• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.2
• /
• pp.215-222
• /
• 2016

Research on gait recognition and its use is actively underway. This study suggests a method to recognize abnormal gaits of pedestrians. The purposes of the existing research to recognize normal steps are to measure physical activities and to validate people by their walks, but the purpose to recognize abnormal steps in this study is to insure the safe life of pedestrians. There are situations in which pedestrians are unaware of themselves vulnerable and can not ask for help. The purpose of this research is that even if pedestrians are unaware of themselves and there are no spontaneous requests for helps, it is intended for them to escape from dangers and difficulties by adopting the recent IOT technology. Hence, this study analyzes normal pace of pedestrians using the triaxial acceleration sensors, and takes ranges of their normal walking. And then, the steps of pedestrians are measured using the triaxial acceleration sensors, contrasted with their normal walking ranges, and determine whether their steps are normal or not. When it is out of the state for normal paces, a method to determine as abnormal paces is suggested.

• Journal of Digital Contents Society
• /
• v.12 no.3
• /
• pp.279-289
• /
• 2011

The latest hardware and software techniques are combined to give safe walking guidance and convenient service of realtime walking assistance system for visually impaired person. This system consists of obstacle detection and perception, place recognition, and sign recognition for pedestrian can safely walking to arrive at their destination. In this paper, we exploit the sign object detection system in subway station for sign recognition that one of the important factors of walking assistance system. This paper suggest the adaptive feature map that can be robustly extract the sign object region from complexed environment with light and noise. And recognize a sign using fast zernike moment features which is invariant under translation, rotation and scale of object during walking. We considered three types of signs as arrow, restroom, and exit number and perform the training and recognizing steps through adaboost classifier. The experimental results prove that our method can be suitable and stable for real-time system through yields on the average 87.16% stable detection rate and 20 frame/sec of operation time for three types of signs in 5000 images of sign database.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.519-521
• /
• 2019

자율주행 자동차에서의 보행자 인식 및 사람의 행동 인식과 같은 분야 등에 대한 연구들이 활발하게 진행되고 그에 기반을 둔 기술들이 많이 개발되고 있다. 그리고 대부분의 연구에서는 사람에 대한 경계 박스를 검출한다. 영상에서 사람의 유무 혹은 위치를 판단하는 문제에서는 경계 박스만을 검출하는 것이 효율적일 수 있으나 경계 박스는 행동 인식과 같은 분야에 사용하기에는 많은 정보의 손실이 발생할 수 있다. 본 논문에서는 U-NET 구조의 딥러닝 모델을 사용해 경계 박스로 인한 정보 손실을 줄일 수 있는 보행자 분할 방법을 제안한다. 모델의 학습을 위해 2017 COCO 데이터셋의 사람 카테고리를 사용하였으며 Penn-Fudan 보행자 데이터셋을 이용하여 제안 방법을 테스트하였으며 기존의 방법들과 비교하여 의미 있는 결과를 얻었다.

• Design Convergence Study
• /
• v.14 no.5
• /
• pp.157-169
• /
• 2015

In this study, three axillary crutches(Mobilegs, KM crutch, Pro In-motion) were tested with 12 healthy male subjects by measuring the EMG activity of the latissimus dorsi and gastrocnemius and the user-perceived levels focusing on the comfort and ease of use. The result showed that the EMG activity of the gastrocnemius was significantly reduced during ambulation using Mobilegs and Pro In-motion compared with the ambulation using KM crutch, a conventional crutch. However, no statistically significant difference was found for EMG activity of the latissimus dorsi. Subjects perceived the Mobilegs to be more comfortable and easy to use than the other crutches. Theses result may delivered mostly from the characteristics of spring-loaded axillary pad and ergonomic crutch handle. The results indicate that ambulation using the spring-loaded crutch is much easy with asking less exertion at gastrocnemius. In addition, the characteristics of crutch design, such as embedded spring, makes muscles to consume less energy. When the reasonable structure and form of the axillary pad and crutch handle are applied herein, the ambulation using the crutches are perceived to comfort.

• Proceedings of the KOR-KST Conference
• /
• 1998.10a
• /
• pp.42-51
• /
• 1998

안전한고 쾌적한 보행환경을 조성하여 보행 교통을 활성화시킨다면, 자동차의 사용이 줄게 되고 자동차의 유해한 배출가스로 인한 공기 오염 및 소음 등을 낮출 수 있을 뿐만 아니라 도심부의 미관 증대, 역사적 구역의 보존, 물리적인 도시 이미지 향상 등의 효과로 도심기능의 활성화에 기여할 수 있을 것이다. 이와 같은 보행통행의 중요성을 인식하여 안전하고 효율성 있는 보행동선을 조성할 필요가 있다. 그러나 상당수의 종합병원과 같은 공공성을 띤 건물들은 대부분의 보행자가 보행동선을 이용하여 건물에 접근하는데도 불구하고 차량을 중심으로 동선이 운영되고 있는 실정이다. 차량위주의 동선 체계는 보행 통행자로 하여금 차량통행으로의 전환을 유도할 가능성이 있어 이에 대한 대책이 필요하다. 본 연구는 분석대상으로 차량과 보행자에게 동등하게 접근의 용이성을 제공해야 하는 광주시의 4대 종합병원을 대상으로 보행자 집단에게 가해지는 저항이 구체적으로 얼마나 심각하며, 그 원인은 어떠한 물리적 조건에 의하여 발생하는지 알아 보았다. 보행저항을 파악하기 위한 지표로는 차량과 보행자의 충돌점의 수, 최단거리 선호도, 보행로 미확보율 등을 설정하여 분석하였다. 이러한 분석의 결과 나타난 문제점들을 해결하기 위한 방안도 함께 모색하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.441-443
• /
• 2018

This paper deals with the analysis of leg motion using RGB image. We used RGB image as gait analysis element by using BMC(Background Model Challenge) method and by using combining object recognition segmentation algorithm and attitude detection algorithm. It is considered that gait analysis incorporating image can be used as a parameter for classification of gait pattern recognition and abnormal gait.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.1206-1207
• /
• 2023

보행의 제한은 시각장애인의 자립적인 생활을 어렵게 하며 안전에도 큰 영향을 끼친다. 본 논문은 YOLOv5(You Only Look Once version 5)를 활용하여 안전한 보행을 돕는 방법을 제시한다. 제시하는 방법은 자동차나 자전거, 전동킥보드 등의 움직이는 사물과 사람을 실시간으로 인식하여 시각장애인에게 알림으로써 보행에 도움을 줄 수 있으며 시각장애인의 안전한 보행에 도움을 줄 것이라 기대한다.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.4
• /
• pp.33-39
• /
• 2011

Biped robot with high DOF has instability in mechanism. Therefore, it is important to guarantee walking stability of biped robot. Biped robot can stably walk on the flat ground using static walking patterns. However, walking stability of robot becomes increasingly worse on the uneven terrain. In the paper, we propose a robust walking algorithm of biped robot with motion stabilization to solve the problem The proposed algorithm was designed to stabilize walking motions based on the inclination of robot body using a gyro sensor and a accelerometer equipped in the center of the upper body. If unstable motions are recognized, angles of each joints are modified to increase stability by using compensation of angles of lower legs. The experimental results show that biped robot performs stable walking on the uneven terrain.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2012.07a
• /
• pp.83-86
• /
• 2012

본 논문에서는 야간에 보행자인식의 성능 향상을 위한 효율적인 인식 방법을 제안한다. 이 논문은 야간에 차량에 비치 된 Thermal Camera를 이용하여 적외선 영상을 얻은 후, 적응적 thresholding, Histogram Equalization, Morphology Operation, Labelling, HOG및 SVM Training 방법을 사용하여 보행자의 인식율을 높이도록 하였다. 3830개의 training 영상을 사용하였으며 실험결과 우수한 인식 결과를 얻었다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.6
• /
• pp.654-662
• /
• 2010

In this paper, we suggest an advanced algorithm, to recognize pedestrian/non-pedestrian using second-stage cascade method, which applies Adaboost algorithm to make a strong classification from weak classifications. First, we extract two feature vectors: (i) Histogram of Oriented Gradient (HOG) which includes gradient information and differential magnitude; (ii) Curvature-HOG which is based on four different curvature features per pixel. And then, a strong classification needs to be obtained from weak classifications for composite recognition method using both HOG and curvature-HOG. In the proposed method, we use one feature vector and one strong classification for the first stage of recognition. For the recognition-failed image, the other feature and strong classification will be used for the second stage of recognition. Based on our experiment, the proposed algorithm shows higher recognition rate compared to the traditional method.