s application. That means that it’s possible to get something working with very little hardware and some easy-to-use OpenCV functions.

Even better performance can be had by adding IR illumination and repackaging the camera into a 3D printed enclosure. The pupil of the eye is an aperture in the iris that appears as a black circle, and that’s even more true under IR illumination which is invisible to the naked eye. If you’re curious about what’s inside those USB endoscope cameras and how to remove their IR filter, there are some good pictures of that process in this project.

The ability to get something prototyped quickly and working well enough to learn new things is a valuable skill, and that’s why re-engineering Education is one of the challenges in the 2023 Hackaday Prize.

The HackadayPrize 2023 is Sponsored by:
Four images in one. Top left is an image of four individuals in a room with whiteboards and desks in the background along with various clutter on the floor. Over the people is a wireframe overlay of their poses. The image on the top right is just the wireframe people on a black background. Bottom left image is of a single individual standing in a room with the pose wireframe overlay. Bottom right image is the single pose wireframe on a black background.

Tracking Humans With WiFi

January 26, 2023 by 45 Comments

In case you thought that cameras, LiDAR, infrared sensors, and the like weren’t enough for Big Brother to track you, researchers from Carnegie Mellon University have found a way to track human movements via WiFi. [PDF via VPNoverview]

The process uses the signals from WiFi routers for an inexpensive way to determine human poses that isn’t hampered by lack of illumination or object occlusion. The system produces UV coordinates of human bodies by analyzing signal strength and phase data to generate a 2D feature map and then feeding that through a modified DensePose-RCNN architecture which corresponds to 3D human poses. The system does have trouble with unusual poses that are not in the training set or if there are more than three subjects in the detection area.

While there are probably applications in Kinect-esque VR Halo games, this will probably go straight into the toolbox of three letter agencies and advertising-fueled tech companies. The authors claim this to use “privacy-preserving algorithms for human sensing,” but only time will tell if they’re correct.

If you’re interested in other creepy surveillance tools, checkout the Heat-Sensing Crotch Monitor or this Dystopian Peep Show.

Tracking Weather Balloons With SDR

September 8, 2022 by 26 Comments

The advent of cheap software-defined radio hardware means that what would have once been an exotic expensive undertaking can now be relatively cheap. [David] notes that using some pretty simple gear, he could track down weather balloons.

The U.S. National Weather Service sends up a large number of radiosondes attached to balloons twice a day. Their job is to measure conditions at high altitudes up to about 30km. Once the balloon gets too high, the pressure inside bursts the balloon, and a small parachute slows the instrument package’s descent back to Earth. [David] wanted to track these down and return them to the NWS for reuse.

Continue reading “Tracking Weather Balloons With SDR” →

Hackaday Prize 2022: Compact Solar Tracking System Doesn’t Break The Bank

August 28, 2022 by 33 Comments

If you need to squeeze every available watt out of a solar panel, you’ll probably want to look into a solar tracking system. Unfortunately, they are usually quite large, heavy, and expensive. As an alternative, [JP Gleyzes] has put together a DIY solar tracking system that aims to address these issues.

Starting with a 100 W flexible solar panel purchased during a Black Friday sale, [JP] first created a simple frame using 20 mm PVC tubing and a few 3D printed brackets. It mounts on a wooden base with a printed worm gear rotation mechanism, powered by a stepper motor. The tilt is a handled by a lead screw made from a threaded rod, connected between the wooden base and the top of the solar panel, and is also driven by a stepper motor.

For even more efficiency, [JP] also created an MPPT charge controller with companion app using an ESP32, modified 20 A buck converter, and current sensor module. The ESP32 also controls the stepper motors. The optimum angle for the solar panel determined using the date, time, and the system’s GPS position. [JP] had also created a simple Android app to calibrate the panels’ start position.

This project is a finalist in the Planet-Friendly Power challenge of the 2022 Hackaday Prize, and all the details to build your own are available on your project page. Looking at the size of the system, we suspect future iterations could be even smaller.

Continue reading “Hackaday Prize 2022: Compact Solar Tracking System Doesn’t Break The Bank” →

Maximum Power Point Tracking: Optimizing Solar Panels

August 3, 2022 by 59 Comments

When looking at integrating a photovoltaic solar panel into a project, the naive assumption would be that you simply point the panel into the general direction of where the Sun is, and out comes gobs of clean DC power, ready to be used for charging a battery. To a certain extent this assumption is correct, but feeding a solar panel’s output into something like a regular old PWM buck or boost regulator is unlikely to get you anywhere close to the panel’s full specifications.

The keywords here are ‘maximum power point’ (MPP), which refers to the optimal point on the solar panel’s I-V curve. This is a property that’s important not only with photovoltaics, but also with wind turbines and other highly variable power sources. The tracking of this maximum power point is what is generally referred to as ‘MPPT‘, but within this one acronym many different algorithms are covered, each with its own advantages and disadvantages. In this article we’ll take a look at what these MPPT algorithms are, and when you would want to pick a particular one.

Continue reading “Maximum Power Point Tracking: Optimizing Solar Panels” →

TapType: AI-Assisted Hand Motion Tracking Using Only Accelerometers

May 14, 2022 by 16 Comments

The team from the Sensing, Interaction & Perception Lab at ETH Zürich, Switzerland have come up with TapType, an interesting text input method that relies purely on a pair of wrist-worn devices, that sense acceleration values when the wearer types on any old surface. By feeding the acceleration values from a pair of sensors on each wrist into a Bayesian inference classification type neural network which in turn feeds a traditional probabilistic language model (predictive text, to you and I) the resulting text can be input at up to 19 WPM with 0.6% average error. Expert TapTypers report speeds of up to 25 WPM, which could be quite usable.

Details are a little scarce (it is a research project, after all) but the actual hardware seems simple enough, based around the Dialog DA14695 which is a nice Cortex M33 based Bluetooth Low Energy SoC. This is an interesting device in its own right, containing a “sensor node controller” block, that is capable of handling sensor devices connected to its interfaces, independant from the main CPU. The sensor device used is the Bosch BMA456 3-axis accelerometer, which is notable for its low power consumption of a mere 150 μA.

User’s can “type” on any convenient surface.

The wristband units themselves appear to be a combination of a main PCB hosting the BLE chip and supporting circuit, connected to a flex PCB with a pair of the accelerometer devices at each end. The assembly was then slipped into a flexible wristband, likely constructed from 3D printed TPU, but we’re just guessing really, as the progression from the first embedded platform to the wearable prototype is unclear.

What is clear is that the wristband itself is just a dumb data-streaming device, and all the clever processing is performed on the connected device. Training of the system (and subsequent selection of the most accurate classifier architecture) was performed by recording volunteers “typing” on an A3 sized keyboard image, with finger movements tracked with a motion tracking camera, whilst recording the acceleration data streams from both wrists. There are a few more details in the published paper for those interested in digging into this research a little deeper.

The eagle-eyed may remember something similar from last year, from the same team, which correlated bone-conduction sensing with VR type hand tracking to generate input events inside a VR environment.

Continue reading “TapType: AI-Assisted Hand Motion Tracking Using Only Accelerometers” →

Magpies Help Each Other Escape Tracking Devices With This One Weird Trick

April 5, 2022 by 18 Comments

Scientists who work with animals love to track their movements. This can provide interesting insights on everything from mating behaviour, food sources, and even the way animals behave socially – or anti-socially, as the case may be.

This is normally achieved with the use of tracking devices, affixed to an animal so that it can be observed remotely while going about its normal business. However, Australian scientists have recently run into some issues in this area, as the very animals they try to track have been removing these very devices, revealing some thought-provoking behaviour in the process.

Continue reading “Magpies Help Each Other Escape Tracking Devices With This One Weird Trick” →