• Proceedings of the KAIS Fall Conference
• /
• 2010.11a
• /
• pp.251-254
• /
• 2010

게이트는 사람의 걸음걸이 특성을 나타내는 용어로, 게이트 인식의 경우 원 거리에서 획득한 정보만으로도 개개인을 인지할 수 있는 장점을 갖고 있다. 지문 인식이나 홍채 인식과 같은 기존의 생체 인식 방법은 사용자로 하여금 정보 제공을 위해 직접적인 접촉이나 근접 촬영 등 불편한 행위가 수반되어야 하는 반면, 게이트 인식은 이와 같은 단점이 없기 때문에 새로운 생체 인식 방법으로 많은 연구가 진행되고 있다. 그러나 게이트 인식의 경우 한 개인 간에도 내외부적인 요인에 의한 변화가 크기때문에 단순한 형태 특징만으로는 높은 인식 성능을 기대하기가 어렵다. 본 논문에서는 게이트 인식을 위해 단순한 형태 특징이 아닌 게이트 영상 시퀀스의 움직임에 대한 정보를 이용하기 위한 방안을 제안하고자 한다. 이를 위해 Shape Sequence를 도입하고 게이트 인식에 적용할 수 있는 방법을 제시한다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.6
• /
• pp.1233-1242
• /
• 2017

Various attempts have been made to prevent crime risk. One of the cases where outdoor pedestrians are attacked by criminals is the abnormal health condition. When a mental or mental condition that can not sustain normal walking due to drunkenness is exposed, the case of being a crime is revealed through crime case analysis. In this study, we propose a method for estimating the state of an individual that can be detected in outdoor activities. In order to avoid the inconvenience of installing a separate terminal for event information transmission of sensors and sensors, it is possible to estimate an abnormal state by using a 3-axis acceleration sensor built in a smart phone. The state of the user can be estimated by analyzing the momentum of the user and analyzing it with the passage of time. It is possible to distinguish the flow of time at regular intervals, to recognize the activity patterns in each time band, and to distinguish between normal and abnormal. In this study, we have evaluated the total amount of kinetic energy and kinetic energy in each direction of the acceleration sensor and the Fourier transformed value of the total energy amount to distinguish the abnormal state.

• Journal of IKEEE
• /
• v.24 no.1
• /
• pp.9-18
• /
• 2020

The pattern recognition or fuzzy inference, which is mainly used for the development of the automatic walking mode change of the above knee prosthesis, has a disadvantage in that it is difficult to estimate with the immediate change of the walking environment. In order to solve a disadvantage, this paper developed an algorithm that automatically converts the walking mode of the next step by estimating the walking environment at a specific gait phase. Since the proposed algorithm should be implanted and operated in the microcontroller, it is developed using the random forest base in consideration of calculation amount and estimated time. The developed random forest based gait and environmental estimation model were implanted in the microcontroller and evaluated for validity.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.35-42
• /
• 2021

In this paper, we propose a deep learning-based person re-identification method using a three-dimensional RGB-Depth Xtion2 camera considering joint coordinates and dynamic features(velocity, acceleration). The main idea of the proposed identification methodology is to easily extract gait data such as joint coordinates, dynamic features with an RGB-D camera and automatically identify gait patterns through a self-designed one-dimensional convolutional neural network classifier(1D-ConvNet). The accuracy was measured based on the F1 Score, and the influence was measured by comparing the accuracy with the classifier model (JC) that did not consider dynamic characteristics. As a result, our proposed classifier model in the case of considering the dynamic characteristics(JCSpeed) showed about 8% higher F1-Score than JC.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.2
• /
• pp.237-244
• /
• 2016

There are two destinations to aware the risk of common life. Recognition of the condition of pedestrian's own and the environmental factor awareness both are beneficial for risk awareness. It is good way of advancing the crime prevention effectivity that including IoT technology at the crime prevention research. The purpose of this research is that advanced way of crime prevention with multi-sensor data fusion of the condition of pedestrian and environmental factors. The 3-axis acceleration sensor is available to recognize the gait and the illumination sensor also useful to infer the road state. This research suggest a novel way of assess these factors and the result is the degree of danger.

• Journal of mucopolysaccharidosis and rare diseases
• /
• v.2 no.1
• /
• pp.5-7
• /
• 2016

Mucolipidoses II and III alpha/beta (ML II and ML III) are lysosomal disorders in which the essential mannose-6-phosphate recognition marker is not synthesized onto lysosomal hydrolases and other glycoproteins. The disorders are caused by mutations in GNPTAB, which encodes two of three subunits of the heterohexameric enzyme, N-acetylglucosamine-1-phosphotransferase ML II, recognizable at birth, often causes intrauterine growth impairment and sometimes the prenatal "Pacman" dysplasia. The main postnatal manifestations of ML II include gradual coarsening of neonatally evident craniofacial features, early cessation of statural growth and neuromotor development, dysostosis multiplex and major morbidity by hardening of soft connective tissue about the joints and in the cardiac valves. Fatal outcome occurs often before or in early childhood. ML III with clinical onset rarely detectable before three years of age, progresses slowly with gradual coarsening of the facial features, growth deficiency, dysostosis multiplex, restriction of movement in all joints before or from adolescence, painful gait impairment by prominent hip disease. Cognitive handicap remains minor or absent even in the adult, often wheelchair-bound patient with variable though significantly reduced life expectancy. As yet, there is no cure for individuals affected by these diseases. So, clinical manifestations and conservative treatment is important. This review aimed to highlight the extra-skeletal clinical problems in ML II and III.

• Journal of Information Processing Systems
• /
• v.14 no.5
• /
• pp.1114-1135
• /
• 2018

A multiple classification system based on a new boosting technique has been approached utilizing different biometric traits, that is, color face, iris and eye along with fingerprints of right and left hands, handwriting, palm-print, gait (silhouettes) and wrist-vein for person authentication. The images of different biometric traits were taken from different standard databases such as FEI, UTIRIS, CASIA, IAM and CIE. This system is comprised of three different super-classifiers to individually perform person identification. The individual classifiers corresponding to each super-classifier in their turn identify different biometric features and their conclusions are integrated together in their respective super-classifiers. The decisions from individual super-classifiers are integrated together through a mega-super-classifier to perform the final conclusion using programming based boosting. The mega-super-classifier system using different super-classifiers in a compact form is more reliable than single classifier or even single super-classifier system. The system has been evaluated with accuracy, precision, recall and F-score metrics through holdout method and confusion matrix for each of the single classifiers, super-classifiers and finally the mega-super-classifier. The different performance evaluations are appreciable. Also the learning and the recognition time is fairly reasonable. Thereby making the system is efficient and effective.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05a
• /
• pp.691-694
• /
• 2003

게이트는 사람의 걷는 방법 혹은 그 특성을 나타내는 용어로써, 최근 컴퓨터 비젼 기술을 이용하여 개개인을 분별하기 위한 게이트 특징 정보를 추출하고자 하는 연구가 활발히 진행되고 있다. 그러나 영상을 기반으로 추출한 게이트 정보는 카메라의 시점에 종속적인 단점을 가지고 있다. 이러한 단점을 해결하기 위한 노력으로 3차원 정보를 획득하려는 연구가 진행되고 있으나 이는 카메라와 사람간의 거리, 카메라 파라미터 등 부가적인 정보를 필요로 한다. 본 논문에서는 영상내의 정보만을 이용하여, 카메라 시점에 종속적인 게이트 인식의 단점을 해결할 수 있는 방안을 제안한다. 먼저 실루엣 영상으로부터 걷는 방향을 찾아내고, 간단한 연산을 통해 평면 호모그래피를 추정한다. 추정된 호모그래피를 이용하여 측면 시점의 영상으로 재구성하면, 시점 변화에 비종속적인 게이트 정보를 추출할 수 있다. 본 논문에서 제안한 방법을 평가하기 위하여 실추엣 영상의 폭과 높이 변화를 비교하였다 실험을 통해 제안한 방법을 적용할 경우, 그렇지 않은 경우에 비하여 특징 변화가 적음을 확인하였고, 특히 보폭 통의 게이트 특징 정보가 일정한 값을 유지함을 볼 수 있었다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.6C
• /
• pp.593-603
• /
• 2009

In this paper, we propose a new integrated computer vision system designed to track multiple human beings and extract their silhouette with an active stereo camera. The proposed system consists of three modules: detection, tracking and silhouette extraction. Detection was performed by camera ego-motion compensation and disparity segmentation. For tracking, we present an efficient mean shift based tracking method in which the tracking objects are characterized as disparity weighted color histograms. The silhouette was obtained by two-step segmentation. A trimap is estimated in advance and then this was effectively incorporated into the graph cut framework for fine segmentation. The proposed system was evaluated with respect to ground truth data and it was shown to detect and track multiple people very well and also produce high quality silhouettes. The proposed system can assist in gesture and gait recognition in field of Human-Robot Interaction (HRI).

• Journal of Internet Computing and Services
• /
• v.12 no.3
• /
• pp.17-26
• /
• 2011

We have developed a wearable device that can convert sensor data into real-time step counts. Sensor data on gait were acquired using a triaxial accelerometer. A test was performed according to a test protocol for different walking speeds, e.g., slow walking, walking, fast walking, slow running, running, and fast running. Each test was carried out for 36 min on a treadmill with the participant wearing an Actical device, and the device developed in this study. The signal vector magnitude (SVM) was used to process the X, Y, and Z values output by the triaxial accelerometer into one representative value. In addition, for accurate step-count detection, we used three algorithms: an heuristic algorithm (HA), the adaptive threshold algorithm (ATA), and the adaptive locking period algorithm (ALPA). The recognition rate of our algorithm was 97.34% better than that of the Actical device(91.74%) by 5.6%.