• Journal of the Korean Society for Precision Engineering
• /
• v.32 no.12
• /
• pp.1065-1072
• /
• 2015

This paper is about the development of an insole sensor system that can determine the model of an exoskeleton robot for lower limb that is a multi-degree of freedom system. First, the study analyzed the kinematic model of an exoskeleton robot for the lower limb that changes according to the gait phase detection of a human. Based on the ground reaction force (GRF), which is generated when walking, to proceed with insole sensor development, the sensing type, location, and the number of sensors were selected. The center of pressure (COP) of the human foot was understood first, prior to the development of algorithm. Using the COP, an algorithm was developed that is capable of detecting the gait phase with small number of sensors. An experiment at 3 km/h speed was conducted on the developed sensor system to evaluate the developed insole sensor system and the gait phase detection algorithm.

• Journal of Korea Multimedia Society
• /
• v.11 no.6
• /
• pp.787-795
• /
• 2008

Human recognition on camera is an interesting topic in computer vision. While fingerprint and face recognition have been become common, gait is considered as a new biometric feature for distance recognition. In this paper, we propose a gait recognition algorithm based on the knee angle, 2 feet distance, walking velocity and head direction of a person who appear in camera view on one gait cycle. The background subtraction method firstly use for binary moving object extraction and then base on it we continue detect the leg region, head region and get gait features (leg angle, leg swing amplitude). Another feature, walking speed, also can be detected after a gait cycle finished. And then, we compute the errors between calculated features and stored features for recognition. This method gives good results when we performed testing using indoor and outdoor landscape in both lateral, oblique view.

• Journal of Information Processing Systems
• /
• v.15 no.4
• /
• pp.957-966
• /
• 2019

This paper studies a novel approach to natural gait cycles based gait recognition via kernel Fisher discriminant analysis (KFDA), which can effectively calculate the features from gait sequences and accelerate the recognition process. The proposed approach firstly extracts the gait silhouettes through moving object detection and segmentation from each gait videos. Secondly, gait energy images (GEIs) are calculated for each gait videos, and used as gait features. Thirdly, KFDA method is used to refine the extracted gait features, and low-dimensional feature vectors for each gait videos can be got. The last is the nearest neighbor classifier is applied to classify. The proposed method is evaluated on the CASIA and USF gait databases, and the results show that our proposed algorithm can get better recognition effect than other existing algorithms.

• Journal of Biomedical Engineering Research
• /
• v.30 no.6
• /
• pp.516-520
• /
• 2009

The purpose of this study is to determine optimal filtering condition and threshold for the detection of gait-cycles for various walkway slopes as well as gait velocities. Ten young healthy subjects with accelerometer system on thigh and ankle walked on a treadmill at 9 conditions (three speeds and three slopes) for 5 minutes. Two direction signals, i.e. anterior-posterior (AP) and superior-inferior (SI) directions, of each sensor (four sensor orientations) were used to detect specific events of gait cycle. Variation of the threshold (from -1G to 1G) and lowpass cutoff frequency (fc) were applied to the event detection and their performance was evaluated according to the error index (EI), which was defined as the combination of the accuracy and false positive rate. Optimal fc and threshold were determined for each slope in terms of the EI. The optimal fc, threshold and their corresponding EI depended much on the walkway slope so that their coefficients of variation (CV) ranged 19~120%. When all data for 3 slopes were used in the identification of optimal conditions for each sensor, the best error indices for all sensor orientations were comparable ranging 1.43~1.76%, but the optimal fc and threshold depended much on the sensor position. The result indicates that the gait-cycle detection robust to walkway slope is possible by threshold method with well-defined filtering condition and threshold.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2008.11a
• /
• pp.649-650
• /
• 2008

• ETRI Journal
• /
• v.33 no.2
• /
• pp.259-266
• /
• 2011

We present a new method for an automated markerless system to describe, analyze, and classify human gait motion. The automated system consists of three stages: I) detection and extraction of the moving human body and its contour from image sequences, ii) extraction of gait figures by the joint angles and body points, and iii) analysis of motion parameters and feature extraction for classifying human gait. A sequential set of 2D stick figures is used to represent the human gait motion, and the features based on motion parameters are determined from the sequence of extracted gait figures. Then, a k-nearest neighbor classifier is used to classify the gait patterns. In experiments, this provides an alternative estimate of biomechanical parameters on a large population of subjects, suggesting that the estimate of variance by marker-based techniques appeared generous. This is a very effective and well-defined representation method for analyzing the gait motion. As such, the markerless approach confirms uniqueness of the gait as earlier studies and encourages further development along these lines.

• Korean Journal of Applied Biomechanics
• /
• v.21 no.4
• /
• pp.495-501
• /
• 2011

The purpose of this study was to develop the inertial sensor module system to detect gait event using single angular rate sensor(gyroscope), and evaluate the accuracy of this system. This sensor module is attached at the heel and gait events such as heel strike, foot flat, heel off, toe off are detected by using proposed automatic event detection algorithm. The developed algorithm detect characteristics of pitch data of the gyroscope to find gait event. To evaluate the accuracy of system, 3D motion capture system was used and synchronized with sensor module system for comparison of gait event timings. In experiment, 6 subjects performed 5 trials level walking with 3 different conditions such as slow, preferred and fast. Results showed that gait event timings by sensor module system are similar to that by kinematic data, because maximum absolute errors were under 37.4msec regardless of gait velocity. Therefore, this system can be used to detect gait events. Although this system has advantages of small, light weight, long-term monitoring and high accuracy, it is necessary to improve the system to get other gait information such as gait velocity, stride length, step width and joint angles.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.5
• /
• pp.990-992
• /
• 2007

The purpose of this study is to develop a practical gait-event detection system which is necessary for the FES (functional electrical stimulation) control of locomotion in paralyzed patients. The system is comprised of a sensor board and an event recognition algorithm. We focused on the practicality improvement of the system through 1) using accelerometer to get the angle of shank and dispensing with the foot-switches having limitation in indoor or barefoot usage and 2) using a rule-base instead of threshold to determine the heel-off/heel-strike events corresponding the stimulation on/off timing. The sensor signals are transmitted through RF communication and gait-events was detected using the peaks in shank angle. The system could detect two critical gait-events in all five paralyzed patients. The standard deviation of the gait events time from the peaks were smaller when 1.5Hz cutoff frequency was used in the derivation of the shank angle from the acceleration signals.

• Journal of information and communication convergence engineering
• /
• v.15 no.4
• /
• pp.244-249
• /
• 2017

Wearable sensor-based gait analysis has been widely conducted to analyze various aspects of human ambulation abilities under the free-living condition. However, there have been few research efforts on using wearable sensors to analyze human walking on an unstable surface such as on a ship during a sea voyage. Since the motion of a ship on the unstable sea surface imposes significant differences in walking strategies, investigation is suggested to find better performing wearable sensor-based gait analysis algorithms on this unstable environment. This study aimed to compare two representative gait event algorithms including time domain and frequency domain analyses for detecting heel strike on an unstable platform. As results, although two methods did not miss any heel strike, the frequency domain analysis method perform better when comparing heel strike timing. The finding suggests that the frequency analysis is recommended to efficiently detect gait event in the unstable walking environment.

• Journal of Korea Multimedia Society
• /
• v.11 no.12
• /
• pp.1676-1687
• /
• 2008

In this paper, we proposed a new multi-view human recognition method based on face and gait features detection algorithm. For getting the position of moving object, we used the different of two consecutive frames. And then, base on the extracted object, the first important characteristic, walking direction, will be determined by using the contour of head and shoulder region. If this individual appears in camera with frontal direction, we will use the face features for recognition. The face detection technique is based on the combination of skin color and Haar-like feature whereas eigen-images and PCA are used in the recognition stage. In the other case, if the walking direction is frontal view, gait features will be used. To evaluate the effect of this proposed and compare with another method, we also present some simulation results which are performed in indoor and outdoor environment. Experimental result shows that the proposed algorithm has better recognition efficiency than the conventional sing]e view recognition method.