Today's inspirational paper provides a glimpse into another unique Kinect usage, using it for tracking objects and not just people...
Kinsight for Kinect tracks household items, finds the remote for you
Computer scientists at the University of Virginia have developed a way to track household items and help you find lost objects like your phone, keys, wallet, and the infamous remote. Shahriar Nirjon and John Stankovic worked together to create the system which uses two algorithms programmed with the Microsoft Kinect sensor to determine where objects are. The system works by tracking human movement and detecting items that are interacted with. Kinsight also has "context oriented object recognition," meaning that it can determine where objects are likely to be and can tell similarly-shaped objects apart. What about objects that get buried in the couch, left in a pocket, or buried underneath something else? The Kinsight can tell you the last place the object was seen to aid your search...
Project Information URL: http://www.theverge.com/2012/6/8/3073450/kinsight-kinect-tracks-household-items
Kinsight: Localizing and Tracking Household Objects using Depth-Camera Sensors
We solve the problem of localizing and tracking household objects using a depth-camera sensor network. We design and implement Kinsight that tracks household objects indirectly – by tracking human figures, and detecting and recognizing objects from human-object interactions. We devise two novel algorithms: (1) Depth Sweep – that uses depth information to efficiently extract objects from an image, and (2) Context Oriented Object Recognition – that uses location history and activity context along with an RGB image to recognize objects at home. We thoroughly evaluate Kinsight’s performance with a rich set of controlled experiments. We also deploy Kinsight in real-world scenarios and show that it achieves an average localization error of about 13 cm.
Project Information URL: http://www.cs.virginia.edu/~stankovic/psfiles/DCOSS2012.pdf