DribbleUp’s ‘smart’ soccer ball helps you train with an app

We live in a time when even the most conventional things around us, like balls to play sports, are becoming smart in some way. Over the past few years, brands such as Adidas and Wilson have introduced sensor-laden balls designed to track performance data, including shot accuracy and trajectory. But those products have been far from perfect: they’re not always precise and, in the case of Adidas’ miCoach Smart Ball, having to charge it is a tedious process. Here’s where DribbleUp, a startup based out Brooklyn, hopes to shine with its new app-enabled soccer ball.

One of the most interesting parts about DribbleUp’s ball is that doesn’t have any sensors inside of it. Rather than pairing it to an iOS or Android device via Bluetooth, that step is done when you scan a QR code-like optical marker on the ball’s design with your smartphone or tablet’s camera. I was actually quite surprised by how efficiently this worked during our demo, as the setup only took about a second or two. Once you’ve done that, DribbleUp says its proprietary computer vision and machine learning takes care of tracking the ball in real-time and uses that information to grade your footwork.

I’ll admit that it can be a little odd to practice your skills in front of a screen, but the virtual trainer does a great job of not being obtrusive. All you see is the ball, your feet and, depending on the lesson, a set of digital cones and a speed bar that show how well (or not) you’re doing. The companion application gives you access to more than 100 drills, ranging from juggling tutorials to side taps, ball steps and alternating sole flicks challenges — moves you’d practice in a typical soccer training session. At the end of each workout, you’ll get graded based on your efficiency: “A+” means you’ve done exceptionally well, “F” would suggest you should probably find another sport to play.

There are also playlists within the app that provide daily lessons, featuring different drill combinations that you can filter based on your level of expertise or how old you are. DribbleUp says the system is designed for all types of players, from someone who plays recreationally to pros and even kids who are just getting into the sport. I can see this as a great tool for people to practice indoors, since the reflection of the iPhone and iPad displays we were using don’t really make for a pleasant experience outdoors — especially if the sun is out.

The good news is that since the ball doesn’t come with sensors built in, you don’t have to worry about charging it or depend on the app for it to be useful. As is the case with most high-end soccer balls, DribbleUp’s own is hand-stitched and made out of synthetic leather and water-resistant materials. It’s worth noting that this isn’t the first time DribbleUp has created a “smart” ball. It has an app-enabled basketball, too, which it claims is one of the best-selling on Amazon — we checked and it has a 4.5-star rating, so it seems like most buyers are happy with their purchase.

At $ 90, DribbleUp’s soccer ball is worth a look when it launches on November 1st, especially since most high-quality ones cost between $ 100 and $ 150. And you need to remember that none of those come with a virtual trainer. Yes, that may be a bit gimmicky (because who really wants to train in front of an iPhone or iPad), but at least you have the option to see if the AR-esque drills can help improve your skills. Worst case scenario, you take it out with you and treat is as you would any other dumb ball.

Engadget RSS Feed

Microsoft app helps blind people ‘see’ the world with AI

Microsoft has launched an iPhone app designed to help blind and partially-sighted people better navigate the world. The app, Seeing AI, uses ‘computer vision’ to narrate the user’s surroundings, read text, describe scenes and even identify friends’ facial cues.

The project has been in the works since September 2016; in March this year, Microsoft demonstrated a prototype of the app for the first time. It uses neural networks, similar to the technology found in self-driving cars, to identify its environment and speak its observations out loud.

Point your phone camera at a friend and it’ll tell you who they are. Aim it toward a short piece of text such as a name badge or room number and it’ll speak it instantly — a marked step up from the optical character recognition (OCR) technology of yore. Plus, it guides the user into capturing the object in question correctly, telling them to move the camera left or right to get the target in shot.

The app also recognizes currency, identifies products via their barcodes and, through an experimental feature, can describe entire scenes, such as a man walking a dog or food cooking on a stove. Basic tasks can be carried out directly within the app, without the need for an internet connection. It’s currently available to download for free in the US on iOS, but there’s no indication when it’ll come to other platforms or countries.

In a blog post by Harry Shum, executive vice president of Microsoft’s AI and research group, the company explains that Seeing AI is “just the beginning” for this kind of AI application. Machine learning, perception and natural language processing have evolved over time into separate fields of research, it says, but “we believe AI will be even more helpful when we can create tools that combine those functions.”

Source: Microsoft

Engadget RSS Feed