FORK

Mon, 24 Aug 2015 07:46:59 -0500

Fine grained Occupancy estimatoR using Kinect (FORK)

This project focused on developing a prototype system to explore the potential of using depth sensors to detect, estimate, identify, and track occupants in buildings. The FORK system uses a cheaper and lower power ARM processor for real-time processing, instead of using a high-power and high-cost computer, like an XBOX or an Intel Core i7 based machine. Unlike other camera based approaches, FORK is much less privacy invasive (even if the sensor is compromised) through its use of depth sensing and local processing.

My Contributions

Researched/sourced the embedded platform with USB 3.0 support and that was capable of real-time processing
Packaged the dependencies and environment needed for fast Debian deployment
Created the C++ XMPP Mortr.io interface for background data offloading
Created tools to remotely monitor and control multiple FORK nodes

Embedded Hardware

We settled on an ODROID XU4, which hosts a Samsung Exynos 5 Octa 5422 SoC. This Samsung SoC was the deciding factor in choosing the XU4 due its USB 3.0 support and its powerful Mali-T628 MP6 GPU.

Debian Packages

Enlighten

Sat, 14 Feb 2015 07:46:59 -0500

This project focused on sending data to a mobile device using the camera.

Through the use of an off the shelf smart bulb, we were able to send location specific bits of data to an iPhone.

Hardware

We have chosen the $80 LIFX multicolored LED smart bulb. It has two ARM Cortex-M3 processors onboard to handle WiFI and 802.15.4 radios. What makes this bulb more appropriate for the project, as compared to the “CREE Connected” or the “Connected by TCP” bulb, is the fact that the onboard LED driver circuit is directly connected to the MCU IO pin and is capable of being PWM controlled. This allows us to send data using nothing other than frequency modulated light. The CREE and TCP bubs use a continuous current LED driver circuit that cannot be used without hardware modifications.

Software

The iPhone app used the Apple® Cocoa™ Touch library and OpenCV.

other | Craig Hesling