The Weird Week in Review

Tuba Thefts Linked to Banda Music

A rash of tuba thefts may be attributed to the popularity of a genre of music called banda. High schools all over Southern California report thefts of Sousaphones and concert tubas, which may be sold on the black market to banda musicians. Mexican banda music has been growing in popularity over the past twenty years, and the tuba is the most important instrument for the distinctive sound. Banda bandits are suspected because other instruments that are easier to carry off and sell for scrap have been left behind in the break-ins.

Courthouse Evacuated Over Coconut

A deputy at the Frederick County Courthouse in Maryland spotted a coconut on Wednesday morning. The coconut was placed on one of the building's columns, and appeared to have been split open and pieced back together. The courthouse was evacuated and the Maryland State Fire Marshal's Bomb Squad responded. Upon examination, they determined that the coconut was no threat. The investigation continues.

738-pound Tuna

Nathan Adams caught a pretty big fish, considering he was only using a rod and reel and fishing from a 20-foot boat. Adams landed a Pacific bluefin tuna that weighed in at 738 pounds! Bigger tuna have been caught, but the New Zealand fisherman may have set a world record for a rod and reel. Tuna that size can sell for hundreds of thousands of dollars at a fish market, but Adams cannot sell the tuna for meat, as New Zealand law bans selling fish caught from a registered recreational vessel. He is considering having the fish mounted, which means Adams cannot eat the tuna himself, either.

Giant Chicken Stolen

A 10-foot-tall chicken was stolen last week from a poultry farm in Windham Township, Ontario. The fiberglass rooster had been guarding the farm since it was imported from Texas in 2004. Thieves broke the $3,000 chicken and made off with it, leaving its feet behind. An anonymous caller reported the bird's whereabouts, and police found it in a backyard in Milton. The homeowner, 36-year-old Brent Smith, was arrested for fowl play possession of stolen property. The farmers, Sonia and Frank Dierick, are hoping that an auto body shop may be able to reattach the big bird to its feet.

Terrifying Tom Turkey

Edna Geisler of Commerce Township, Michigan, is afraid to leave her home, because she is being stalked by a turkey. The 69-year-old woman calls the big tom "Godzilla." The bird stakes out her front lawn from sunup to sundown, and attacks if she tries to cross the yard. It has bumped her and even clawed her once. A wildlife expert says the behavior is unusual, but it appears the gobbler is defending its territory. Geisler just hopes Godzilla leaves before gardening season begins.

Town Covered in Spider Webs

Townspeople in Wagga Wagga, NSW, Australia, were evacuated during recent floods. When they returned, the fields surrounding the town were covered with a blanket of spider webs! Experts explained that the local wolf spiders threw out webs hoping to escape the danger of flooding, a process called "ballooning." The water made the webs more visible to the human eye. The water also makes the webs stickier, which means they trap more insects. The many webs are actually advantageous to people, as they help capture mosquitoes, which normally thrive during floods.

Steven Seagal Sued over Raid

The expected response to a story we posted here a year ago has come about. Last March, actor Steven Seagal assisted the Maricopa County (Arizona) Sheriff's office in a raid over suspected cockfighting. They showed up with an armored vehicle and a SWAT team and busted through a wall at the home of Jesus Llovera. The raid, during which Llovera's dog was shot, was filmed for the TV show Steven Seagal: Lawman. Llovera initiated a lawsuit this week against Seagal and the sheriff. The recorded raid was for an episode that was supposed to be aired in January, but the show was pulled from the A&E network lineup.

Original image
iStock // Ekaterina Minaeva
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
Name the Author Based on the Character
May 23, 2017
Original image