• Annual Conference of KIPS
• /
• 2020.11a
• /
• pp.870-872
• /
• 2020

본 시스템은 어린이보호구역에 발생하는 차량사고가 불법주정차된 차량으로 인한 사각지대에 의해 발생되는 것에 착안하여 보행자를 인식하여 운전자들에게 알려 안전운전을 유도하여 사고를 예방해 주는 시스템이다 본 시스템은 영상인식장치, 경광장치, 중계장치, 차량 내 경고장치, 원격 트래픽 경고 수신기로 구성되어 있으며 영상인식장치가 edge-TPU 장치를 활용하여 카메라로부터 입력받은 영상을 모바일넷 기반의 딥러닝으로 처리하여 보행자, 차량, 그밖의 물체를 인식한다. 보행자가 인식되면 외부에서 경광장치가 발광하여 신호를 보내고, 중계장치를 통해 차량 내 경고장치로 보행자 경고 신호를 보낸다. 실험 결과 영상인식을 통해 보행자와 차량을 분류 인식할 수 있음을 확인하였다. 이러한 시스템은 어린이 보호구역에서 발생할 수 있는 교통사고를 방지하기 위해 효과적임을 확인할 수 있었다.

• Journal of KIISE
• /
• v.44 no.1
• /
• pp.44-50
• /
• 2017

Pedestrian detection, an important component of autonomous driving and driving assistant system, has been extensively studied for many years. In particular, image based pedestrian detection methods such as Hierarchical classifier or HOG and, deep models such as ConvNet are well studied. The evaluation score has increased by the various methods. However, pedestrian detection requires high sensitivity to errors, since small error can lead to life or death problems. Consequently, further reduction in pedestrian detection error rate of autonomous systems is required. We proposed a new method to detect pedestrians and reduce the error rate by using the Faster R-CNN with new developed pedestrian training data sets. Finally, we compared the proposed method with the previous models, in order to show the improvement of our method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.4
• /
• pp.812-820
• /
• 2012

In this paper, multiple pedestrians tracking system using Histogram of Oriented Gradient and occlusion detection is proposed. The proposed system is applicable to Intelligent Surveillance System. First, we detect pedestrian in a image sequence using pedestrian's feature. To get pedestrian's feature, we make block-histogram using gradient's direction histogram based on HOG(Histogram of Oriented Gradient), after that a pedestrian region is classified by using Linear-SVM(Support Vector Machine) training. Next, moving objects are tracked by using position information of the classified pedestrians. And we create motion trajectory descriptor which is used for content based event retrieval. The experimental results show that the proposed method is more fast, accurate and effective than conventional methods.

• Journal of Cadastre & Land InformatiX
• /
• v.45 no.1
• /
• pp.225-240
• /
• 2015

The effect of passing pedestrians'characteristics on locational goodwill was empirically modeled and tested. The theoretical basis for the study was central place theory, bid rent and, agglomeration theory, and demand externality theory. The data included information on goodwill, retail rents and passing pedestrians' characteristics in 100 retail trade areas in Seoul. The empirical model was tested with the sample of 1,307 retail units in Seoul, South Korea. The data set was analyzed with the Classification and Regression Tree software. As the results, using the regression tree method, the variables does affect locational goodwill in the each retail trade area were the volume of pedestrians around 2:00 pm on weekdays, volume of pedestrians around 4:00 pm on weekdays, and volume of pedestrians around 8:00 pm on weekdays. In summary, not only the economic base in the retail trade area but also the volume of passing pedestrians should be considered to determine the locational goodwill.

• Annual Conference of KIPS
• /
• 2014.11a
• /
• pp.921-923
• /
• 2014

보행자 검출과정은 특징추출, 추출된 특징을 기반으로 한 학습과정, 그리고 학습된 데이터를 기반으로 한 분류과정으로 나눌 수 있다. 이들 중 연산시간이 가장 오래 걸리는 특징추출과정이다. 기존의 HOG 특징 추출은 하나의 학습 샘플 이미지에 대하여 많은 픽셀 연산이 필요하기 때문에 많은 시간이 소요되었다. 본 논문에서는 실시간 스트리밍 환경에서 이전 프레임의 HOG 특징 검출정보를 분석하여 다음 프레임에서 보행자가 존재 할 가능성이 높은 부분에 대해서만 특징을 추출한다. 이 방법으로 기존의 연구와 비교하여 인식성능에는 거의 영향을 주지 않고 인식 속도를 향상할 수 있다.

• Annual Conference of KIPS
• /
• 2015.04a
• /
• pp.779-781
• /
• 2015

최근 여러 매체에서 화두가 되고 있는 자율 주행 자동차나 Advanced driver assistance systems (ADAS)과 같은 분야에서 보행자 검출 기술은 핵심 요소 기술 중에 하나로 손꼽히고 있다. 특히, 인간의 인지 부하(Cognitive Load)를 고려했을 때, 주행 중에 발생할 수 있는 모든 사건을 다룬다는 것은 매우 어렵기 때문에, 앞서 언급한 방법의 도움을 받아 도로 주행 중에 발생 될 수 있는 인명 사고율을 줄이고자 하는데 그 목적이 있다. 본 논문에서는 Integral Channel Feature를 사용하여 AdaBoost 알고리즘으로 보행자 검출을 위한 분류기를 구현하였다. 그 결과, INRIA에서 제공되는 Pedestrian dataset에서 Detection rate는 97%이상, False positive는 1%에 정도로 나타났다.

• Journal of Korean Society of Transportation
• /
• v.25 no.2 s.95
• /
• pp.83-93
• /
• 2007

Pedestrians and vehicle users should be treated with equal importance in urban street design. However, current street design suggests that the design criteria for sidewalks is based on the functional hierarchy of the vehicles, therefore it is necessary to develop sidewalk design standards that give more weight to pedestrians rather than vehicles. For this, this study suggests that the level of service of pedestrians should be considered in the process of designing sidewalks. Currently, level of service (LOS) criteria for pedestrians in the Korean Highway Capacity Manual are based on pedestrian volume, but the volume of pedestrians is seldomly estimated in practice. So, the current LOS criteria has limitations in terms of practical use. Also, the study assumes that the pedestrian flow rate is hardly the dominant factor that could affect the LOS of pedestrians at most urban sidewalks. In this context, the study considers a new LOS for sidewalk design based on the comfort of pedestrians while passing pedestrians coming from the opposite direction. Then the study attempts to link the new LOS criteria to the land use patterns using data of pedestrian traffic characteristics acquired from the field. In addition to this, the scope in which the suggested criteria can be applied is suggested.

• Journal of the Korea Society of Computer and Information
• /
• v.7 no.4
• /
• pp.150-156
• /
• 2002

In this paper, the traffic carrying capacity of the IMT-2000 ATM-MSC is analyzed by using the reference throughput based on ITU-R. The IMT-2000 services are classified into circuit switching(speech. circuit-switched data. high interactive multimedia) and packet switching(simple message, medium multimedia, high multimedia). The indoor vehicle and pedestrian users are considered. The AAL type 2 for the speech are considered. The ratio of indoor：pedestrian：vehicle are assumed to be 40：40：20%, and size 256 of ATM-MSC are designed.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.4
• /
• pp.58-70
• /
• 2019

In the case of a pedestrian traffic accident, it has a large-scale danger directly connected by a fatal accident at the time of the accident. The domestic ITS is not used for intelligent risk classification because it is used only for collecting traffic information despite of the construction of good quality traffic infrastructure. The CNN based pedestrian detection classification model, which is a major component of the proposed system, is implemented on an embedded system assuming that it is installed and operated in a restricted environment. A new model was created by improving YOLO's artificial neural network, and the real-time detection speed result of average accuracy 86.29% and 21.1 fps was shown with 20,000 iterative learning. And we constructed a protocol interworking scenario and implementation of a system that can connect with the ITS. If a pedestrian accident prevention system connected with ITS will be implemented through this study, it will help to reduce the cost of constructing a new infrastructure and reduce the incidence of traffic accidents for pedestrians, and we can also reduce the cost for system monitoring.

• Journal of Korean Society of Transportation
• /
• v.34 no.2
• /
• pp.168-179
• /
• 2016

This study describes an improved model for estimating pedestrian LOS (Level of Service) by utilizing the space occupied by pedestrians. The method introduced the concept of conflict along the bi-directional pedestrian flow which enables calculating conflict area and average travel time in walking. Especially, the method incorporates the idea of generalized density concept which can consider effective walking area and pedestrian flow rates that might vary during the analysis period. After establishing methodology, adjustments of pedestrian LOS criteria in term of walking space occupied by pedestrians were performed. As a result, walking-occupied space at capacity level is 0.68 and corresponding pedestrian flow rate was calculated as 80 persons/min/m, while different pedestrian-occupied spaces were ordered to classify LOS at the points where the gradient changes. Furthermore, the statistical verification of service levels has shown that there is significant difference among all LOS categories at 5% significance level.