Conference PaperPDF Available

Pedestrian Activity Classification to Improve Human Tracking and Localization

Authors:

Abstract and Figures

The advent of miniaturized sensing technology (MEMS: Micro-Electro-Mechanical Systems) gave the possibility to collect data on different aspects of human activities. E.g. it is possible to recognize activities using hip-mounted sensing. Furthermore a dynamic changing filter model could be developed for the use in existing pedestrian localization systems (fusion algorithm) depending on the human activity to improve the estimated position. Nine degrees of freedom (DOF) sensors (acceleration, angular rate and magnetic field), such as those integrated in almost every smartphone, have been taken as the basis. With the presented algorithm it is possible to distinguish seven activities: standing, walking, running, lying, cycling, throwing and entering or leaving a car. Each activity is identified by using a linear classifier and a decision tree approach. The linear classifier parameters are set by using the k-means algorithm of the clustered features. The features for classification process include quantities like variance, frequency component, mean and the absolute value. Finally, when no periodical movement pattern is detected, the system successfully discriminates between standing and lying by estimating the projection of the gravitational field vector.Measurement data was collected with twenty subjects performing the seven different activities. Using the algorithm, activities were classified correctly with an accuracy of 91 %.An advantage of the presented method is the simple implementation, because of the low complexity of the algorithm. Furthermore, the algorithm works with low-cost sensors and is independent of any infrastructure. Possible applications are a indoor navigation scenarios in combination with Wi-Fi localization or protection of vulnerable road users in traffic situations by communicating the data to the vehicle.
Content may be subject to copyright.
2013 International Conference on Indoor Positioning and Indoor Navigation, 28
th
-31
th
October 2013
Pedestrian Activity Classification to Improve Human
Tracking and Localization
Marcus Bocksch, Jochen Seitz, Jasper Jahn
Fraunhofer Institute for Integrated Circuits IIS
Nordostpark 93
Erlangen-Nuremberg, Germany
Email: marcus.bocksch@iis.fraunhofer.de
Abstract—The advent of miniaturized sensing technology
(MEMS: Micro-Electro-Mechanical Systems) gave the possibility
to collect data on different aspects of human activities. E.g. it is
possible to recognize activities using hip-mounted sensing.
Furthermore a dynamic changing filter model could be developed
for the use in existing pedestrian localization systems (fusion
algorithm) depending on the human activity to improve the
estimated position. Nine degrees of freedom (DOF) sensors
(acceleration, angular rate and magnetic field), such as those
integrated in almost every smartphone, have been taken as the
basis. With the presented algorithm it is possible to distinguish
seven activities: standing, walking, running, lying, cycling,
throwing and entering or leaving a car. Each activity is identified
by using a linear classifier and a decision tree approach. The
linear classifier parameters are set by using the k-means
algorithm of the clustered features. The features for classification
process include quantities like variance, frequency component,
mean and the absolute value. Finally, when no periodical
movement pattern is detected, the system successfully
discriminates between standing and lying by estimating the
projection of the gravitational field vector.Measurement data was
collected with twenty subjects performing the seven different
activities. Using the algorithm, activities were classified correctly
with an accuracy of 91 %.An advantage of the presented method
is the simple implementation, because of the low complexity of
the algorithm. Furthermore, the algorithm works with low-cost
sensors and is independent of any infrastructure. Possible
applications are a indoor navigation scenarios in combination
with Wi-Fi localization or protection of vulnerable road users in
traffic situations by communicating the data to the vehicle.
Keywords: motion classification, pedestrian activity recognition,
motion sensors, low-cost sensor, inertial sensor
I. I
NTRODUCTION
This The Fraunhofer Institute for Integrated Circuits (IIS)
develops different pedestrian localization systems based on
sensor fusion for different environments. We are working on a
seamless citywide indoor and outdoor Wi-Fi positioning
system (awiloc
®
) based on a database of so called fingerprints.
Reasons for choosing this approach are that fingerprinting is
reported to achieve higher precision than base station based
methods and in general positions of publically available access
points are unknown and subject to privacy protection [1]. Also,
we have a high precision Pseudolite System (PLIIS) for
localization in GPS-denied environments and GPS-Inertial
Navigation System (INS) positioning systems as well.
The heart of those systems are Bayesian estimators like
Kalman or particle filter. In each time step, the filter estimates
a new position based on the assumed motion model. For this
reason a correct motion model is very important for the
precision of the position. But what if the pedestrian changes
his motion state? An algorithm is needed to estimate the
pedestrian activity and adapt the motion model of the
localization filter dynamically.
Furthermore, an INS Localization system provides a
suitable position and orientation estimate only for a very
limited period of time. The first problem is initialization of an
inertial navigation system (INS) - an absolute position is
needed. Second, the systematic errors that are present in small
low-cost inertial sensors quickly accumulate to unacceptable
position errors. Such characteristics are not appropriate to
compute position by double integration of acceleration.
An alternative is to use the sensor signal pattern to classify
the motion. Depending on the motion, each step can be
detected and the length estimated [13] to compute the distance
travelled from the last known or estimated position. When the
information on the distance travelled is combined with the
azimuth information, the current position can be calculated
(Dead Reckoning) [1,7].
In this paper we present a pedestrian activity classification
algorithm based on IMU and magnetic field sensors. It can be
easily adapted to fit different sensor platforms.
2013 International Conference on Indoor Positioning and Indoor Navigation, 28
th
-31
th
October 2013
II. M
ATERIALS AND METHODS
A. Measurement Systems
An IMU uses a combination of a three-axial accelerometer
and a three-axial angular rate sensor. With these sensors
accelerations and rotations in six degrees of freedom can be
measured [6].
In this work micro-electro-mechanical system (MEMS)
sensors are used. The reasons are their low cost, low power
consumption, small size and light weight. Such MEMS sensors
are available as three-axial accelerometer, three-axial angular
rate and three-axial magnetometers. Nowadays, they can be
found in various consumer products such as smart phones,
gaming devices, etc. For the mentioned reasons, these sensors
are a suitable base for pedestrian activity classification.
B. Hardware Systems
Figure 1 shows a self-designed hardware prototype for
demonstration purposes.
Figure 1. Demonstrator hardware for Pedestrian activity classification
The prototype consists of two parts. The first part is a belt-
worn sensor platform and the second is an Android based
tablet. Both modules communicate via Bluetooth to each other.
The battery-operated sensor platform (icos-X) works full
autonomous and can be hence worn near the center of mass of
the body. It is also a self-designed highly integrated electronic
system for various applications [4]. The icos-X with hardware
architecture is shown in Figure 2. For the demonstrator
hardware we use only the processor board, IMU board and the
powersupply board. The small package size makes it attractive
for use in pedestrian applications.
The data are measured with an accelerometer, gyroscope
and magnetometer. The accelerations and rotation rates are
measured in the range between ±2g and ±2000 °/s,
respectively. The range of the magnetometer is between ±0.7
Gauss. This sensitivity is sufficient for the mentioned
activities. The sample rate (fs) is set to 50 Hz.
Figure 2. Modular HW/SW platform (icos-X)
The data are measured with an accelerometer, a gyroscope
and a magnetometer. The accelerations and rotation rates are
measured in the range between ±2g and ±2000 °/s,
respectively. The range of the magnetometer is between ±0.7
Gauss. This sensitivity is sufficient for the mentioned
activities. The sample rate (fs) is set to 50 Hz.
These sensors are connected to the microprocessor, which
performs the signal processing. The algorithm results are
transmitted wireless to the Android device. At the end, the
classified activities are presented to the user as animations. In
addition the visualization-app shows the counted steps and the
estimated velocity [5, 14].
C. Feature Extraction
The classification algorithm distinguishes between
standing, walking, running, lying (on the ground), cycling,
throwing and entering- or leaving-a-car. Some features from
acceleration, angular rate and magnetic field describe similar
relations and are not complementary. To reduce not required
features the Stepwise-Selection-Method [3] was used.
The algorithm is based on the parameters which are
extracted from the measured data using a time window
t. The
key sensor input for most of the activities is the accelerometer
data. Very important features are the simple moving average
value (SMA) and the variance (
s
2
) of the acceleration signal.
The SMA-value is computed from the acceleration vector
acc= (acc
x
acc
y
acc
z
) and the average in respect to the time
window
t:
2013 International Conference on Indoor Positioning and Indoor Navigation, 28
th
-31
th
October 2013
+
=
++
=
tt
tt
zyx
n
accaccacc
t
SMA
0
0
222
1
(1)
The variance value is the sum of each axis computed
variance of the acceleration signal:
+
=
=
tt
tt
mean
n
acc
t
acc
0
0
1
(2)
+
=
=
tt
tt
mean
n
accacc
t
0
0
||
1
²
σ
(3)
The advantage compared to some other features is the
independence from the orientation of the sensor module.
D. Data Collection Phase
The algorithm is calibrated and validated with data from 14
male and 6 female persons. The age of the persons was
between 20 and 30 years. All measurements for standing,
walking, running, cycling and entering or leaving a car were
performed on level asphalt ground. The data-collection phase
was split in four parts.
The first phase consisted of a 150 meter long way for the
activities walking and running. In second phase we collected
data for the activity bicycle riding. A standard city bicycle was
used without mechanical suspension. Each person had to ride
two different bicycles for one kilometer. In third phase we were
walking to the car, entering the car, sitting in the car, leaving
the car and go back to the start position. Two different cars
with 5 doors in normal size were used. Measurements like
open-the-door without entering the car, or pass-the-car were
also part of the phase. In phase four we collected data for lying
on the ground and the special state throwing. The state
throwing was measured by a two meter free fall of the sensor-
system.
E. Classification
Only one half of these data sets (training data) were used
for estimating the thresholds of the decision rules. The
computed features are drawn in scatter plot [8].
At first, the centers of gravity of each cluster were
determined. The most well-known and commonly used
partitioning method for that is the k-means algorithm.
2
1
),(
∑ ∑
= ∈
=
k
i Cim
ji
j
mpdistE
(4)
The k-means algorithm takes the input parameter, and
partitions a set of j features into k clusters [9]. dist is the
distance measure between a data point m
j
(mj,x|mj,y) and the
cluster center pi(pi,x|pi,y) with 1<= k <= N. N describes the
sum of all features. Both pi and m
j
are multidimensional. The
computed distance is based on the most widely used Euclidean
distance:
||),(
jiji
mpmpdist =
(5)
E is the sum of the squared Euclidean distance for all
features in the data set. The aim is to minimize E for each
cluster. The derivation of E is the cluster center pi, it is
computed by the labeled trainings data.
0
)( =
i
i
p
pE
;
=
ij
ij
Cm
Cm
j
i
m
p1
(6)
At the end, each cluster is represented by its centroid. Two
centroids describe a straight line Pi,l with i != l. The
orthogonal line through the midpoint Mi,l of two centroids is
the result for thresholds Ti,l (straight line) of the classifications
[15].
xi,xl,
yl,xi,yi,xl,
xi,xl,
yi,yl,
,,,
pp
pppp
pp
pp
+=+= xnxmP
lilili
(7)
=
+
+
2
pp
;
2
pp
);(
yl,yi,
xl,xi,
,
yx
MMM
li
(8)
++=
x
li
y
li
li
M
m
Mx
m
xT
,,
,
11
)(
(9)
F. Activity Classification Algorithm
At each step the algorithm will provide a new computed
feature. The decision rules are modeled with a decision tree:
1) Classifier state throwing:
If the acceleration sensor unit is in free-fall motion, the
SMA features (t = 1/fs) is close to zero. Therefore, it will
check periodically, if it is close to zero. If it is the case, the
state throwing is classified.
2) Classifier state lying (on the ground):
Measurements from the accelerometer have two major
contributions: local gravity and acceleration due to motion. The
gravity is taken as 1g (equal 9.81 m/s
2
). For that reasons, lying
is classified by the orientation of the earth-gravitational-field
vector. In this case, the wearing position must be known.
3) Classifier state running:
Typical characteristics for walking/running are found in
frequency domain (peak frequency and amplitude) and
2013 International Conference on Indoor Positioning and Indoor Navigation, 28
th
-31
th
October 2013
variance [8]. The linking of two features like SMA and variance
provides non-overlapping clusters (see Figure 3).
Figure 3. Scatter plot to classificate running
4) Classifier state entering-a-car:
A vehicle consists mainly of ferromagnetic materials. If a
ferromagnetic material (e.g. hollow cylinder) is placed in a
homogeneous magnetic field, the field lines are distorted. The
magnetic field inside of the cylinder is also reduced [10]. This
effect occurs in similar fashion by the activity entering-a-car
(see Figure 4).
Figure 4. Change / Distortion of the earth magnetic field close to
ferromagnetic material (entering-a-car)
An indicator for the state is a minimum detection of the
filtered SMA value. After that it has to be checked, if the
current signal is reduced and if the amplitude of the variance is
low.
This characteristic is not sufficient enough, because passing
a metal door would yield similar results. A second
characteristic is the signal pattern of the angular rate sensor.
Each axis provides different information. The rotation of the
body is measured be the vertical component (upward). In this
way it is easy to recognize e.g. the door-open-phase. The
algorithm uses the data of the horizontal axis (toward the left
side of the body). This axis has the advantage that the
measured signals are independent of the entry side of the
vehicle. The movement into the vehicle produces a forward
movement with a subsequent backward movement of the body
into the seat. In the following door-close-phase the movements
have a similar pattern. Figure 5 shows the forward and
backward rotations of all persons. The characteristic can be
filtered by a simple band-pass filter with the cutoff frequencies
at 0.5 and 1.5 Hz . If the both conditions occur in a time span of
three seconds, the state is classified.
Figure 5. Signal pattern of the angular rate sensor (horizontal axis, toward to
the left side of the body): (a) time domain, (b) frequency domain
2013 International Conference on Indoor Positioning and Indoor Navigation, 28
th
-31
th
October 2013
5) Classifier state standing:
If the variance of the acceleration sensor is below a certain
threshold, the state standing is classified.
6) Classifier state cycling or walking:
The difference between cycling and walking can be found
in the frequency domain. The middle step frequency for
walking is around 1.5 Hz [11]. In contrast with cycling, the
frequencies are nearly evenly distributed [2]. To distinguish
between these two states a bandpass (BP) and highpass (HP)
filter is used to get the characteristics. Movements with and
without ground contact is classified by a simple threshold value
of the BP/HP value. To make the classification more reliable,
the feature for cycling must occur multiple times. If the
verification for cycling is true, cycling is classified. If not,
walking is detected.
Figure 6 displays the state transition model of all pedestrian
activities. It is optimized to reduce false detections. At first, it
is initialized with the state standing. From class standing it can
be changed to all other classes and vice versa. It is also possible
to stay in each class. Not all transitions are allowed e.g. from
the class lying it is not possible to change to falling or walking.
Figure 6. State transition model of all motions
III. R
ESULTS
The results of the classification were obtained from the
other half of the measured data. Table I shows the classification
results in percent.
TABLE I. C
LASSIFICATION
R
ESULTS
labeled data
values / percent
standing
walking
running
entering
a car
throwing
cycling
lying
standing 92 0 0 24 0 7 0
walking 8 100 0 0 0 21 0
running 0 0 100 0 0 0 0
entering a
car 0 0 0 76 0 0 0
throw 0 0 0 0 100 0 0
cycling 0 0 0 0 0 72 0
classification
lying 0 0 0 0 0 0 100
The sum of each column is 100 percent. Column one e.g.,
standing is classified correctly with 92 % and with 8 %
wrongly as walking. Using the algorithm, all activities were
classified correctly with an accuracy of 91 %.
IV. C
ONCLUSIONS
In this paper, an algorithm for pedestrian activity
classification is presented. With the algorithm it is possible to
distinguish seven activities: standing, walking, running, lying,
cycling, throwing and entering or leaving a car. Nine degrees
of freedom (DOF) sensors (acceleration, angular rate and
magnetic field), such as those integrated in almost every
smartphone, have been taken as the basis. The activities are
classified by using a linear classifier and a decision tree
approach. The mean accuracy of all activities is 91%.
To show the algorithm results, a demonstrator for
Pedestrian activity classification was developed and
successfully presented on many exhibitions.
In the next version, the algorithm will provide qualities
criterion for all activities.
A
CKNOWLEDGMENT
Most of the work was performed as part of the project Ko-
TAG, which is part of the project initiative Ko-FAS, and has
been partially funded by the German Bundesministerium für
Wirtschaft und Technologie (Federal Department of
Commerce and Technology) under contract number 19S9011.
Ko-TAG is a research project in the field of safety
improvements for vulnerable road users. The project analyzes
the potential of cooperative sensor technologies to create a
consistent environmental model. This environmental model
supports the driver in assessing the current traffic situation by
detecting and highlighting vulnerable road users like kids or
cyclists.
2013 International Conference on Indoor Positioning and Indoor Navigation, 28
th
-31
th
October 2013
R
EFERENCES
[1] Seong Yun Cho, “MEMS Based Pedestrian Navigation System”, The
journal of navigation, 2006
[2] M. Rulsch, M. Benz, C. Arzt, C. Podolak, J. Zhong, R. Couronné, „A
lightweight approach for activity classification on microcontrollers“
[3] L. Fahrmeir, T. Kneib, S. Lang, „Regression Modelle, Methoden und
Anwendung“, Spring, 2. Auflage, New York, 2009
[4] progenoX GmbH, "icos-X: Integrierte Kommunikations-, Ortungs- und
Sensorplattform", 2013
[5] BUSINESS GEOMATICS, “Lokalisierung auf Hüfthöhe”
[6] M. S. Grewal, L. R. Weill, A. P. Andrews, „Global Positioning
Systems, Inertial Navigation and Integration“, Second Edition, New
Jersey, 2007
[7] J. Yang, “Toward Physical Activity Diary: Motion Recognition Using
Simple Acceleration Features with Mobile Phones”, Proc. 1st Int.
Workshop on Interactive Multimedia for Consumer Electronics (IMCE)
at ACM Multimedia 2009, ACM Press, Oct. 2009, pp. 1-10.
[8] J. Kantola, M. Perttuner, T. Leppänen, J. Collin, J. Riekki, “Context
Awareness for GPS-Enabled Phones”
[9] Junjie Wu, “Advances in K-means Clustering: A Data Mining
Thinking”, Springer, Berlin, Heidelberg, 2012
[10] Bergmann Schaefer, “Elektromagnetismus” Band 2, 8 Auflage, 1999
[11] Q. Ladetto, V. Gabaglio, B. Merminod, P. Terrier, Y. Schutz, “Human
Walking Analysis Assisted by DGPS, GNSS, Ediburgh, 2000
[12] 1J. Seitz, T. Vaupel, S. Haimerl, J. Guti´errez Boronat, and J. Thielecke,
“Wi-fi azimuth and position tracking using directional received signal
strength measurements” in Workshop on Sensor Data Fusion (SDF
2012): Trends, Solutions, Applications, Sept. 2012, pp. 72 –77.
[13] J. Jahn,U. Batzer,J. Seitz, L. Patino-Studencka,J. G. Boronat,
“Comparison and Evaluation of Acceleration Based Step Length
Estimators for Handheld Devices”, In Proceedings of IEEE 2nd
Conference on Indoor Positioning and Indoor Navigation, Zurich,
Switzerland, 15–17 September 2010; pp. 1–6.
[14] Fraunhofer IIS, „Algorithms for motion classification”,
http://www.iis.fraunhofer.de, 2013
[15] M. Koecher, “Lineare Algebra und analytische Geometrie”, 4 Auflage,
Springer, 2003
... Inertial measurement units (IMU) are often used to estimate orientation and motion of human body or limbs in human positioning and navigation systems. Most of these systems use trunk [1] or foot [2] movement to identify human gait and they usually use relatively computationally expensive orientation estimation algorithms often utilizing Kalman filtering [3][4][5]. ...
... However, it was noted that the total acceleration can be less than gravity when the IMU is in acceleration against gravity. Hence, one condition for zero acceleration update was taken as (1) where ( = , , ) is the acceleration of axis measured at time stamp k. The parameters and are selected to accommodate the noise embedded in the accelerometer reading. ...
... The average execution time is~250 µs for walking trials. This implies that the GIOF is computationally economical (by a factor of 1 2 ) compared to complementary filter. Further, although the complementary filter had similar correlations when α = 0.9999 in MATLAB simulations, in real-time implementation, the output of complementary filter drifted for that α value. ...
Article
Full-text available
Inertial measurement units are commonly used to estimate the orientation of sections of sections of human body in inertial navigation systems. Most of the algorithms used for orientation estimation are computationally expensive and it is difficult to implement them in real-time embedded systems with restricted capabilities. This paper discusses a computationally inexpensive orientation estimation algorithm (Gyro Integration-Based Orientation Filter—GIOF) that is used to estimate the forward and backward swing angle of the thigh (thigh angle) for a vision impaired navigation aid. The algorithm fuses the accelerometer and gyroscope readings to derive the single dimension orientation in such a way that the orientation is corrected using the accelerometer reading when it reads gravity only or otherwise integrate the gyro reading to estimate the orientation. This strategy was used to reduce the drift caused by the gyro integration. The thigh angle estimated by GIOF was compared against the Vicon Optical Motion Capture System and reported a mean correlation of 99.58% for 374 walking trials with a standard deviation of 0.34%. The Root Mean Square Error (RMSE) of the thigh angle estimated by GIOF compared with Vicon measurement was 1.8477°. The computation time on an 8-bit microcontroller running at 8 MHz for GIOF is about a half of that of Complementary Filter implementation. Although GIOF was only implemented and tested for estimating pitch of the IMU, it can be easily extended into 2D to estimate both pitch and roll.
... Inertial measurement units (IMU) are often used to estimate orientation and motion of human body or limbs in human positioning and navigation systems. Most of these systems use trunk [1] or foot [2] movement to identify human gait and they usually use relatively computationally expensive orientation estimation algorithms often utilizing Kalman filtering [3][4][5]. ...
... However, it was noted that the total acceleration can be less than gravity when the IMU is in acceleration against gravity. Hence, one condition for zero acceleration update was taken as (1) where ( = , , ) is the acceleration of axis measured at time stamp k. The parameters and are selected to accommodate the noise embedded in the accelerometer reading. ...
... The average execution time is~250 µs for walking trials. This implies that the GIOF is computationally economical (by a factor of 1 2 ) compared to complementary filter. Further, although the complementary filter had similar correlations when α = 0.9999 in MATLAB simulations, in real-time implementation, the output of complementary filter drifted for that α value. ...
Article
Gait analysis is relevant to a broad range of clinical applications in areas of orthopedics, neurosurgery, rehabilitation and the sports medicine. There are various methods available for capturing and analyzing the gait cycle. Most of gait analysis methods are computationally expensive and difficult to implement outside the laboratory environment. Inertial measurement units, IMUs are considered a promising alternative for the future of gait analysis. This study reports the results of a systematic validation procedure to validate the foot pitch angle measurement captured by an IMU against Vicon Optical Motion Capture System, considered the standard method of gait analysis. It represents the first phase of a research project which aims to objectively evaluate the ankle function and gait patterns of patients with dorsiflexion weakness (commonly called a “drop foot”) due to a L5 lumbar radiculopathy pre- and post-lumbar decompression surgery. The foot pitch angle of 381 gait cycles from 19 subjects walking trails on a flat surface have been recorded throughout the course of this study. Comparison of results indicates a mean correlation of 99.542% with a standard deviation of 0.834%. The maximum root mean square error of the foot pitch angle measured by the IMU compared with the Vicon Optical Motion Capture System was 3.738° and the maximum error in the same walking trail between two measurements was 9.927°. These results indicate the level of correlation between the two systems.
... Researchers have used many approaches to detect different human activities. In most of these techniques, a 3-axis accelerometer is used to measure the acceleration of the trunk [1] or a section of a leg [2]. This paper proposes a novel approach for human activity detection using the thigh angle derived from a single thigh mounted Inertial Measurement Unit (IMU). ...
... II. EXISTING WORK the majority of the existing work on human activity detection use 3-axis accelerometers to measure the trunk or the leg movement while some work use a gyroscope in conjunction with the accelerometer. Bocksch et al. [1] have discussed an activity classification method that uses a 9-degree of freedom IMU. They detect standing, running, walking, in car, lying, cycling and falling in their system. ...
Conference Paper
Full-text available
Accurate human activity recognition is a challenging topic of research in many areas. A common approach to activity recognition is to use accelerometers and/or gyroscopes to detect trunk or leg movement. This paper present a novel approach to detect human activities based on thigh angle computed using data from a single thigh mounted Inertial Measurement Unit (IMU). As this work forms a component of a system under development to assist the vision impaired in indoor navigation, activities common in indoor pedestrian tracking such as sitting, standing and walking were considered in the development of the algorithm. This algorithm uses simple signal processing techniques including peak detection, zero crossing detection and timers to identify the activity based on the thigh angle computed by fusing accelerometer and gyroscope. This allows implantation of the algorithm in a general purpose low end microcontroller. To reduce the number of input parameters to the algorithm, it was assumed that accelerometer y–axis is aligned with the thigh such that gyroscopic x–data represents angular velocity of the forward and backward movement of the thigh. The algorithm has shown above 78% accuracy in detecting standing, above 92% accuracy for walking and no measured errors for sitting, in a test conducted with a limited number of samples with ideal testing conditions. These results indicate that this less computationally intense algorithm gives promising results in activity detection in indoor pedestrian navigation applications.
... Gait recognition is often used in infrastructure-independent navigation systems, such as inertial navigation systems. Gait analysis is performed in these systems based on trunk movement [1,2], foot movement [3,4] or thigh movement [5,6]. Some of these techniques use acceleration, whereas the others use the rotation or the orientation of the particular body section. ...
Article
Full-text available
The majority of human gait modeling is based on hip, foot or thigh acceleration. The regeneration accuracy of these modeling approaches is not very high. This paper presents a harmonic approach to modeling human gait during level walking based on gyroscopic signals for a single thigh-mounted Inertial Measurement Unit (IMU) and the flexion–extension derived from a single thigh-mounted IMU. The thigh angle can be modeled with five significant harmonics, with a regeneration accuracy of over 0.999 correlation and less than 0.5° RMSE per stride cycle. Comparable regeneration accuracies can be achieved with nine significant harmonics for the gyro signal. The fundamental frequency of the harmonic model can be estimated using the stride time, with an error level of 0.0479% (±0.0029%). Six commonly observed stride patterns, and harmonic models of thigh angle and gyro signal for those stride patterns, are presented in this paper. These harmonic models can be used to predict or classify the strides of walking trials, and the results are presented herein. Harmonic models may also be used for activity recognition. It has shown that human gait in level walking can be modeled with a harmonic model of thigh angle or gyro signal, using a single thigh-mounted IMU, to higher accuracies than existing techniques.
... Gait recognition is often used in infrastructure-independent navigation systems, such as inertial navigation systems. Gait analysis is performed in these systems based on trunk movement [1,2], foot movement [3,4] or thigh movement [5,6]. Some of these techniques use acceleration, whereas the others use the rotation or the orientation of the particular body section. ...
Article
The majority of human gait modeling is based on hip, foot or thigh acceleration. The regeneration accuracy of these modeling approaches is not very high. This paper presents a harmonic approach to modeling human gait during level walking based on gyroscopic signals for a single thigh-mounted Inertial Measurement Unit (IMU) and the flexion–extension derived from a single thigh-mounted IMU. The thigh angle can be modeled with five significant harmonics, with a regeneration accuracy of over 0.999 correlation and less than 0.5° RMSE per stride cycle. Comparable regeneration accuracies can be achieved with nine significant harmonics for the gyro signal. The fundamental frequency of the harmonic model can be estimated using the stride time, with an error level of 0.0479% (±0.0029%). Six commonly observed stride patterns, and harmonic models of thigh angle and gyro signal for those stride patterns, are presented in this paper. These harmonic models can be used to predict or classify the strides of walking trials, and the results are presented herein. Harmonic models may also be used for activity recognition. It has shown that human gait in level walking can be modeled with a harmoni
... Experimental road roughness data was classified according to ISO 8608 road class using vehicle transfer functions and classification tree for customer usage profile, in the context of durability engineering [21]. For hybrid data-mining approach in automotive applications, K-means clustering and classification tree were combined to classify pedestrian activity [22]. Based on the literature survey, combination of various data mining approach has shown improved efficiency in various automotive applications. ...
Article
This paper presents clustering of automotive spring fatigue life for failure classification based on K-means approach. For safety promotion of buses, fatigue life prediction of the spring is needed to be classified for maintenance. In this analysis, the strain signals of a heavy vehicle leaf spring were collected from two common roads and analyzed using Hilbert Huang transform. The strain amplitude was used to obtain fatigue life of the leaf spring. Subsequently, the instantaneous frequencies, energies and fatigue lives were clustered into three groups according to the K-means approach. Numerous classification trees were trained with the clustered group as target while the instantaneous frequencies, energies and fatigue lives datasets as input. The trained classification trees were evaluated using receiver operating characteristic curve which shown an acceptable prediction of classes. This classification tree serves as a tool to evaluation automotive leaf spring design for fatigue failure prevention without destroying the component.
Chapter
The automated recognition of human activity is an important computer vision task, and it has been the subject of an increasing number of interesting home, sports, security, and industrial applications. Approaches using a single sensor have generally shown unsatisfactory performance. Therefore, an approach that efficiently combines data from a heterogeneous set of sensors is required. In this paper, we propose a new method for human activity recognition fusing data obtained from inertial sensors (IMUs), surface electromyographic recording electrodes (EMGs), and visual depth sensors, such as the Microsoft Kinect®. A network of IMUs and EMGs is scattered on a human body and a depth sensor keeps the human in its field of view. From each sensor, we keep track of a succession of primitive movements over a time window, and combine them to uniquely describe the overall activity performed by the human. We show that the multi-modal fusion of the three sensors offers higher performance in activity recognition than the combination of two or a single sensor. Also, we show that our approach is highly robust against temporary occlusions, data losses due to communication failures, and other events that naturally occur in non-structured environments.
Conference Paper
Regaining the locomotive ability is necessary to maintain the activities of daily living in lower extremity amputees. Recently, the stability of the gait and multifunctionality of transfemoral prosthetic knees have drastically improved with the use of microprocessor-controlled knees, such as Genium ® (Otto Bock, GmbH). However, these knees, which also include products from other companies, are very expensive. Therefore, the purpose of the present study was to develop a control method for transfemoral prosthetic knees in order to perform level walking and stairs ascending safely, with fewer sensors or simpler procedures. First, we analyzed the gait of an intact subject and therefore we proposed a control algorithm for prosthetic knees with only thigh angular kinematics. Then, an evaluation experiment on the prototype knee, in which the proposed algorithm was implemented, was conducted. As a result, the participant successfully performed level walking, stairs ascending and transition between the two types of gait. The functions of the prosthetic knee changed automatically using the proposed algorithm with thigh angular kinematics. Then, the reliability of the algorithm was checked with a database of gait analyses. The results showed that the algorithm was applicable to 99.8 % of the population.
Book
In dieser Einführung werden erstmals klassische Regressionsansätze und moderne nicht- und semiparametrische Methoden in einer integrierten, einheitlichen und anwendungsorientierten Form beschrieben. Die Darstellung wendet sich an Studierende der Statistik in Wahl- und Hauptfach sowie an empirisch-statistisch und interdisziplinär arbeitende Wissenschaftler und Praktiker, zum Beispiel in Wirtschafts- und Sozialwissenschaften, Bioinformatik, Biostatistik, Ökonometrie, Epidemiologie. Die praktische Anwendung der vorgestellten Konzepte und Methoden wird anhand ausführlich vorgestellter Fallstudien demonstriert, um dem Leser die Analyse eigener Fragestellungen zu ermöglichen.
Conference Paper
A new approach for estimating and tracking the azimuth angle regarding north and a two-dimensional position of a mobile unit is presented. Outdoors, the azimuth angle of a device can be easily detected using an electronic compass and the position can be calculated using a global navigation satellite system (GNSS). Indoors, magnetic disturbances lead to unreliable compass outputs. Also, indoors there exists no standard positioning system like GNSS outdoors. The presented approach is based on Wi-Fi signal strength measurements collected by four horizontally arranged directional antennas. To proof the concept the well known Wi-Fi fingerprinting based on the normalized Euclidean distance in signal space has been adopted. A test with measurements collected in a laboratory demonstrates the feasibility of the approach. Especially in indoor environments this facilitates the use of electronic guides that offer additional information by means of augmented reality, e.g. on museum exhibits in visual range.
Chapter
A lightweight activity classification algorithm suitable for microcontrollers is presented, which is intended to be used on activity monitors. Therefore it focuses on five daily activities: inactivity, walking, cycling and walking up- and downstairs. This algorithm includes a novel approach for detecting cycling, which relies on properties of the power spectrum. Classification parameters are extracted from accelerometer and barometer data streams. Resources on activity monitors are usually short. The algorithm is able to cope with these limitations and was implemented on our demonstration activity monitor. Classification results were obtained from two test trials. The first trial consisted of consecutive sequences of basic activities. In the second trial a complex daily activity was executed. Twelve persons participated in each trial. Classification rates in the first trial were very promising: inactivity (97.3 %), walking a straight plane (92.6%), cycling (82.2%), walking upstairs (66.8%) and downstairs (65.7%). However trial two depicted that a supplementary class should be introduced, which requires further research.
Conference Paper
A comparison between different step length estimation algorithms for pedestrian dead reckoning is presented. This work covers theoretic evaluation of the estimators' performance and presents a comparison based on measurement data. Measurement data were taken from a group of five adults walking at three different velocities. For reference, the sensors were placed according to the recommendation given for each algorithm. In respect to everyday usability the performance of the estimators is furthermore evaluated for arbitrary placement of the sensors, as it is the case when using a mobile measurement platform like a smartphone.
MEMS Based Pedestrian Navigation System
  • Yun Seong
  • Cho
Seong Yun Cho, "MEMS Based Pedestrian Navigation System", The journal of navigation, 2006
Lokalisierung auf Hüfthöhe
  • Business Geomatics
BUSINESS GEOMATICS, "Lokalisierung auf Hüfthöhe"
Toward Physical Activity Diary: Motion Recognition Using Simple Acceleration Features with Mobile Phones
  • J Yang
J. Yang, "Toward Physical Activity Diary: Motion Recognition Using Simple Acceleration Features with Mobile Phones", Proc. 1st Int. Workshop on Interactive Multimedia for Consumer Electronics (IMCE) at ACM Multimedia 2009, ACM Press, Oct. 2009, pp. 1-10.