CLOSE
Original image

6 Remarkable Police Animals

Original image

We’ve seen bookstore cats, animals trained to sniff out bombs and heroic dogs, but now we're here to focus on animals who have served, or are currently serving, their local police departments.

1. Momo, Nara Police Department, Japan

http://www.youtube.com/watch?feature=player_embedded&v=YVn9UKutgAs

We’re used to seeing large police dogs because, let’s face it, a lap dog can’t take down a running fugitive. But there are a lot of other duties for police dogs out there—and a pup doesn't have to be big to sniff out bombs, drugs, or people buried under rubble. So why not have some small dogs work in these specialized areas?

The Japanese made news last year when they hired a tiny little Chihuahua as the Nara Police Department's newest police dog. Momo passed her search and rescue test with flying colors by finding a person within five minutes after smelling their hat. While the little pup might not be able to drag anyone from the rubble, officers do point out that her size provides her with a major advantage when it comes to squeezing into small openings that would be too narrow for most rescue dogs. Of course, in between earthquakes and fires, she’s still doing good community service by looking absolutely adorable.

2. Mattie, Connecticut State Police, United States

When it comes to arson investigations, dogs are better at sniffing out accelerants than most of the investigator’s instruments. But the idea of using dogs for that task is still pretty new; the first dog, a black lab named Mattie, was put to work in 1986. In order to graduate from Accelerant Detection Canine School, which is run by the ATF, she had to be able to identify 17 different types of accelerants in a fire’s aftermath, even when there were only a few drops of the compounds. (Dogs and their handlers can only pass if they have a perfect score in the final test.)

Mattie was placed in service with the Connecticut State Police that same year. While waiting for fires to be put out, she would be brought out to the scene, where she would sniff at any onlookers. In many cases, Mattie was able to identify suspects in the crowd who still had residue from the accelerants on them. Mattie worked with the state police for 11 years before retiring in 1997.

3. Lemon, Kyoto Police Department, Japan

If you think a Chihuahua is a bad police dog, then just imagine having a police cat. To be fair, Officer Lemon operates in a small town in Kyoto Prefecture, Japan, which has a population made up of mostly elderly folks, and his only cases involve suspicious phone calls. Lemon doesn't help track down the prank callers, but he does help relax the victims—an important job for police handling these kinds of situations.

Lemon has been with the police since he was two weeks old. Of course, that’s probably why he’s so comfortable in his adorable little uniform; most cats that grew up without clothing probably wouldn’t be so willing to wear the tiny jacket and hat that Lemon sports while on duty.

4. Santisuk, Saiburi Police Department, Thailand

This officer might monkey around a bit, but you’d still better take him seriously—no matter how cute he looks in his little police shirt. Santisuk, a pig-tailed macaque, was adopted by a police officer after he was found with a broken arm. They soon started training him to pick up coconuts and then they realized that he might just help alleviate tensions at police checkpoints.

Their plan worked. When Santisuk stands duty at the checkpoints, motorists happily stop their vehicles and many even pull over to take their picture with the monkey. He has changed the public image of the police force so much that many other police precincts in the area are considering adding their own monkeys to the force.

5 & 6. Echo, Metropolitan Police Department, and Sefton, Household Cavalry, United Kingdom

Echo and Sefton are probably the best remembered police horses, and it’s for a rather sad reason.

The horses were survivors of the July 20, 1982 bombing of Hyde Park. A car bomb—made from 25 pounds of explosives surrounded in 4- and 6-inch nails—killed four soldiers and seven other horses. Echo, part of the Metropolitan Police Department, was left was a piece of shrapnel in his side. Household Cavalry horse Sefton had 38 shrapnel wounds, and his jugular vein was severed. Another Cavalry horse, Yeti, also survived the blast. After the incident, Echo, too nervous to go back to the police department, was retired from duty. Sefton did go back to work for a bit, but eventually, all three horses were retired at the same stable, where they would live for the rest of their lives. When the horses made public appearances, people were touched—Echo and Sefton even received a standing ovation when they appeared at the Horse of the Year show.

Original image
iStock // Ekaterina Minaeva
technology
arrow
Man Buys Two Metric Tons of LEGO Bricks; Sorts Them Via Machine Learning
May 21, 2017
Original image
iStock // Ekaterina Minaeva

Jacques Mattheij made a small, but awesome, mistake. He went on eBay one evening and bid on a bunch of bulk LEGO brick auctions, then went to sleep. Upon waking, he discovered that he was the high bidder on many, and was now the proud owner of two tons of LEGO bricks. (This is about 4400 pounds.) He wrote, "[L]esson 1: if you win almost all bids you are bidding too high."

Mattheij had noticed that bulk, unsorted bricks sell for something like €10/kilogram, whereas sets are roughly €40/kg and rare parts go for up to €100/kg. Much of the value of the bricks is in their sorting. If he could reduce the entropy of these bins of unsorted bricks, he could make a tidy profit. While many people do this work by hand, the problem is enormous—just the kind of challenge for a computer. Mattheij writes:

There are 38000+ shapes and there are 100+ possible shades of color (you can roughly tell how old someone is by asking them what lego colors they remember from their youth).

In the following months, Mattheij built a proof-of-concept sorting system using, of course, LEGO. He broke the problem down into a series of sub-problems (including "feeding LEGO reliably from a hopper is surprisingly hard," one of those facts of nature that will stymie even the best system design). After tinkering with the prototype at length, he expanded the system to a surprisingly complex system of conveyer belts (powered by a home treadmill), various pieces of cabinetry, and "copious quantities of crazy glue."

Here's a video showing the current system running at low speed:

The key part of the system was running the bricks past a camera paired with a computer running a neural net-based image classifier. That allows the computer (when sufficiently trained on brick images) to recognize bricks and thus categorize them by color, shape, or other parameters. Remember that as bricks pass by, they can be in any orientation, can be dirty, can even be stuck to other pieces. So having a flexible software system is key to recognizing—in a fraction of a second—what a given brick is, in order to sort it out. When a match is found, a jet of compressed air pops the piece off the conveyer belt and into a waiting bin.

After much experimentation, Mattheij rewrote the software (several times in fact) to accomplish a variety of basic tasks. At its core, the system takes images from a webcam and feeds them to a neural network to do the classification. Of course, the neural net needs to be "trained" by showing it lots of images, and telling it what those images represent. Mattheij's breakthrough was allowing the machine to effectively train itself, with guidance: Running pieces through allows the system to take its own photos, make a guess, and build on that guess. As long as Mattheij corrects the incorrect guesses, he ends up with a decent (and self-reinforcing) corpus of training data. As the machine continues running, it can rack up more training, allowing it to recognize a broad variety of pieces on the fly.

Here's another video, focusing on how the pieces move on conveyer belts (running at slow speed so puny humans can follow). You can also see the air jets in action:

In an email interview, Mattheij told Mental Floss that the system currently sorts LEGO bricks into more than 50 categories. It can also be run in a color-sorting mode to bin the parts across 12 color groups. (Thus at present you'd likely do a two-pass sort on the bricks: once for shape, then a separate pass for color.) He continues to refine the system, with a focus on making its recognition abilities faster. At some point down the line, he plans to make the software portion open source. You're on your own as far as building conveyer belts, bins, and so forth.

Check out Mattheij's writeup in two parts for more information. It starts with an overview of the story, followed up with a deep dive on the software. He's also tweeting about the project (among other things). And if you look around a bit, you'll find bulk LEGO brick auctions online—it's definitely a thing!

Original image
quiz
arrow
Name the Author Based on the Character
May 23, 2017
Original image
SECTIONS
BIG QUESTIONS
BIG QUESTIONS
WEATHER WATCH
BE THE CHANGE
JOB SECRETS
QUIZZES
WORLD WAR 1
SMART SHOPPING
STONES, BONES, & WRECKS
#TBT
THE PRESIDENTS
WORDS
RETROBITUARIES