• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.10a
• /
• pp.293-297
• /
• 2007

This thesis suggests a new algorithm to detects multiple moving objects using a CMODE(Correct Multiple Object DEtection) method in the color images acquired in real-time and to track the interested pedestrian using motion and hue information. The multiple objects are detected, and then shaking trees or moving cars are removed using structural characteristics and shape information of the man , the interested pedestrian can be detected, The first similarity judgment for tracking an interested pedestrian is to use the distance between the previous interested pedestrian's centroid and the present pedestrian's centroid. For the area where the first similarity is detected, three feature points are calculated using k-mean algorithm, and the second similarity is judged and tracked using the average hue value for the $3{\times}3$ area of each feature point. The zooming of camera is adjusted to track an interested pedestrian at a long distance easily and the FOV(Field of View) of camera is adjusted in case the pedestrian is not situated in the fixed range of the screen. As a experiment results, comparing the suggested CMODE method with the labeling method, an average approach rate is one fourth of labeling method, and an average detecting time is faster three times than labeling method. Even in a complex background, such as the areas where trees are shaking or cars are moving, or the area of shadows, interested pedestrian detection is showed a high detection rate of average 96.5%. The tracking of an interested pedestrian is showed high tracking rate of average 95% using the information of situation and hue, and interested pedestrian can be tracked successively through a camera FOV and zooming adjustment.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.1
• /
• pp.333-340
• /
• 2014

We analyzed pedestrian preference and features of preferential space by MDS (Multi Dimensional Scaling). As the result, features of pedestrian space in dimension 1 could be interpreted as "Segregation of Pedestrian and Vehicle", and features of pedestrian space in dimension 2 could be read like "Natural-City". And as a result of vector analysis about preferential of pedestrian, a pedestrian mall between housing complex, pedestrian space in pocket park, pedestrian space in neighborhood park, and pedestrian space around public facilities was the best preferential space. On the other hand, pedestrians tended to dislike pedestrian space between detached.

• Journal of Korean Society of Transportation
• /
• v.30 no.3
• /
• pp.7-15
• /
• 2012

Korean Highway Capacity Manual (KHCM) has been used when we analyze the pedestrian Level of Service (LOS) of a pedestrian facility. However, the pedestrian LOS by KHCM is largely insensitive to pedestrian congestion levels. The objective of this study is to identify the source of this problem within the KHCM calculation method, and to propose an improved method using the case study from Seoul. Based on KHCM results, the pedestrian LOS is A for more than 90% of the Seoul region, which seems to be unrealistic. On the other hand, this study includes an effective adjustment parameter using the absolute value of effective sidewalk width. Using this method, results shows some changes including newly identified areas of LOS C and LOS D. The analysis of pedestrian LOS is carried out for the entire metropolitan region of Seoul in order to evaluate area wide pedestrian level of service in Seoul.

• Smart Media Journal
• /
• v.1 no.2
• /
• pp.12-22
• /
• 2012

Today we are witnessing an increasingly widespread use of cameras in our lives for video surveillance, robot vision, and mobile phones. This has led to a renewed interest in computer vision in general and an on-going boom in human activity recognition in particular. Although not particularly fancy per se, human gait is inarguably the most common and frequent action. Early on this decade there has been a passing interest in human gait recognition, but it soon declined before we came up with a systematic analysis and understanding of walking motion. This paper presents a set of DBN-based models for the analysis of human gait in sequence of increasing complexity and modeling power. The discussion centers around HMM-based statistical methods capable of modeling the variability and incompleteness of input video signals. Finally a novel idea of extending the discrete state Markov chain with a continuous density function is proposed in order to better characterize the gait direction. The proposed modeling framework allows us to recognize pedestrian up to 91.67% and to elegantly decode out two independent gait components of direction and posture through a sequence of experiments.

• International Journal of Highway Engineering
• /
• v.12 no.4
• /
• pp.11-16
• /
• 2010

Various researches have been performed on the topic of pedestrian traffic flow. At the beginning, the modeling and simulation method for the vehicular traffic flow was simply applied to pedestrian traffic flow. Recently, CA based simulation models are frequently applied to pedestrian flow analysis. Initially, the square Lattice Model is a base model for applying to pedestrians of counterflow and then Hexagonal Lattice Model improves its network as a hexagonal cell for more realistic movement of the avoidance of pedestrian conflicts. However these lattice models express only one directional movement because they express only one directional movement. In this paper, MLPM (the Multi-Layer Pedestrian Model) is suggested to give various origins and destinations for more realistic pedestrian motion in some place.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.06a
• /
• pp.222-223
• /
• 2016

보행자 인식을 위한 컴퓨터 비전 알고리즘은 야간 상황과 같이 저조도 환경에서는 인식 성능이 떨어지고 있다. 이로 인하여 최근 저조도 환경에서 촬영된 영상으로 야간 상황에서 객체 인식 성능을 높이는 기법들이 연구되고 있다. 야간 환경은 주간 환경과는 다르게 광량이 적기 때문에 인간의 시각으로도 객체 인식에 어려움이 있고 일반적인 카메라로 촬영된 영상으로 객체 인식이 어렵다. 최근에는 NIR 카메라를 이용하여 촬영된 영상으로 야간 보행자 인식 알고리즘이 개발되고 있으나, 인식률과 객체 인식 가능 거리 및 범위가 한정적이다. 또한 기존의 야간 보행자 검출 기법들은 방대한 연산량이 필요하기 때문에 실시간 객체 인식이 불가능하다. 본 논문에서는 NIR 카메라로부터 촬영된 영상으로 preprocessing 후 ACF(Aggregated Channel Feature)를 이용하여 최근 연구되고 있는 카메라 움직임이 있는 야간 환경에서 보행자 인식 알고리즘을 PC 및 TK1 Board 환경에서 구현하고 객체 인식률을 높인다.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.819-820
• /
• 2008

본 논문에서는 적외선 거리측정 센서를 이용한 보행자 측정 시스템을 제안하였다. 제안한 시스템은 적외선 거리측정 센서의 배열를 이용하여 센서 시스템을 통과하는 보행자의 높이를 영상으로 획득하며, 이러한 센서열을 두 행으로 배치함으로서 보행자의 이동 방향을 판단한다. 실험 결과 제안한 시스템은 약 90% 의 정확도로 보행자 수를 측정할 수 있음을 확인하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.229-232
• /
• 2017

기존의 이동방향 인식 시스템은 개인의 스마트폰 내부에 있는 센서 중 자이로/가속도 센서를 이용하여 측정하였다. 자이로/가속도 센서는 외부의 영향을 거의 받지 않아 정확도가 높다고 볼 수 있지만, 스마트폰의 위치에 따라 정확도가 변한다. 따라서, 기존의 이동방향 인식 시스템은 개인의 이동방향을 감지하기에는 적합하나 다수의 보행자에 대한 이동방향을 시스템에서 인식하기에는 부적합하다. 본 논문에서는 다수의 보행자에 대한 이동방향을 인식하기 위해 압전센서 어레이를 이용하여 특정 구역의 바닥에 설치하고 보행자와 압전센서 사이의 접촉형태와 개수를 파악하고, 시간을 측정하여 보행자의 이동방향을 계산한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1685-1686
• /
• 2015

보행 이동장치 기술은 가상현실 시뮬레이터 환경에서 사용자의 보행 이동을 이용한 공간 탐색과 네비게이션을 가능하게 하여, 훈련 시뮬레이터 시스템의 체감 몰입감과 훈련 충실도를 향상시키는 휴먼 인터페이스 기술이다. 본 연구에서는 현재까지 개발된 다양한 보행 이동 인터페이스 기술들을 분석하고, 체감 네비게이션을 이용한 훈련 몰입도 향상 방안에 대해 소개하며, 훈련 시뮬레이터 시스템에 통합하기 위한 보행 이동 시스템의 설계 과정을 기술한다.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.7 no.2
• /
• pp.75-84
• /
• 2013

In this study, the patterns and characteristics according to gait cycle were analyzed using to EMG signals during walking, and analyzed in the time domain and frequency domain. The experiments was performed divide to level-ground walking and stair walking, and gait cycle was analysis by stance and swing. In the sagittal plane by using the tilt sensor measures the angle of the lower leg, and EMG was measured from the quadriceps and biceps femoris. The tilt of the lower leg was showed the biggest tilt at HS, and showed lowest value at TO. All in walking according to the gait cycle IEMG showed a specific pattern, and is expected useful to determine the gait cycle and kind. In the frequency domain analysis was using STFT on able to frequency analysis according to time, and using the tilt sensor was identify gait cycle. We analyzed also spectrum of the results of the STFT in all gait types, and recognized that stance had broad bandwidth than that of swing. Through this study, it was confirmed the possibility of judgment and analysis of the gait cycle using EMG and the tilt in the sagittal plane of the lower leg. When used it, can improve the quality of life of amputation patients