• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1883-1886
• /
• 2003

Gait is defined as "a manor of walking". It can used as a biometric measure to recognize known persons. Gait is an idiosyncratic feature determined by an individual's weight, stride length, and posture combined with characteristic motion. but its feature extracted from images varies with the viewpoint. In this paper, we propose a gait recognition method using a planer homography, which is robust for viewpoint variation. We represent an individual as key-silhouettes. And we endow key-silhouettes with weight calculated using the characteristic of PCA. Experimental result shows that proposed method is robust for viewpoint variation as images synthesised same viewpoint.

• Journal of the Ergonomics Society of Korea
• /
• v.10 no.2
• /
• pp.15-22
• /
• 1991

Gait analysis techniques are widely used in Europe and the United States to investigate the loosening problems of total joint implantation and to improve the technologies in designing prosthetic devices. In Korea, however, the gait data are rarely found. Recently, as the standards of living become improved, the number of lower extremity operation patients increase rapidly. Therefore, a study on the gait characteristic parameters for Koreans is of great importance. In this study, time-distance gait parameters and ground reaction fore are analyzed using a FOANAS system developed by Pohang Institute of Science and technology (POSTECH). Gait parameters of Korean normal adults were preceded and comparisons were made for the distinction of sex and age.

• Journal of Korean Institute of Industrial Engineers
• /
• v.17 no.2
• /
• pp.39-50
• /
• 1991

The movement of human beings - walking, running, jumping and climbing, etc. - have long been of scientific interest. In particular, the science of human walking is called gait analysis. Various instruments have been developed to assist in the study of human gait. Recently gait analysis techniques are used in medical research to investigate the abnormalities of pathological gait. In this study, we constructed a comprehensive gait analysis system consisting of a walkway, a force platform, foot-switches and an ExpertVision motion analysis system. Time-distance gait parameters and vector diagrams can be analyzed by a special application program called Force Analysis System(FOANAS). Using quantitative discrimination of this system, the gait characteristic parameters of normal and pathological gait is facilitated.

• The Journal of Korean Physical Therapy
• /
• v.34 no.6
• /
• pp.326-331
• /
• 2022

Purpose: The stroke patients have gait dysfunction due to impaired neural tracts; corticospinal tract (CST), corticoreticular pathway (CRP), and vestibulospinal tract (VST). In this study, we investigated characteristics of gait pattern according to the injury aspect of the neural track in a stroke patient. Methods: One patient and six control subjects of similar age participated. A 19-year-old male patient with spontaneous intracerebral hemorrhage on right basal ganglia, thalamus, corona radiata and cerebral cortex due to arteriovenous malformation rupture. Diffusion tensor imaging (DTI) data was acquired 21 months after the stroke. Kinematic and spatio-temporal parameters of gait were collected using a three-dimensional gait analysis system. Results: On 21 months DTI, the CST and CRP in affected hemisphere showed severe injury, in contrast, the VST in affected hemisphere showed intact integrity. Result of gait analysis, walking distance and speed were significantly decreased in a patient. The stance rate of unaffected lower limb, the swing rate of affected lower limb and the duration of double stance significantly increased compared with normal control. The knee and hip joint angle were significantly decreased in a patient. Conclusion: We found recovered independent gait ability may be associated with unimpaired VST in a patient with severe injury in CST and CRP.

• Proceedings of the KOSOMBE Conference
• /
• v.1992 no.05
• /
• pp.203-208
• /
• 1992

In order to restore the gait function by functional electrical stimulation(FES) in hemiplegic patients, an electrical stimulator and foot sensor were developed on the basis of optimal parameters which resulted from animal experiments. Physical properties of the soleus muscle were quite different from those of themedial gastrocnemius muscle, that is, the former had a characteristic or slow muscle and the letter had a characteristic of fast muscle in rats. Optimal parameters for electrical stimulation were 0.2ms of pulse width and 20Hz of frequency in the soleus muscle and 0.3ms, 40Hz in the medial gastrocnemius muscle. Amplitude modulated electrical stimulator with -15V of maximal output was made and automatic on-off time if the stimulator was 5 seconds. The foot sensor composed of 3 sensors in 3 pressure points of the foot was made in order to control the gai t function by closed loop feedback system. The gait function was improved by using the stimulator and foot sensor in peroneal palsy. These results suggest that the electrical stimulator with closed loop feedback system may restore the gait function in hemiplegic patients.

• The Journal of Korean Physical Therapy
• /
• v.30 no.2
• /
• pp.73-77
• /
• 2018

Purpose: The prefrontal lobe, supplementary motor area, cerebellum, and basal ganglia are activated during gait. In addition, gait is controlled by nerves, such as the corticospinal tract (CST) and corticoreticular pathway (CRP). In this study, the presence of an injury to the CST and CRP was identified by diffusion tensor imaging and the characteristics of the gait pattern were investigated according to inferior cerebral artery infarction. Methods: One patient and six control subjects of a similar age participated. A 69-year-old female patient had an injury to the left basal ganglia, insular gyrus, corona radiata, dorsolateral prefrontal cortex, and postcentral gyrus due to an inferior cerebral artery infarction. Diffusion tensor imaging (DTI) data was acquired 4 weeks after the stroke. The kinematic and spatio-temporal parameters of gait were collected using a three-dimensional gait analysis system. Results: On 4 weeks DTI, the CST and CRP in the affected hemisphere did not show injury to the affected and unaffected hemisphere. Gait analysis showed that the cadence of spatio-temporal parameter was decreased significantly in the patient. The angle of the knee joint was decreased significantly in the affected and unaffected sides compared to the control group. Conclusion: The results of diffusion tensor imaging showed that although the patient was evaluated to be capable of an independent gait, the quality and quantity of gait might be reduced. This study could help better understand the gait ability analysis of stroke patients and the abnormal gait pattern of patients with a brain injury.

• The Journal of the Korea Contents Association
• /
• v.6 no.1
• /
• pp.31-40
• /
• 2006

In this paper, we propose a gait recognition method based on gait silhouette sequences. Features of gait are affected by the variation of gait direction. Therefore, we synthesize silhouettes to canonical form by using planar homography in order to reduce the effect of the variation of gait direction. The planar homography is estimated with only the information which exist within the gait sequences without complicate operations such as camera calibration. Even though gait silhouettes are generated from an individual person, fragments beyond common characteristics exist because of errors caused by inaccuracy of background subtraction algorithm. In this paper, we use the Principal Component Analysis to analyze the deviated characteristics of each individual person. PCA used in this paper, however, is not same as the traditional strategy used in pattern classification. We use PCA as a criterion to analyze the amount of deviation from common characteristic. Experimental results show that the proposed method is robust to the variation of gait direction and improves separability of test-data groups.

• Journal of the Korean Society for Precision Engineering
• /
• v.22 no.5 s.170
• /
• pp.197-204
• /
• 2005

In this study, ground reaction force(GRF), absolute symmetry index(ASI) and coefficient of variation(CV) of fixed, single-axis and multi-axis prosthetic ankle assemblies were investigated to show the biomechanical evaluation for above knee amputees. In the experiments, 37 normal male volunteers, two male and two female AK amputees were tested with fixed, single-axis and multi-axis prosthetic ankle assembly. A gait analysis was carried out to derive the ratio of GRF to weight as the percentage of total stance phase for ten points. The results showed that fixed-axis ankle was superior to the other two ankle assemblies for the characteristic of forwarding and breaking forces. Multi-axis ankle was relatively superior to the other two ankle assemblies for gait balancing and movement of the center for mass. single-axis ankle was relatively superior to the other two ankle assemblies for CV and ASI of GRF.

• The Journal of Korean Physical Therapy
• /
• v.21 no.1
• /
• pp.89-96
• /
• 2009

Purpose: The purpose of this study was to determine the effect of modified golf swing training on gait characteristic in hemiplegic patient through Kwon 3D motion analysis system. Methods: This study has performed single subject design from September to October 2008. The subject had left hemiplegia due to CVA in December 2003. He has treated Bobath approach twice a week. In order to increase ankle dorsiflexion and knee flexion, the subject has applied modified golf swing training on the basis of Bobath approach. The measurement of gait characteristic was taken by Kwon 3D motion analysis system. Results: The results were as follows : 1) Walking velocity was increased 0.62m/sec than before the training. 2) Step length was increased 0.09m than before the training. 3) Left ankle and hip angle were increased, but left knee angle was decreased. Conclusion: It could be concluded that the activity modified golf swing training in walking pattern contributed to improve the movement quality and speed of gait.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.15-18
• /
• 2007

Identification of humans from multiple view points is an important task for surveillance and security purposes. For optimal performance the system should use the maximum information available from sensors. Multimodal biometric systems are capable of utilizing more than one physiological or behavioral characteristic for enrollment, verification, or identification. Since gait alone is not yet established as a very distinctive feature, this paper presents an approach to fuse face and gait for identification. In this paper we will use the single camera case i.e. both the face and gait recognition is done using the same set of images captured by a single camera. The aim of this paper is to improve the performance of the system by utilizing the maximum amount of information available in the images. Fusion is considered at decision level. The proposed algorithm is tested on the NLPR database.