Facebook fact checkers will soon review Instagram posts

Posted on 06/05/2019 by Engadget RSS Feed

Fake news, conspiracy theories and misinformation aren't just problems for Facebook, YouTube and Twitter. They're also rampant on Instagram. While Instagram has been working to reduce the reach of false posts, starting this week, it will go a step fu...

Edges2cats Turns Doodles Into Creepy Cat Photos

Posted on 22/02/2017 by Shane McGlaun

A new bit of software has turned up that is both cool and a bit creepy. The software is called pix2pix and it can take a source sketch or image and then build a rough photographic representation of it. The Edges to Photo capability lets you draw a doodle of an object and then turns those doodles into pictures using images cobbled together from photographs of similar objects. One specific variant of the tool is called edges2cats, and it transforms your cute kitty doodles into some really disturbing critters.

After you submit your doodle, the resulting photo is a composite using parts from cat pictures presumably found online. Originally you had to download the software and write your own front-end code for it, but now you can play with it for yourself online over at affinelayer.com, thanks to Christopher Hesse.

Sure, the photos are downright weird, but it’s still fun to see your drawings become… well… slightly more realistic cats. There are also online tools for doodling shoes and handbags, which seems ever stranger to me.

[via Kotaku]

Artificial intelligence could be used to stop car smugglers

Posted on 28/06/2016 by Engadget RSS Feed

Chances are, you don't spend a lot of time thinking about the logistics of international shipping -- but you shouldn't be surprised that transportation hubs are ripe for export fraud. Part of the reason for this is that there's simply too much intern...

DIY Color-sensing Nerf Turret Sees Red, Green, Blue…

Posted on 31/01/2016 by Lambert Varias

A couple of years ago, we featured the Pixy, a compact image sensor that can tag hundreds of objects based on their color. Electronics company RobotGeek combined Pixy with a couple of its robot kits to create a small turret that automatically follows and shoots at its targets.

The turret is a combination of the Pixy and the RobotGeek Desktop Robo Turret with the Foam Dart Gun (i.e. Nerf pistol) attachment. You’ll need to connect the Pixy to the turret’s Geekduino microcontroller via RobotGeek’s Sensor Shield. You can teach it to track certain colors using RobotGeek’s Arduino sketch. It will automatically follow objects that bear the target colors and shoot them if they stay still for a few seconds.

Head to RobotGeek’s Instructables page for the full guide. It’s an expensive toy, but at least you can expand its capabilities and use its parts for other projects.

[via Gadgetify]

Fleye Drone Hides Moving Parts in its Shell: UAV Protection

Posted on 06/12/2015 by Lambert Varias

Even though consumer UAVs are becoming smarter and easier to use, they can still cause physical harm. Just last month a baby lost one of his eyes because he was accidentally hit by a quadcopter’s propeller. That’s why Fleye is working on a drone that hides its propeller and other moving parts in a spherical shell.

Fleye’s sensors help it to remain stable when it bumps into something or someone so you can safely touch or push it. Fleye has three autonomous modes – selfie, panorama, and hover – but you can also control it manually using a mobile app.

But Fleye isn’t just about safety or ease of use. It runs on the Linux-based Yocto and supports OpenCV so you can make programs for it that depend on computer vision. It will also have a remote API as well as SDKs for iOS, Android, Node.js, and Python. Finally, the company is offering a Fleye Developer Edition that has twice the CPU cores and RAM of the consumer edition.

Pledge at least ~$740 (USD) on Kickstarter to receive a Fleye unit as a reward.

Blippar Brings AR Advertising and Image Recognition to Google Glass

Posted on 26/02/2014 by Alexandru Chiuariu

Wearables were meant from the beginning to offer the means for new ways of advertising and new search methods. Blippar’s implementation of AR advertising and image recognition into Google Glass is firm proof of that.

Ambarish Mitra, the CEO of Blippar, showcased at MWC in Barcelona the app that makes all of this possible. Certainly, the idea of augmented reality advertising isn’t new, as numerous companies have already played with this technology, Cadburry and IKEA being only two examples.

Mitra explained that “Glass today can be likened to what mobile phones were in early nineties. We at Blippar anticipate that if Glass reaches a couple million users in its first year of launch, it will be a good business opportunity for us to develop in the space. We are investing in the potential of Glass.” I have to admit that the CEO of this company is right. Smart glasses are still a new thing, and people are currently only scratching the surface in terms of the applications that these wearables could have.

Blippar wouldn’t mind at all if the user base of Google Glass went beyond one million, especially since its app is used by five million people worldwide. In terms of brands and publishers, Blippar offers its AR advertising service to 750 companies, a number that will certainly grow in the future.

Besides Android, which is obviously the operating system Google Glass comes with, Blippar also works with smartphones running iOS, Blackberry OS or Windows Phone. Assuming that these operating systems showed up one day in a pair of smart glasses, it wouldn’t be difficult for Blippar to port their app to the wearables.

The demonstration that Mitra conducted at MWC also included the recognition of images, products, and even human faces. The last aspect is a bit scary, especially since Google claimed that it won’t implement face recognition into its smart glasses.

While Google Images is able to recognize pictures and can even decipher some product logos, the face recognition and AR advertising technologies that Blippar brings to the table are definitely innovative, especially in the context of smart glasses. In time, tech companies will hopefully come with even more diverse applications for wearables. I’m confident about this, as smart watches and smart glasses are only the beginning of the adventure.

Be social! Follow Walyou on Facebook and Twitter, and read more related stories about the Häagen-Dazs AR Concerto Timer and Microsoft IllumiRoom.

A Fish Drives a Car

Posted on 11/02/2014 by Lambert Varias

A while back we featured a robot vehicle that was made to be driven by a parrot. This one’s meant for fishes. Image recognition specialist Studio diip made Fish on Wheels to showcase its prowess in its field. The vehicle moves by following the movement of the fish inside the tank.

A webcam positioned above the tank feeds video to a Beagleboard, which analyzes the position of the fish by contrasting the animal’s body with the bottom of the tank. The instructions are then sent to the vehicle itself, which is powered by an Arduino.

This summer, watch as Nemo is awakened from cryogenic sleep in 2099 to search for the remains of Wall-E under the ocean and use it to beat the tyrannical ruler Lightning McQueen in Finding Nemo 2: Cars 2: Wall-E 2: Judgment Day.

[via Studio diip via prosthetic knowledge]

Pixy Open Source Camera Recognizes Objects by Color: Smart Sight

Posted on 27/08/2013 by Lambert Varias

Computers and sensors are quickly decreasing in cost and size, making it easier than ever before to build smart gadgets or robots. From accelerometers to thermal sensors, electronics nowadays can detect and record a variety of events and objects in their surroundings. Here’s one more sensor to add to your robot overlord-in-training. It’s called Pixy, a camera that identifies objects through color.

pixy camera vision sensor by charmed labs and cmu

Pixy was made by Charmed Labs and embedded systems experts from Carnegie Mellon University. It’s actually the team’s fifth version of a smart and low-cost vision sensor, which they previously called the CMUcam. What separates the Pixy from other image sensors is that it only sends a small amount of data and it has its own microprocessor. These traits make it possible to integrate the Pixy even to microcontrollers like the Arduino.

pixy camera vision sensor by charmed labs and cmu 2

Pixy identifies objects using “a hue-based color filtering algorithm”, which supposedly makes it consistent under different lighting conditions. It can also identify hundreds of objects at once. The image below is a screenshot of PixyMon, an open source debugging program for Pixy.

pixy camera vision sensor by charmed labs and cmu 3

As you’ll see in the video below, Pixy can also track moving objects. That’s because it updates once every 20ms, fast enough to keep up with an object moving at 30mph. You can then gather Pixy’s data through UART serial, SPI, I2C, digital out, or analog out.

Pixy can be taught to “remember” up to seven different objects, but you can expand its memory by using color codes. Color codes are simply stickers or strips of paper with two or more different colors. Color codes increase Pixy’s color-coded encyclopedia from seven to several thousands.

pixy camera vision sensor by charmed labs and cmu 4

Pledge at least $59 (USD) on Kickstarter to get a Pixy and an Arduino cable as a reward.

What will you build with Pixy? A security camera that texts you when your cat goes out? A color-seeking water bomb? A clown-loving machine? A drone that follows you around? A box of crayons that can tell you what color you picked? A weapon that works only on people wearing red? A LEGO sorter that can tell you which pieces are missing from your collection? A camera that automatically takes pictures of the sunset? A wearable assistant for colorblind people? A ticker that counts which Premier League referee hands out the most yellow cards? A useless machine that won’t turn itself off if you’re wearing the right color? Are the things I’m saying even possible?

Googlerola buys Viewdle, ups Android’s augmented reality and face recognition game

Posted on 04/10/2012 by Michael Gorman

From existing tech like Face Unlock and Google Goggles to patent filings and Project Glass, it's clear that Google sees augmented reality and image recognition playing a big part in our computing future. It makes sense, then, that Big G subsidiary Motorola has bought Viewdle -- a Silicon Valley company that builds face, object, and gesture recognition technology for mobile devices. We don't know how much MMI paid for Viewdle, but we do know, thanks to a statement obtained by the good folks at TechCrunch, that the two firms "have been collaborating for some time." So, hopefully Android will reap the benefits (and fix those Face Unlock flaws) in the not-so-distant future.

Filed under: Cellphones, Mobile

Googlerola buys Viewdle, ups Android's augmented reality and face recognition game originally appeared on Engadget on Wed, 03 Oct 2012 21:17:00 EDT. Please see our terms for use of feeds.

Permalink | source