Smart Stick: Real-time Fall Detection and Pace Measurement

The objective of the smart stick prototype is to make pace measurement and fall detection. By profiling the time series data collected from the gyroscope sensor embedded into the stick, the tool can be used to evaluate the fitness of individuals. In this prototype an Atmel EB63 is used for data collection and analysis. Performance analysis showed that a small footprint, low power microcontroller can be fit into a walking stick to collect and analyze the angular velocity data. The movement dynamics of the user is represented by the time series data, and the walking pace can be measured by local maxima/minima.

Fall detection:

Figure 2(a) shows an example of raw data of the gyro sensor. Point A represents the first of two parts of a step with a walking stick. Point B represents the step taken by the user to stand beside the stick. The jagged edges is filtered by a simple the running average low-pass minima/maxima filter and the result is given in Figure 2(b). This smoother representation of the gyro output is used for fall detection.

Pace Measurement:

• We consider the time period between two adjacent peaks of angular velocity as one step. A search procedure is initiated to find the distance between peaks. The procedure is terminated if the next point’s value drops under a threshold. The peak points are marked with a vertical black line, as shown in Figure 5. (Pace equations not included on this page.)