Inertial measurement unit

About: Inertial measurement unit is a research topic. Over the lifetime, 13326 publications have been published within this topic receiving 189083 citations. The topic is also known as: IMU.

Potential of IMU Sensors in Performance Analysis of Professional Alpine Skiers

Abstract: In this paper, we present an analysis to identify a sensor location for an inertial measurement unit (IMU) on the body of a skier and propose the best location to capture turn motions for training. We also validate the manner in which the data from the IMU sensor on the proposed location can characterize ski turns and performance with a series of statistical analyses, including a comparison with data collected from foot pressure sensors. The goal of the study is to logically identify the ideal location on the skier's body to attach the IMU sensor and the best use of the data collected for the skier. The statistical analyses and the hierarchical clustering method indicate that the pelvis is the best location for attachment of an IMU, and numerical validation shows that the data collected from this location can effectively estimate the performance and characteristics of the skier. Moreover, placement of the sensor at this location does not distract the skier's motion, and the sensor can be easily attached and detached. The findings of this study can be used for the development of a wearable device for the routine training of professional skiers.

A UAV-based photogrammetric mapping system for road condition assessment

Abstract: We present an Unmanned Aviation Vehicle-based Photogrammetric mapping system in this paper. This work is part of a project monitoring of unpaved road condition using remote sensing and other technology, sponsored by the US Department of Transportation. The system is based on a low cost model helicopter equipped with a GPS/IMU and a geomagnetic sensor to detect the position, attitude and velocity of the helicopter. An autonomous controller was employed to control helicopter to fly along a predefined flight path and reach the desired positions. At the ground station, a computer was used to communicate with the helicopter in real-time to monitor flight parameters and send out control commands. The entire processing system includes camera calibration, integrated sensor orientation, digital 3D road surface model and orthoimage generation, automated feature extraction and measurement for road condition assessment. In this paper, both the project and the system architecture are described, and the recent development results are presented.

Foot-to-Foot Range Measurement as an Aid to Personal Navigation

Abstract: Ultimately there will be times when all enhancements to GPS signal reception fail. In these situations a number of approaches to GPS denied navigation have been proposed. These often make use of supplemental radio frequency signals, some of which actually require setting up a local RF infrastructure. The personal navigation aid proposed here, although utilizing a radio frequency signal, is intended to be self contained and of low power. It consists of a micromechanical IMU on each boot combined with a series of foot-to-foot range measurements. A frequency generator at the waist sends a signal down one leg to a transmitting antenna on one boot. The RF signal is received on the other boot and sent to the waist pack thereby closing the loop. A detector at the waist measures phase change and thus measures the changing distance between the two feet. Our analysis shows that this scalar distance change measurement used in conjunction with micro-mechanical inertial instruments on each foot and combined with "zero-velocity updates" at each (or most) foot falls enables quite accurate personal navigation. The performance of an unaided inertial navigation system based on modest quality micromechanical instruments is truly poor. Our analysis shows a 2.5 km error in each horizontal direction after walking in a straight line for 10 minutes (2900 ft). The addition of zero velocity updates reduces this error to 60 m predominantly in the cross range axis. The addition of the foot-to-foot range change measurement reduces this value by another two orders of magnitude, to 0.6 m This measurement concept is a big step toward an accu-rate self-contained personal navigation system It is not dependent on external signals or ambient light. The RF could be very low power (it only has to extend over the foot-to-foot distance). As such it should be relatively covert compared to a Doppler radar or acoustic Doppler device. There is a price to pay in terms of body mounted hardware, but this could be mitigated by the push toward instrumented clothing.

Human Activity Recognition with Convolutional Neural Networks

Abstract: The problem of automatic identification of physical activities performed by human subjects is referred to as Human Activity Recognition (HAR). There exist several techniques to measure motion characteristics during these physical activities, such as Inertial Measurement Units (IMUs). IMUs have a cornerstone position in this context, and are characterized by usage flexibility, low cost, and reduced privacy impact. With the use of inertial sensors, it is possible to sample some measures such as acceleration and angular velocity of a body, and use them to learn models that are capable of correctly classifying activities to their corresponding classes. In this paper, we propose to use Convolutional Neural Networks (CNNs) to classify human activities. Our models use raw data obtained from a set of inertial sensors. We explore several combinations of activities and sensors, showing how motion signals can be adapted to be fed into CNNs by using different network architectures. We also compare the performance of different groups of sensors, investigating the classification potential of single, double and triple sensor systems. The experimental results obtained on a dataset of 16 lower-limb activities, collected from a group of participants with the use of five different sensors, are very promising.