Conferences and supporting programme
Embedded Algorithms for Motion Detection and Processing
MEMS inertial modules are powerful and versatile converge technology: mechanical and electronic functions are merged into a single component, ready to offer to users physical data about environment(body or equipment) on which sensor is mounted. In the last years, thanks to inertial sensor power consumption dramatic reduction, new applications came out: IoT is certainly, but not only, an example of what can be achieved on battery operated devices. At this point the pervasion is continuing, and accordingly the technology convergence: innovative smart sensors, able to further reduce energy requirement, able to recognize autonomously what’s happening around them, are on the road: new sensors are able to give to the application the right feedback just when application needs it. This paper introduces a programmable and configurable embedded digital module which further reduces system power consumption, moving part of the intelligence into the sensor, and so keeping the main processor in sleep mode. The digital module is composed by two embedded reconfigurable blocks able to solve two main sets of application requests. The first is conceived for systematic motion recognition using a reconfigurable Finite State Machine; application examples are motion-no motion, human gestures and industrial applications. The second is conceived for statistical-based context awareness; using a decision tree approach it is possible to perform human activity recognition (still, walk, vehicle, etc.), carry-position detection (on wrist, in pocket, on table, etc.) and machine activity and movement recognition. These two blocks can be programmed and mutually concatenated by using a simple GUI running on a common PC to exploit digital module full configurability and to fit user needs easily, quickly and effectively. The embedded digital module allows to move whole or part of the algorithm elaboration in a custom low power environment on sensor side, reducing communication to the main processor, and thus reducing overall power consumption.
--- Date: 28.02.2018 Time: 10:30 AM - 11:00 AM Location: Conference Counter NCC Ost