This thesis investigates the feasibility and performance of an inertial based positioning system for dairy cows in a barn environment. The investigated positioning method is pedestrian dead reckoning using inertial navigation with MEMS sensors. While this method is well known for human positioning applications, there has not been a lot of studies of its use on terrestrial animals. Since inertial based positioning systems are dependent on drift correction, the focus of the research is drift correction methods. Two methods, zero velocity update (ZUPT) and sparse locations, are compared with regards to positioning accuracy, energy consumption and sensor placement.  The best positioning estimates are achieved by using ZUPT corrections at a sample rate of 10 Hz, resulting in a mean position drift of 0.2145 m=m. Using a proposed equidistant sample time based sleep mode scheme, this would require a theoretical supply current of 0.21 mA. It is also seen that better position estimates are obtained for sensors that are placed low and on the front legs. The sparse locations method suffers from severe position drift between the locations, resulting in unusable positioning data. A combination of ZUPT and sparse location yields less accurate positioning than ZUPT only. / Denna masteruppsats undersöker genomförbarhet och prestanda av ett tröghetsbaserat positioneringsssystem för mjölkkor i en lada. Den undersökta metoden är död räkning för fotgängare mha. tröghetsnavigering med MEMSsensorer. Denna metod är välkänd för positionering av människor, men få studier har gjorts kring dess användbarhet för djur. Eftersom tröghetsbaserad navigering är beroende av driftkorrigering är detta fokuset för forskningen. Två olika metoder utvärderas, zero velocity update (ZUPT) och sparse locations, och en jämförelse görs med avseende på positionsnoggrannhet, energiförbrukning och sensorplacering.Bäst positionering uppnås med ZUPT-korrigeringar vid en samplingsfrekvens på 10 Hz, vilket ger ett medelvärde av positionsdrift på 0.2145 m=m. Om ett föreslaget ekvidistant samplingstidsbaserat schema för viloläge används skulle 10 Hz kräva en teoretisk matningsström på 0.21 mA. Vidare fås bättre positioneringsresultat för sensorer som är placerade lågt och på frambenen. Korrektionsmetoden med sparse locations ger en svår positionsdrift mellan platserna, vilket resulterar i oanvändbar positionsdata. En kombination av ZUPT och sparse locations ger sämre precision än om endast ZUPT används, samt ökar energiförburkningen på grund av behovet av ytterligare sensorer.

INTRODUCTION: The zero-velocity update (ZUPT) method has become a popular approach to estimate foot kinematics from foot worn inertial measurement units (IMUs) for walking and running. However, it remains unknown how accurate the ZUPT method is for track sprinting speeds when using sensors with characteristics (i.e., higher ranges and sampling rates) better suited for sprinting. METHODS: 18 participants performed 70-meter track sprints while wearing a Blue Trident IMeasureU IMU. Two cameras, at 20 and 70 meters from the start, were placed to validate the ZUPT method on a stride-by-stride and on a cumulative distance basis. The validity of the method was assessed on: (1) A single stride attained at the end of the maximal speed phase, i.e., at 70m; (2) On a cumulative distance basis for the maximal speed phase from 20 to 70 meter; and (3) On total distance traveled for a 70-meter track sprint. RESULTS: Individual stride and cumulative distance errors remained within -8 to 3% and -4 to 2%, respectively. CONCLUSION: The results of this study demonstrate the ZUPT method is capable of yielding accurate estimates of stride length and cumulative distance traveled for sprinting speeds.

Along with the development of localization and navigation technologies, the Global Positioning System (GPS) plays an important role in our daily life, but it is confined in outdoor environments. The technology of human localization has been developed in recent years. This technology utilizes sensors to determine the movement of human and measure the distance of walking, which is not only used to solve the problem of GPS out-of-lock, but also used for the indoor localization. This thesis describes a human step-length recognition and real-time localization base on an embedded system. The goal of this system is to develop a gait pattern classification and pedestrian dead reckoning (PDR) method for human localization. Through the information of an Inertial Measurement Unit (IMU) and two force sensors mounted on a shoe, the wireless transmission module is used to send data of sensors to an embedded platform. Then the functions of step detection, step length estimation and gait pattern recognition can be achieved. According to coordinate transformation and the ZUPT algorithm, the accumulated error of velocity can be corrected. The dead reckoning method is used to obtain the information of location. Finally, the information of human location and gait patterns is sent to the Android system for remote monitoring.

No description available.