|English: The Microsoft Kinect peripheral for the Xbox 360. (Photo credit: Wikipedia)|
I could really use this! You don't know how much time I spend running around looking for my wallet, keys, or TV remote! Sometimes I think that I am a bit like Poindexter, the mad scientist.
This problem is especially true for folks with ADHD. Blogger Christine Brady writes, "When I wake up in the morning, I'm aware of the fact that I will misplace at least one thing that day. I just pray that I will find it again. I am, in a sense, notoriously good at losing and finding things I've lost. I always lose something, find it, lose it again, and, if I'm lucky, find it again before I have a chance to lose it one more time — or fall asleep, whichever comes first."
I am not this bad. But I do have some days like this. Less since we got the organizer to come in.
FITTING your house with a network of Kinect sensors could mean never losing your wallet, TV remote or other small items again.
"We want to make Google for your home," says Shahriar Nirjon, a computer scientist at the University of Virginia in Charlottesville. To do this, Nirjon and colleague John Stankovic developed Kinsight, which records the location of household items using a Kinect depth camera in each room. It works by tracking people and detecting the size and shape of any objects they interact with. Each object is compared to Kinsight's database for the house and either recognised or added to the list.
For a Deep Sweep search, Kinsight will basically look at where you last interacted with the object and use the Kinect's depth perception to find the item--pretty useful if your phone is down the side of the couch. Meanwhile, Context-Oriented Object Recognition can tell different objects apart from one another and look for where you are likely to leave them, or even where you left them in the past--good if that pesky keyring keeps falling out of your pocket when you sit down.
Of course, for both of these methods to work, you will need to add the objects into the Kinsight's repository so it knows what to search for. The mod is also far from complete: For instance, if an object is a certain distance away from the sensors, Kinsight might not be able to locate it, which could be annoying if you are searching a big room. The same problem will arise if an object is too small for Kinsight to identify, or if it's transparent. Interestingly, items that were too close together--for example, a bunch of keys, with each key scanned in individually--also gave Kinsight some difficulty.