• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.65 no.2
• /
• pp.130-135
• /
• 2016

Gait recognition has advantage of non-contact type recognition. But It has disadvantage of low recognition rate when the pedestrian silhouette is changed due to bag or coat. In this paper, we proposed new method using combination of gait energy image feature and thermal face image feature. First, we extracted a face image which has optimal focusing value using human body rate and Tenengrad algorithm. Second step, we extracted features from gait energy image and thermal face image using linear discriminant analysis. Third, calculate euclidean distance between train data and test data, and optimize weights using genetic algorithm. Finally, we compute classification using nearest neighbor classification algorithm. So the proposed method shows a better result than the conventional method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.1
• /
• pp.6-11
• /
• 2011

In this paper, we propose a gait-based human identification system using eigenfeature regularization and extraction (ERE). First, a gait feature for human identification which is called gait energy image (GEI) is generated from walking sequences acquired from a camera sensor. In training phase, regularized transformation matrix is obtained by applying ERE to the gallery GEI dataset, and the gallery GEI dataset is projected onto the eigenspace to obtain galley features. In testing phase, the probe GEI dataset is projected onto the eigenspace created in training phase and determine the identity by using a nearest neighbor classifier. Experiments are carried out on the CASIA gait dataset A to evaluate the performance of the proposed system. Experimental results show that the proposed system is better than previous works in terms of correct classification rate.

• Korean Journal of Applied Biomechanics
• /
• v.20 no.4
• /
• pp.387-393
• /
• 2010

The purpose of this study was to compare pregnant women's gait parameters and mechanical energies caused by changes in hormone levels and anatomical features such as body mass, body-mass distribution, joint laxity, and musculo-tendinous strength from pregnancy to postpartum. Ten subjects (height: $161{\pm}6.5cm$, mass: $62.7{\pm}10.4\;kg$, $66.4{\pm}9.3\;kg$, $68.4{\pm}7.7\;kg$, $57.2{\pm}7.7\;kg$) participated in the four times experiments (the first, middle, last term and after birth) and walked ten trials at a self-selected pace without shoes. The gait motions were captured with Qualisys system and gait parameters were calculated with Visual-3D. Pregnant women's gait velocities were decreased during the pregnancy periods, but increased after birth. Stride width and cycle time were increased during pregnancy, but decreased after birth. Thigh energy (77.4%) was greater than shank energy (19.06%) or feet (3.54%) about total energy of the lower limbs. Their feet (Left R2=0.881, Right R2=0.852) and shank (Left R2=0.318, Right R2=0.226) energies were significantly increased (positive correlation), but double limb stance time (DLST, R2=0.679) and body total energy (R2=0.138) were decreased (negative correlation) for their velocities. These differences suggest that thigh segment may be a dominant segment among lower limbs, and have something to do with gait velocities. Further studies should investigate joint power and joint work to find energy dissipation or absorption from pregnancy period to postpartum.

• Science of Emotion and Sensibility
• /
• v.6 no.4
• /
• pp.25-32
• /
• 2003

This paper suggests the evaluation method of gait analysis in measurements obtained using the "Foot Scanner" and "Foot Analyzer" system. Previous examination method with the unaided eye on the sole of the foot and analysis method of pressure distribution in gait have been discussed by many researchers. Also they have concerned with pressure curve, COP(center of pressure) trace, and velocity in COP. However experiment results depend on test environment and conditions of subjects. Consequently we need to regard the special energy parameter for solving the problem. The kinetic energy and impulse parameter can be used as parameters of gait analysis. The results of this study confirmed the validity of presented of the parameters through the experiment with eight subjects.

• The Journal of Korea Robotics Society
• /
• v.8 no.1
• /
• pp.8-19
• /
• 2013

One of the important issues for structural and electrical specifications in developing a robot is to determine lengths of links and motor specifications, which need to be appropriate to the purpose of robot. These issues become more critical for a gait rehabilitation robot, since a patient wears the robot. Prior to developing an entire gait rehabilitation robot, designing of a 1DOF assistive knee joint of the robot is considered in this paper. Human gait motions were used to determine an allowable range of knee joint that was rotated with a linear type actuator (ball-screw type) and links. The lengths of each link were determined by using an optimization process, minimizing the stroke of actuator and the total energy (kinetic and potential energy). Kinetic analysis was performed in order to determine maximum rotational speed and maximum torque of the motor for tracking gait trajectory properly. The prototype of 1 DOF assistive knee joint was built and examined with a impedance controller.

• Journal of the Korean Society for Precision Engineering
• /
• v.29 no.3
• /
• pp.346-353
• /
• 2012

The purpose of this study is to verify the energy efficiency of the integrated system combining human and a lower extremity exoskeleton robot when it is applied to the proposed gait pattern. Energy efficient gait pattern of the lower limb was proposed through leg function distribution during stance phase and the dynamic-manipulability ellipsoid (DME). To verify the feasibility and effect of the redefined gait trajectory, simulations and experiments were conducted under the conditions of walking on level ground and ascending and descending from a staircase. Experiments to calculate the metabolic cost of the human body with or without the assistance of the exoskeleton were conducted. The energy consumption of the lower extremity exoskeleton was assessed, with the aim of improving the efficiency of the integrated system.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.9
• /
• pp.959-966
• /
• 2009

An essential consideration when analyzing the gait of walking robots is their ability to maintain stability during walking. Therefore, this study proposes a vertical waist-jointed walking robot and gait algorithm to increase the gait stability margin while walking on the slope. First, the energy stability margin is compared according to the posture of the walking motion on slope. Next, a vertical waist-jointed walking robot is modeled to analyze the stability margin in given assumption. We describe new parameters, joint angle and position of a vertical waist-joint to get COG (center of gravity of a body) in walking. Finally, we prove the superiority of the proposed gait algorithm using simulation and conclude the results.

• Journal of Korean Physical Therapy Science
• /
• v.7 no.1
• /
• pp.285-294
• /
• 2000

80 persons who don't have past history of cardiopulmonary and neuromuscular disease. The results were as follow; 1. PCI(Physiological Cost Index) value without loading to ankle were significantly increased compared to 1kg, and 2kg (p<0.01). 2. Female Subjects showed more increased PCI value in without loading and lkg, 2kg loading compared to male subjects (p<0.01). 3. In every PCI condition the difference among height groups was observed (p<0.01). 4. The difference among weight groups in each PCI condition was observed (p<0.01). These results showed that energy consumption was increased according to loading on the ankle during gait so weight of orthosis or prosthesis must be considered when choosing them and during gait training with these ones.

• Journal of Information Processing Systems
• /
• v.14 no.4
• /
• pp.892-903
• /
• 2018

The paper proposes a novel gait recognition algorithm based on feature fusion of gait energy image (GEI) dynamic region and Gabor, which consists of four steps. First, the gait contour images are extracted through the object detection, binarization and morphological process. Secondly, features of GEI at different angles and Gabor features with multiple orientations are extracted from the dynamic part of GEI, respectively. Then averaging method is adopted to fuse features of GEI dynamic region with features of Gabor wavelets on feature layer and the feature space dimension is reduced by an improved Kernel Principal Component Analysis (KPCA). Finally, the vectors of feature fusion are input into the support vector machine (SVM) based on multi classification to realize the classification and recognition of gait. The primary contributions of the paper are: a novel gait recognition algorithm based on based on feature fusion of GEI and Gabor is proposed; an improved KPCA method is used to reduce the feature matrix dimension; a SVM is employed to identify the gait sequences. The experimental results suggest that the proposed algorithm yields over 90% of correct classification rate, which testify that the method can identify better different human gait and get better recognized effect than other existing algorithms.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.6
• /
• pp.1247-1252
• /
• 2005

Though a legged robot has a high terrain adaptability as compared with a wheeled robot, its moving speed is considerably low in general. For attaining a high moving speed with a logged robot, a dynamically stable walking is a promising solution. However, the energy efficiency of a dynamically stable walking is generally lower than the efficiency of a stable gait such as a crawl gait. In this paper, energy consumption of two walking patterns for a trot gait is simulated through modeling a quadruped walking robot named TITAN-VIII.