• Spatial Information Research
• /
• v.20 no.5
• /
• pp.77-89
• /
• 2012

Walking is the most basic personal mobility and its importance and concern is ever increasing with the highlighting of a new paradigm, such as transit oriented development, sustainable development and revitalization of green transport. The existing analytical research on pedestrian network is using a pedestrian's moving distance to a destination and integration in space syntax theory as its representative accessibility factors. However, the uniplanar network moving distance fails to reflect topographic characteristics, so the moving distance could show a similar result value in case of the regions for analysis that have a similar network structure to each other. Accordingly, the aim of this study is to suggest a new analytical methodology on pedestrian network accessibility in consideration of the grade in pedestrian sections and a pedestrian's size. this study, in its analysis of a uniplanar pedestrian network moving distance, analyzed the pedestrian network moving distance in consideration of the grade in pedestrian sections, and even the pedestrian network moving distance in consideration of a pedestrian's size, and suggested the methodology on pedestrian network accessibility analysis in consideration of a more substantive pedestrian's characteristics. It is hoped that the methodology used by this study will be used as the methodology on pedestrian network analysis which can reflect topographic characteristics in the pedestrian network analysis, and take a more substantive pedestrian's movement into account.

• Journal of Korean Society for Geospatial Information Science
• /
• v.19 no.3
• /
• pp.67-74
• /
• 2011

In recent years, with increasing utilization of mobile devices such as smartphones, the need for PNS(Pedestrian Navigation Systems) that provide guidance for moving pedestrians is increasing. For the navigation services, road network is the most important component when it comes to creating route and guidance information. In particular, pedestrian network requires modeling methods for more detailed and vast space compared to road network. Therefore, more efficient method is needed to establish pedestrian network that was constructed by existing field survey and manual editing process. This research proposed a pedestrian network creation method appropriate for pedestrians, based on CNS(Car Navigation Systems) data that already has been broadly constructed. Pedestrian network was classified into pedestrian link(sidewalk, side street, walking facility) and openspace link depending on characteristics of walking space, and constructed by applying different methodologies in order to create path that similar to the movements of actual pedestrians. The proposed algorithm is expected to become an alternative for reducing the time and cost of pedestrian network creation.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.11a
• /
• pp.307-310
• /
• 2009

본 논문은 대형 건축물 내에서의 보행자 대피 시뮬레이션을 위해, 광범위한 네트워크 모델과 세밀한 네트워크 모델을 통합하는 방법과보행자가 자연스럽게 벽이나 장애물을 피하면서 이동할 수 있도록 하는 개선된 보행자 이동 모델을 제안한다. 제안하는 네트워크 모델을 통해 기존의 광범위 네트워크 모델에서 분석할 수 없는 보행자 개개인의 이동정보를 세밀한 네트워크보다 적은 양의 연산으로 계산할 수 있었고, 개선된 보행자 이동 모델을 통해 보행자가 자연스럽게 벽이나 장애물을 피하면서 이동할 수 있도록 하였다. 제안하는 방법을 대형 건축물인 코엑스 몰에 적용하여 대피 시뮬레이션을 수행한 결과, 3000명의 보행자에 대해 초당 10번 이상의 시뮬레이션 정보를 계산할 수 있었고, 대피 시의 방향 유도에 따른 대피 시간을 확인할 수 있었다.

• Proceedings of the KOR-KST Conference
• /
• 2007.05a
• /
• pp.701-707
• /
• 2007

• Journal of Korean Society of Transportation
• /
• v.26 no.1
• /
• pp.137-144
• /
• 2008

It is important to know pedestrian volume to carry out pedestrian safety analysis and pedestrian friendly design. However, it is too difficult to come across research work related to pedestrian volume analysis in the field of transport, due to lack of interests on pedestrian movement. Most transport research has been focused on vehicles and highways rather than pedestrian. On the other hand, in the field of urban studies, there comes an effective tool to estimate pedestrian volumes using Space Syntax theory. This theory twins out to be effective and economic because it only requires network information, which is easy to acquire from maps and field survey. However, this method is different in the way representing networks from the way that is common in the field of transport. To make up for this point, this paper develops a novel measure for estimating pedestrian volume using Dial's algorithm, and applies the model in the two test networks; Insadong and Soongryemoon networks. The application results reveals that developed measure is an effective tool to explain pedestrian volume; a correlation coefficient between the measure and pedestrian volume is 0.713 in Insadong and 0.492 in Soongryemoon, and the goodness of fit($R^2$) of regression models are 0.893 in Insadong and 0.671 in Soongryemoon. This estimation method is significantly less complicated to estimate the effect of a pedestrian network change than Space Syntax theory, which requires special softwares not readily available.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.5
• /
• pp.62-70
• /
• 2016

Ensuring walkability in a city where pedestrians and vehicles coexist is an issue of critical importance. The relative relationship between vehicle transit and walkability improvements complicates the evaluation of walkability, which thus necessitates the formation of a quantitative standard by which a methodological measurement of walkability can be achieved inside the pedestrian network. Therefore, a model is determined whereby quantitative indices such as, but not limited to, experiences of accessibility, mobility, and convenience within the network are estimated. This research proposes the integration of space syntax theory and the logit path choice model in the evaluation of walkability. Space syntax theory assesses adequacy of the constructed pedestrian network through calculation of the link integration value, while the logit model estimates its safety, mobility, and accessibility using probability. The advantage of the integrated model hence lies in its ability to sufficiently reflect such evaluation measures as the integration value, mobility convenience, accessibility potential, and safety experienced by the demand in a quantitative manner through probability computation. In this research, the Dial Algorithm is used to arrive at a solution to the logit model. This process requires that the physical distance of the pedestrian network and the perceptive distance of space syntax theory be made equivalent. In this, the research makes use of network expansion to reflect wait times. The evaluation index calculated through the integrated model is reviewed and using the results of this sample network, the applicability of the model is assessed.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2009.04a
• /
• pp.7-9
• /
• 2009

Because unlike cars, pedestrians are not moving along the middle axis of street lanes, PNS needs more sophisticated information. So we defined the specific needs of pedestrians, analyzed already existing geodata sets and selected the reasonable layers.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.79-81
• /
• 2018

최근 딥 러닝의 발전과 함께 보행자 검출 기술의 성능이 발전하면서 다양한 분야에서 응용되고 있다. 영상 내 보행자의 위치나 움직임을 파악함으로써 위험 지역이나 보안 지역에 접근하는 보행자를 찾아낼 수 있다. 일반적인 딥 러닝 기반의 물체 검출기는 멀리 있는 보행자와 같은 작은 물체를 검출 하는 데에 적합하지 않다. 또, 검출을 수행하기 위해서 큰 계산량을 필요로 하기 때문에, 동영상의 매 프레임 마다 수행하기 부적합 하다는 단점이 있다. 본 논문에서는 작은 물체도 잘 검출할 수 있도록 기존 YOLO 네트워크의 구조를 변경하고, 보행자 데이터를 이용하여 추가로 학습함으로써 보행자를 검출하는 성능을 증가시켰다. 그리고 검출한 보행자들에 대해 추적 기법을 이용함으로써, 동영상의 매 프레임 마다 검출을 수행하는 것을 피할 수 있도록 하였다. 실제로 DukeMTMC Dataset을 이용하여 실험을 해본 결과, YOLO 네트워크의 구조를 변경하고 추가 학습을 함으로써 검출 정확도가 개선되는 것을 확인할 수 있었다. 또, 추적 기법을 이용했을 때, 성능이 크게 떨어지지 않으면서 검출 속도를 개선할 수 있는 것을 확인할 수 있었다.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.29-38
• /
• 2022

This paper proposes a system for classifying gait types using an ensemble deep learning network for gait data measured by a smart insole equipped with multi-sensors. The gait type classification system consists of a part for normalizing the data measured by the insole, a part for extracting gait features using a deep learning network, and a part for classifying the gait type by inputting the extracted features. Two kinds of gait feature maps were extracted by independently learning networks based on CNNs and LSTMs with different characteristics. The final ensemble network classification results were obtained by combining the classification results. For the seven types of gait for adults in their 20s and 30s: walking, running, fast walking, going up and down stairs, and going up and down hills, multi-sensor data was classified into a proposed ensemble network. As a result, it was confirmed that the classification rate was higher than 90%.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.435-437
• /
• 2022

보행 보조 로봇의 효과적인 보조를 위해서는 사용자의 보행 유형을 인식하는 것이 중요하다. 본 논문에서는 end-to-end 분류 네트워크 기반 보행 환경 인식 방법을 사용하여 사용자의 보행 유형을 강인하게 추정한다. 실외 보행 환경을 오르막길, 평지, 내리막길 3 가지로 분류하는 딥러닝 모델을 학습시켰으며, 엣지 디바이스에서 이를 사용하기 위해 네트워크 경량화를 진행하였다. 경량화 후 추론 속도는 약 47FPS 수준으로 실시간으로 보행 보조 로봇에 적용 가능한 것을 검증했으며, 정확도 측면에서도 97% 이상의 성능을 얻을 수 있었다.