FORK: fine grained occupancy estimatoR using kinect on ARM embedded platforms

Sirajum Munir, Le Tran, Jonathan Francis, Charles Shelton, Ripudaman Singh Arora, Craig Hesling, Matias Quintana, Anand Krishnan Prakash, Anthony Rowe, Mario Berges

Abstract: Occupancy estimation is very useful for a wide range of smart building applications including energy efficiency, safety, and security. In this demonstration, we present a novel solution called FORK, which uses a Kinect depth sensor for estimating occupancy in real-time. Unlike other camera-based solutions, FORK is much less privacy invasive (even if the sensor is compromised) and it does not require a powerful machine like a Microsoft XBOX or an Intel® Core™ i7 processor to process the depth data. Our system performs the entire depth data processing on a cheaper and lower-power ARM processor, in real-time. In order to do that, FORK uses a novel lightweight human model by leveraging anthropometric properties of human bodies for detecting individuals. We will show how FORK detects, tracks, and counts occupants accurately in real-time.