Fall Detection by Helmet Orientation and Acceleration

during Bike Riding
Ho-Rim Choi1, Mun-Ho Ryu2,3, Yoon-Seok Yang2, Nak-Bum Lee4
and Deok-Ju Jang5
1

Department of Healthcare Engineering, Chonbuk National University, 567 Baekje-daero,
Deokjin-gu, Jeonju-si, Jeollabuk-do 561-756 Republic of Korea
2
Division of Biomedical Engineering, Chonbuk National University, 567 Baekje-daero,
Deokjin-gu, Jeonju-si, Jeollabuk-do 561-756 Republic of Korea
3
Center for Healthcare Technology Development, Chonbuk National University, 567 Baekjedaero, Deokjin-gu, Jeonju-si, Jeollabuk-do 561-756 Republic of Korea
4
Technology Licensing Center, Industrial-Academic Cooperation Foundation, Chonbuk
National University, 567 Baekje-daero, Deokjin-gu, Jeonju-si, Jeollabuk-do 561-756
Republic of Korea
5
eClio Co., Ltd., 761-10, 2ga, Palbok-dong, Deokjin-gu, Jeonju-si, Jeollabuk-do, Republic of
Korea
{ck-ccr, mhryu, ysyang, biomecca}@jbnu.ac.kr, jdjjang@cliotech.co.kr

Abstract. This study represents research on falls while riding bicycles. We
present an algorithm that detects the occurrence and direction of falls during
bicycle riding through the use of a sensor module installed on the helmet. The
sensor module is equipped with a tri-axial accelerometer, tri-axial gyroscope,
and tri-axial magnetometer to record acceleration and tilt signals. We determine
the threshold of the algorithm for fall detection based on experiments of riding
over speed bumps and performing warm-up exercise motions prior to riding a
bicycle. The algorithm we developed achieved 98% accuracy in fall detection
and 98.5% accuracy in detection of fall direction. This study performed
simulations indoors for the sake of subjects’ safety; however, we expect to
produce the research in an environment more similar to real-life situations. In
future, it is also possible that the developed system will be applied to an
emergency reporting system for bicycle falls.
Keywords: Fall Detection, Bike Riding, Inertial Sensor, Helmet.

1.

Introduction

Bicycles are an economical and eco-friendly means of transportation and are used
widely for commuting. As the amount of spare time increases and interest in health
intensifies, more people enjoy riding bicycles for leisure [1, 2]. When people fall
during bicycle riding, they may sustain injuries ranging from bruises to bone fractures
and, in the worst case, even brain injuries. For the elderly, the risk may be much
higher. As a result, people must wear helmets when they ride bicycles.

59

resulting in a much stronger shock. tri-axial accelerometer. Falls are detected using peak values of tri-axial acceleration signals and a system was set up to call for help on short notice through short message service (SMS) when falls occur. Hwang et al. Thus. Because people move less frequently after taking a fall. We designed an algorithm of fall detection by fixing on a leisure bike helmet a sensor module in which a tri-axial gyroscope. due to which accurate angle would not be obtained. and a tri-axial magnetometer. Along with fall detection. this study developed a system of fall detection during bike riding rather than falls during ADL. They designed a specific algorithm based on the integration of angle and speed data. and tri-axial magnetometer were installed. leftward falls. The algorithm of fall detection was applied by calculating the convergence of acceleration signals emitted by the sensor module and the vector signals of the rotation angles of quaternions. fall direction was identified by analyzing vector signals of rotation angle. Nyan et al. Bourke et al. If the average value of the tilt sensor exceeded the first threshold. The velocity of a forward-moving bike compounds the velocity of a fall. Moreover. developed an algorithm of fall detection using a tri-axial accelerometer. it activated a timer and a 10 s countdown was initiated.1 Hardware system The sensor unit employed in the study consisted of a tri-axial gyroscope. Consequently. and a tiltmeter [4].There has already been considerable research conducted on the analysis of patterns of human motion in activities of daily living (ADL) and fall detection. However. conducted research to distinguish ADL from falls by measuring the pitch and roll of the body using a bi-axial gyroscope [5]. The abovementioned studies address falls in ADL but there has been no research on falls during bike rides. The experiment proceeded with forward falls. If the differential value exceeded the second threshold. with the subject sitting on the saddle of a bike indoors for the sake of the subject’s safety. while integrating the speed data. and each case of acceleration that differentiated each speed. and rightward falls. the event is deemed a fall if the differential value of acceleration after 10 s fails to exceed the third threshold. along with a 32-bit multipoint control 60 . Methods 2. research on fall detection during a bike ride is required. therefore. a tri-axial accelerometer. the differential value of acceleration signals was calculated. additional experiments were performed with speed bumps and warm-up exercises prior to riding a bike. in order to set the threshold to be used for the algorithm. 2. backward falls. attached a tri-axial accelerometer to subjects’ clothing at the shoulder and detected lifestyle patterns in the time frequency domain [3]. the danger of a fall during a bike ride is greater. The difference between the risk of falls in ADL and that during a bike ride is significant. the problem of drift occurs in which offsets are integrated. Furthermore. tri-axial gyroscope.

As the angle data on the vertical axis is unrelated with the fall. and right directions from a seated position on a 60 cm high bicycle saddle. The sensitivity of the gyroscope (L3G4200D. θ x . Experiment Protocol Five healthy male subjects (ages 20–28. The angle data used in this study were the rotation angle vectors ( θ x . Therefore. and Z. Fig. θ y . θ z are respectively equivalent to the rotations centering on X. STMicroelectronics) was ±2000 dps. 2. STMicroelectronics) was ±2. STMicroelectronics) was ±8 g. Y. In this study. by applying a low-pass filter with a cutoff frequency of 5 Hz to tri-axial acceleration signals ( a x . Because a (1) can change due to the shock from traversing a speed bump and the acceleration added from riding the bicycle. E2BOX. 24. a z ) for fall detection. Configuration of the sensor unit.3. the data on vertical axis angles were ruled out when calculating the tilt ( θ tilt ) (Eq. calculated as in Eq. All the experiments were repeated 10 times for each direction. Algorithm of Fall Detection This study used signal vector magnitude (SVM). Korea) (Fig. The sampling speed was 100 Hz. 61 .2. which were then converted from radians to degrees. θ y . (2)). Korea). a Bluetooth module was used (Parani ESD-200. that of the accelerometer (LSM303DLH. while wearing a helmet with the sensor module on the head. All of these components were built in to the sensor unit. a fall cannot be detected from a alone. 1).5 gauss. and that of the magnetometer (LSM303DLH. 1. Here. the subjects were induced to fall unintentionally and naturally by moving the mattress quickly using pneumatic pressure. left. a y . Sena. back. θ z ) of quaternions produced by the sensor unit. For wireless communication with the host PC. 2. EBIMU 9-DOF. placed on a mattress indoors for safety. a = ax 2 + a y 2 + az 2 .unit (MCU. (1). The subjects fell to the front.2 on average) participated in this experiment. additional analysis is performed on the tilt of the sensor.

but if it exceeds θ th . Likewise. the tilt of the sensor is analyzed. 2). the trial is identified as a speed bump or an ADL motion. and tri-axial magnetometer. installed on a helmet worn by the experimental subjects. Flow chart of the fall detection algorithm. it is identified as a fall during a bike ride. If the peak value of a value of θ tilt exceeds ath . If the peak does not exceed θ th . tri-axial gyroscope. 2. it is identified as a rightward fall. Fig. if ∆θ y is greater than ∆θ x and θ y is greater than 0. Parameter measurements were obtained from the convergence of readings generated by a sensor module with a built-in triaxial accelerometer. If ∆θ x is greater than ∆θ y and θ x is greater than 0. if the peak value of a does not exceed ath . ∆θ y ) of θ x and θ y after a fall has occurred. falls were not detected in the preliminary experiments involving riding on a 62 . First. it is identified as a backward fall. the trial is identified as a forward fall. RESULTS In this study. the experimental trial is classified as a normal ride. (2) The overall process of fall detection is as follows (Fig. Fall direction is detected by comparing the variations ( ∆θ x . we designed an algorithm to detect the occurrence and direction of falls based on the parameters a and θ tilt . and if θ y is smaller than 0. 3.θ tilt = θ x 2 + θ y 2 . it is identified as a leftward fall. and if θ x is smaller than 0. When the algorithm of fall detection was applied.

no fall was detected because θ tilt did not exceed θ th . the fall detection rate recorded was 98%. though a exceeded ath (Fig. the fall was detected because a and θ tilt exceeded ath and θ th .5% for fall direction (Table 1). Five experimental subjects executed a total of 200 falls comprising 10 trials in each direction. in order to verify the accuracy of detection of falls and fall direction. during warm-up exercises consisting of bending the upper body forward. When a fall occurred during a bike ride. As a result of applying the developed algorithm. left. Fig. 3(c)). traversing a speed bump. classified as front. back. (b) a (top) and θ tilt (bottom) when riding over a speed bump. 3(a)). and (d) a (top) and θ tilt (bottom) when a fall occurs. The algorithm also demonstrated detection capability of 98. In addition. (a) a (top) and θ tilt (bottom) when riding on a flat surface. and performing warm-up exercises. When riding on the flat surface. (c) a (top) and θ tilt (bottom) when performing warm-up exercises (bending the upper body forward). 63 .flat surface. 3(d)). no fall was detected because a and θ tilt did not exceed ath and θ th (Fig. respectively (Fig. and right. no fall was detected because θ tilt exceeded θ th but a did not exceed ath (Fig. starting from a seated position on a bicycle saddle. 3. 3(b)). and when traversing the speed bump. however.

San Francisco (2004) 5.. Thus.N.: Conf. Kim.E.. J. Appleton. Phys. Y. Maat. We developed an algorithm to detect the occurrence and direction of falls using signals of acceleration and rotation angle vector of quaternions. Kang. and triaxial magnetometer. K. 1059--1067 (2006) 4. tri-axial gyroscope. Accuracy of fall detection and fall direction detection. Eng.V. This study was performed indoors rather than on actual bike rides outdoors. Transportation Research Part D 16. Hwang.K. In future.H.. J. Transportation Research Part A 41. Bourke.H.Table 1. Attempts 200 Detections 196 Total (%) 98 200 197 98. Heinen. M.. J. Seah.W. K. Science and Technology (2011-0010715). Parameter readings are emitted by a sensor installed on the leisure helmet.M.. there is a need to conduct further experiments in environments more similar to real bicycle-riding conditions. M. References 1... Gatersleben. Acknowledgments: This work was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education.W.: Development of Novel Algorithm and Real-time Monitoring Ambulatory System Using Bluetooth Module for Fall Detection in the Elderly. Lyons.M. Jang. Med. F. Ser.M. 84--90 (2008) 64 . pp. A. B. the sensor installed on the helmet can be applied to a system in which the sensor reports an emergency by transmitting emergency signals to mobile devices when a fall occurs during a bike ride.C.Y. E. B. G. K.: A Threshold-based Fall-detection Algorithm Using a Bi-axial Gyroscope Sensor..: Contemplating Cycling to Work: Attitudes and Perceptions in Different Stages of Change. Tay.: Garment-based Detection of Falls and Activities of Daily Living using 3-axis MEMS Accelerometer.: The Role of Attitudes toward Characteristics of Bicycle Commuting on the Choice to Cycle to Work over Various Distances. containing a sensor module with a built-in tri-axial accelerometer. we developed a system to detect falls during bike rides while wearing a leisure helmet on the head. Manimaran. it demonstrated excellent detection capabilities for both. Phys. 34. Wee. and the detection of fall direction was determined based on the rotation angle vector. 102--109 (2011) 3. In: Proceeding of the 26th Annual International Conference of the IEEE EMBS. 302--312 (2007) 2. Fall detection Direction detection 4.5 CONCLUSIONS In this study. H. 30. IEEE Press. Nyan. 2204--2207. When fall and fall direction were detected during a bike ride by applying the developed algorithm.. Fall detection was achieved by judging the acceleration signal and the rotation angle vector.