Machine Learning Does Its Civic Duty By Spotting Roadside Litter

If there’s one thing that never seems to suffer from supply chain problems, it’s litter. It’s everywhere, easy to spot and — you’d think — pick up. Sadly, most of us seem to treat litter as somebody else’s problem, but with something like this machine vision litter mapper, you can at least be part of the solution.

For the civic-minded [Nathaniel Felleke], the litter problem in his native San Diego was getting to be too much. He reasoned that a map of where the trash is located could help municipal crews with cleanup, so he set about building a system to search for trash automatically. Using Edge Impulse and a collection of roadside images captured from a variety of sources, he built a model for recognizing trash. To find the garbage, a webcam with a car window mount captures images while driving, and a Raspberry Pi 4 runs the model and looks for garbage. When roadside litter is found, the Pi uses a Blues Wireless Notecard to send the GPS location of the rubbish to a cloud database via its cellular modem.

Cruising around the streets of San Diego, [Nathaniel]’s system builds up a database of garbage hotspots. From there, it’s pretty straightforward to pull the data and overlay it on Google Maps to create a heatmap of where the garbage lies. The video below shows his system in action.

Yes, driving around a personal vehicle specifically to spot litter is just adding more waste to the mix, but you’d imagine putting something like this on municipal vehicles that are already driving around cities anyway. Either way, we picked up some neat tips, especially those wireless IoT cards. We’ve seen them used before, but [Nathaniel]’s project gives us a path forward on some ideas we’ve had kicking around for a while.

Continue reading “Machine Learning Does Its Civic Duty By Spotting Roadside Litter”

Prepare For Wildfire Season With An Air Quality Monitor

For some reason, wildfire seasons in Australia, North America, and other places around the world seem to happen more and more frequently and with greater and greater fervor. Living in these areas requires special precautions, even for those who live far away from the fires. If you’re not sure if the wildfires are impacting your area or not, one of the tools you can build on your own is an air quality meter like [Costas Vav] shows us in this latest build.

The air quality indicator is based around an Adafruit Feather RP2040 which is in turn based on the 32-bit Cortex M0+ dual core processor. This makes for a quite capable processor in a small package, and helps accomplish one of the design goals of a rapid startup time. Another design goal was to use off-the-shelf components so that anyone could easily build one for themselves, so while the Feather is easily obtained the PMS5003 PM2.5 air quality sensor needed to be as well. From there, all of the components are wrapped up in an easily-printed enclosure and given a small (and also readily-available) OLED screen.

[Costas Vav] has made all of the files needed to build one of these available, from the bill of materials to the software running on the Pi-compatible board to the case designs. It’s a valuable piece of technology to have around even if you don’t live in fire-prone areas. Not only can wildfire smoke travel across entire continents but simple household activities such as cooking (especially with natural gas or propane) can decimate indoor air quality. You can see that for yourself with an army of ESP32-based air quality sensors.

Ooohhh, That Smell: Arduino Monitors Air Quality

According to [Dr. Tom Lehrer’s] song Pollution, “Wear a gas mask and a veil. Then you can breathe, long as you don’t inhale!” While the air quality in most of the world hasn’t gotten that bad, there is a lot of concern about long-term exposure to particulates in the air causing health problems. [Ashish Choudhary] married an Arduino with a display and a pollution sensor to give readings of the PM2.5 and PM10 levels in the air.

The sensor uses a laser diode and a photodiode to detect and count particles, while a fan moves air through the system. If you aren’t up on pollution metrics, PM2.5 is a count of very fine particles (under 2.5 microns) and PM10 is a count of particles for 10 microns. You can find a datasheet for the device online.

Continue reading “Ooohhh, That Smell: Arduino Monitors Air Quality”

Untethered: Fishing Without Lines

There’s a laundry list of ways that humans are polluting the earth, and even though it might not look like it from the surface, the oceans seem to bear the brunt of our waste. Some research suggests that plastic doesn’t fully degrade as it ages, but instead breaks down into smaller and smaller bits that will be somewhere the in environment for such a long time it could be characterized in layman’s terms as forever.

Not only does waste of all kinds make its way to the oceans by rivers or simply by outright dumping, but commercial fishing gear is estimated to comprise around 10% of the waste in the great blue seas, and one of the four nonprofits help guide this year’s Hackaday Prize is looking to eliminate some of that waste and ensure it doesn’t cause other problems for marine life. This was the challenge for the Conservation X Labs dream team, three people who were each awarded a $6,000 micro-grant to work full time for two months on the problem.

It isn’t about simply collecting waste in the ocean, but rather about limiting the time that potentially harmful but necessary fishing equipment is in the water in the first place. For this two-month challenge, this team focused on long lines used by professional fishing operations to attach buoys to gear like lobster pots or crab traps. These ropes are a danger to large ocean animals such as whales when they get tangled in them and, if the lines detach from the traps, the traps themselves continue to trap and kill marine life for as long as they are lost underwater. This “ghost gear” is harmful in many different ways, and reducing its time in the water or “soak time” was the goal for the project.

Let’s take a closer look at their work after the break, and we can also see the video report they filed as the project wrapped up.

Continue reading “Untethered: Fishing Without Lines”

Road Pollution Doesn’t Just Come From Exhaust

Alumni from Innovation Design Engineering at Imperial College London and the Royal College of Art want to raise awareness of a road pollution source we rarely consider: tire wear. If you think about it, it is obvious. Our tires wear out, and that has to go somewhere, but what surprises us is how fast it happens. Single-use plastic is the most significant source of oceanic pollution, but tire microplastics are next on the naughty list. The team calls themselves The Tyre Collective, and they’re working on a device to collect tire particles at the source.

Continue reading “Road Pollution Doesn’t Just Come From Exhaust”

UnifiedWater Finds Potable Water And Stops Polluters

Millions of people all over the world don’t have access to clean drinking water, and it’s largely because of pollution by corporations and individuals. Solving this problem requires an affordable, scalable way to quickly judge water quality, package the data, and present it to an authority that can crack down on the polluters before the evidence dissipates. Ideally, the solution would be open source and easy to replicate. The more citizen scientists, the better.

[Andrei Florian]’s UnifiedWater flows directly from this line of thinking. Dip this small handheld device below the surface, and it quickly takes a bunch of water quality and atmospheric readings, averages them, and sends the data to a web dashboard using an Arduino MKR GSM.

UnifiedWater judges quality by testing the pH and the turbidity of the water, which gauges the amount of impurities. Commercial turbidity sensors work by measuring the amount of light scattered by the solids present in a liquid, so [Andrei] made a DIY version with an LED pointed at a photocell. UnifiedWater also reads the air temperature and humidity, and reports its location along with a timestamp.

This device can run in one of two modes, depending on the application. The enterprise mode is designed for a fleet of devices placed strategically about a body of water. In this mode, the devices sample continuously, taking readings every 15 minutes, and can send notifications that trigger on predefined thresholds. There’s also a one-and-done individual mode for hikers and campers who need to find potable water. Once UnifiedWater takes the readings, the NeoPixel ring provides instant color-coded judgment. Check out the demo after the break.

Continue reading “UnifiedWater Finds Potable Water And Stops Polluters”

Hackaday Links Column Banner

Hackaday Links: May 17, 2020

Consider it the “Scarlet Letter” of our time. An MIT lab is developing a face mask that lights up to alert others when the wearer has COVID-19. The detection technology is based on sensors that were developed for the Ebola virus scare and uses fluorescently tagged DNA fragments freeze-dried onto absorbent strips built into the mask. The chemistry is activated by the moisture in the sputum expelled when the wearer coughs or sneezes while wearing the mask; any SARS-CoV-2 virus particles in the sputum bind to the strips, when then light up under UV. The list of problems a scheme like this entails is long and varied, not least of which is what would possess someone to willingly don one of these things. Still, it’s an interesting technology.

Speaking of intrusive expansions of the surveillance state, Singapore is apparently now using a Boston Dynamics Spot robot to enforce social-distancing rules in its public parks and gardens. The familiar four-legged, bright yellow dog-bot is carrying cameras that are relaying images of park attendees to some sort of image analysis program and are totally not capturing facial or personal data, pinky swear. If people are found to be violating the two-meter rule, Spot will bark out a prerecorded reminder to spread out a bit. How the system differentiates between people who live together who are out getting some fresh air and strangers who should be staying apart, and whether the operators of this have ever seen how this story turns out are open questions.

Those who lived through 9/11 in the United States no doubt remember the deafening silence that descended over the country for three days while every plane in the civil aviation fleet was grounded. One had no idea how much planes contributed to the noise floor of life until they were silenced. So too with the lockdown implemented worldwide to deal with the COVID-19 pandemic, except with the sometimes dramatic reduction in pollution levels. We’ve all seen pictures where people suddenly realize that Los Angeles isn’t necessarily covered by an orange cloud of smog, and that certain mountain ranges are actually visible if you care to look. But getting some hard data is always useful, and these charts show just how much the pollution situation improved in a number of countries throughout the world after their respective lockdowns. For some cities, the official lockdown was a clear demarcation between the old pollution regime and the new, but for some, there was an obvious period before the lockdown was announced where people were obviously curtailing their activity. It’s always interesting pore over data like this and speculated what it all means.

While the in-person aspects of almost every conference under the sun have been canceled, many of them have switched to a virtual meeting that can at least partially make up for the full experience. And coming up next weekend is Virtually Maker Faire, in the slot where Bay Area Maker Faire would normally be offered. The call for makers ends today, so get your proposals in and sign up to attend.

And finally, there aren’t too many times in life you’ll get a chance to get to visualize a number so large that an Evil Empire was named for it. The googol, or 10100, was a term coined by the nine-year-old nephew of mathematician Edward Kasner when he asked the child for a good name for a really big number. To put the immensity of that number into perspective, The Brick Experiment Channel on YouTube put together an improbably long gear train using Lego pieces we’ve never seen before with a reduction ratio of 10103.4:1. The gear train has a ton of different power transmission elements in it, from plain spur gears to worm drives and even planetary gears. We found the 2608.5:1 harmonic gear particularly fascinating. There’s enough going on to keep even a serious gearhead entertained, but perhaps not for the 5.2×1091 years it’ll take to revolve the final gear once. Something, something, heat-death of the universe. [Ed note: prior art, which we were oddly enough thinking of fondly just a few days ago. Synchronicity!]