The End of Psychology: Diagnosing Depression With Kinect
Computer scientists at the University of Southern California have used Microsoft’s Kinect sensor to detect, with 90% accuracy, whether you are depressed. All you have to do is sit down in front of Kinect, answer some questions from an on-screen virtual psychologist, and the clever software does the rest. The process is entirely automated, objective, and self-contained, meaning accurate testing could be carried out in complete privacy at home.
The software, called SimSensei and developed by Stefan Scherer and colleagues, is essentially a clever mix of computer vision algorithms and the psychological model of depression. The on-screen psychologist asks you leading questions — a lot like the old-school Eliza, or Alice — and then watches how you physically respond. Using Kinect, the computer vision algorithms build up a very detailed model of your face and body, including your “smile level,” horizontal gaze and vertical gaze, how wide open your eyes are, and whether you are leaning toward or away from the camera. From these markers, SimSensei can work out whether you’re exhibiting signs that indicate depression — gaze aversion, smiling less, and fidgeting. Watch the video below and be amazed.
(via Kinect-based system diagnoses depression with 90% accuracy | ExtremeTech)
Microsoft Patents Method To Count People In a Room Using Kinect, Charge Per Viewer for Content
A U.S. Patent and Trademark Office filing by Microsoft reveals that the company is devising a means for your Xbox peripheral to count the number of people in the room and even identify who they are in order to assess licensing fees for content based on the number of people in the room.
“In Soviet Union, TV Watches You”
Robots That Learn Through Demonstration Instead of Programming
Neil Dantam at the Georgia Institute of Technology in Atlanta and colleagues are developing a system in which robots learn by example. Instead of programming a robot to carry out a task, a demonstration could suffice.
However, the robot does not simply mimic the human’s actions. The prototype system uses an Xbox Kinect camera to observe the human performing an activity, then breaks that activity into a sequence of key actions necessary to carry out the task.
These actions are converted into a general set of instructions – much like those found in an IKEA furniture instruction manual – that can be interpreted even by non-humanoid robots. “You want to somehow capture the important aspects of the human’s motion and transfer that to the robot,” says Dantam. “Think about how you’d tell someone how to make a cake,” he says. The way people follow those steps may vary. “An adult might bend down over the counter to work while a child may stand on tiptoes.”
(via Robot learns using IKEA-style instructions - tech - 10 October 2012 - New Scientist)
Putting a Kinect in Every Room to Help You Remember Where You Put Stuff…
What could possibly go wrong?
“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. By following the location of objects over time, Kinsight can even distinguish between two identical-looking things - if it records a mug that seems to have jumped from the living room to the kitchen without passing through the space between, for example, it knows it is likely to be two mugs. The system can locate fist-sized objects with an accuracy of 13 centimetres.
(via Kinect system keeps track of household objects - tech - 07 June 2012 - New Scientist)
Surgeons Using Kinect to Review Diagnostic Imaging in Real-Time in the OR
On Tuesday last week, a surgeon at Guy’s and St Thomas’ hospital in London began trials of a new device that uses an Xbox Kinect camera to sense body position. Just by waving his arms the surgeon can consult and sift through medical images, such as CT scans or real-time X-rays, while in the middle of an operation.
Maintaining a sterile environment in the operating room is paramount, but scrubbing in and out to scroll through scan images mid-operation can be time-consuming and break a surgeon’s concentration or sense of flow. Depending on the type of surgery, a surgeon will stop and consult medical images anywhere from once an hour to every few minutes.
To avoid leaving the table, many surgeons rely on assistants to manipulate the computer for them, a distracting and sometimes frustrating process.
“Up until now, I’d been calling out across the room to one of our technical assistants, asking them to manipulate the image, rotate one way, rotate the other, pan up, pan down, zoom in, zoom out,” says Tom Carrell, a consultant vascular surgeon at Guy’s and St Thomas’, who led the operation on 8 May to repair an aneurism in a patient’s aorta. With the Kinect, he says, “I had very intuitive control”.
(via Kinect imaging lets surgeons keep their focus - tech - 17 May 2012 - New Scientist)
Canadian Researchers Use Off-The-Shelf Components to Create 3D Holographic Telepresence System:
A long tube is outfitted with six Microsoft Xbox Kinect sensors, a convex mirror and a 3D projector… [The user’s] image is beamed to another translucent cylindrical pod with a 3D projector.
TeleHuman makes it so people can walk fully around the 3D image when talking. This technology allows full interaction between people in different places. They can talk and interact as if face-to-face. The team says it’s the closest thing to zapping into thin air and traversing space.
The image created by the TeleHuman is not your average hologram. The Human Media Lab team takes it to the next level by incorporating more control and “human-scale” interaction. Natural face-to-face “gaze and eye contact” are preserved in the process. Other natural components of conversation researchers kept intact include the 360-degree motion of the bodies, fluid movement and the realistic image size.
(via Life-Size 3D Holograms Bring Us Closer to ‘Teleportation’ [VIDEO])
Microsoft Research - Semantic Map Vision
SemanticMap, The Next Step In Public Information and Navigation On The Go is is a Digital signage prototype featuring proximity detection, face recognition and gesture interaction technologies developed in Microsoft Research Asia. The system provides the right amount and detail of map-related information according to the user’s distance from the display.
Semantic Map Prototype
As people glance at such displays from afar, they see the most significant information in large, bold type. As they approach the display for more information, we dynamically decrease type sizes and increase the detail level of both map layouts and their information overlays. These overlays are dynamic, updating in real-time according to the schedule of events and notices, as well as potentially personalized, connecting to the person’s calendar of meetings and appointments. Overall, the goal of Semantic Map is to help people find their way around both physical and information spaces, by exploiting natural information-seeking behaviors and body movements.
(via futurescope)
