• 동력기계공학회지
• /
• 제13권5호
• /
• pp.76-81
• /
• 2009

The fatalities of pedestrian account for about 21.2% of all fatalities at 2007 year in Korea. To reconstruct exactly the accident, it is important to calculate the throw distance of pedestrian in car to pedestrian accident. The frontal shape of SUV vehicle is dissimilar to passenger car and bus, so the trajectory and throw distance of pedestrian by SUV vehicle is not the same of passenger car and bus. The influencing on it can be classified into the factors of vehicle and pedestrian, and road factor. It was analyzed by PC-CRASH for simulation, and SPSS s/w was used for regression analysis. From the simulation results, the maximum impact energy of multi-body of pedestrian was occurred to that of torso body at the same time. And the throw distance increased with the increasing of impact velocity, and decreased with the increasing of impact offset. Also it decreased with the increasing of velocity of pedestrian at accident, and the throw distance of wet road was longer than that of dry road. Finally, the regression analysis model of SUV(Nissan Pathfinder type)vehicle in car to pedestrian accident was as follows; $$disti_i=-0.87-0.11offseti_i+0.69speed_i-4.27height_i+0.004walk_i+0.63wet_i+{\epsilon}_i$$.

• 한국안전학회지
• /
• 제30권1호
• /
• pp.94-103
• /
• 2015

This study analyzes the influence factors on elderly pedestrian accident. Elderly people are easy to be badly injured by car accidents compared to younger people. Therefore, various plans and measures are required to protect elderly pedestrian from accidents. However, pedestrian accidents studies only focused on microscopic factors such as attribute of driver, pedestrian, road design. In order to prevent pedestrian accident and reduce the severity of the accident, not only microscopic factors but macroscopic variables such as urban planning and facility should be considered. In this regard, this study develops an ordered probit model introduced the characteristics of urban facility which were not considered in the previous studies. The result shows that there is higher level of accident severity in such areas as large commercial area, well-developed area with transportation infrastructure service and non-pedestrian safety zone. Thus, various and appropriate countermeasures should be prepared in order that pedestrian accident can be prevented in the areas mentioned above. In addition to the aforementioned variables, it is revealed that other variables including vehicle speed, gender and age of pedestrian, weather condition, type of vehicle, etc. partly affect the severity of pedestrian accident.

• 반도체디스플레이기술학회지
• /
• 제22권2호
• /
• pp.128-132
• /
• 2023

Recently, with the development of deep learning technology, research on pedestrian attribute recognition technology using deep neural networks has been actively conducted. Existing pedestrian attribute recognition techniques can be obtained in such a way as global-based, regional-area-based, visual attention-based, sequential prediction-based, and newly designed loss function-based, depending on how pedestrian attributes are detected. It is known that the performance of these pedestrian attribute recognition technologies varies greatly depending on the type of backbone network that constitutes the deep neural networks model. Therefore, in this paper, several backbone networks are applied to the baseline pedestrian attribute recognition model and the performance changes of the model are analyzed. In this paper, the analysis is conducted using Resnet34, Resnet50, Resnet101, Swin-tiny, and Swinv2-tiny, which are representative backbone networks used in the fields of image classification, object detection, etc. Furthermore, this paper analyzes the change in time complexity when inferencing each backbone network using a CPU and a GPU.

• 자동차안전학회지
• /
• 제9권4호
• /
• pp.14-19
• /
• 2017

The mortality rate of car-pedestrian accidents is quite high compared to the frequency of accident. Recently, governments and insurance companies tend to establish and implement new safety standards for pedestrian protection such as EURO-NCAP and K-NCAP. The performance for the pedestrian protection has been gradually improved, but it is still insufficient. Therefore, various studies for the pedestrian protection are being carried out. The car-pedestrian accident is simulated in order to study to the upper legform test of the EURO-NCAP protocol. A pedestrian dummy model is employed and the results are discussed.

• 한국자동차공학회논문집
• /
• 제19권5호
• /
• pp.82-91
• /
• 2011

In this paper, a planar model for mechanics of a vehicle/pedestrian collision incorporating road gradient is derived to evaluate the pre-collision speed of vehicle. It takes into account a few physical variables and parameters of popular wrap and forward projection collisions, which include horizontal distance traveled between primary and secondary impacts with the vehicle, launch angle, center-of-gravity height at launch, distance from launch to rest, pedestrian-ground drag factor, the pre-collision vehicle speed and road gradient. The model including road gradient is derived analytically for reconstruction of pedestrian collision accidents, and evaluates the vehicle speed from the pedestrian throw distance. The model coefficients have physical interpretations and are determined through direct calculation. This work shows that the road gradient has a significant effect on the evaluation of the vehicle speed and must be considered in accident cases with inclined road. In additions, foreign/domestic empirical cases and multibody dynamic simulation results are used to construct a least-squares fitted model that has the same structure of the analytical one that provides an estimate of the vehicle speed based on the pedestrian throw distance and the band within which the vehicle speed would be expected to be in 95% of cases.

• Spatial Information Research
• /
• 제22권2호
• /
• pp.53-62
• /
• 2014

Floor Field Model(FFM)은 실내에서 보행자의 움직임을 모델링하기 위한 CA기반 미시적 보행모델이며, static과 dynamic floor field를 이용하여 보행자의 움직임을 표현해낸다. 다만, 실제 보행자의 크기와 모양은 타원체나 직사각형과 유사한데, FFM에서는 정사각형 형태의 보행자를 설정하고 있다. 이로 인해 보행자들의 회전효과 부여에 어려움이 있으며, 보행자들끼리 발생하는 충돌, 끼임 등의 영향을 반영하기에 한계가 있다. 또한, 보행자의 자세 시야의 변경에 따른 영향들도 효과적으로 반영되고 있지 않다. 본 연구에서는 FFM이 가진 한계점을 개선하기 위해 보행자의 크기, 모양 등의 물리적 특성을 반영한 보행모델을 제시한다. 본 모델에서는 정사각형이 아닌 직사각형 형태로 보행자를 정의하며, 한국인의 실제 신체크기에 가깝도록 하였다. 또한, 보행자의 자세정보를 추가하였으며, 보행자들 간에 발생하는 충돌, 끼임 등의 영향을 반영할 수 있도록 정의하였다. 제안된 모델을 이용한 시뮬레이터를 개발하였으며, 개선된 모델과 기존 모델간의 비교 분석을 통해 차이점을 분석하였다. 이를 통해 기존 모델에서 발생하던 dynamic value 적용문제의 해결과 대피상황에서 발생하는 패닉현상의 반영을 확인할 수 있었다.

• 대한토목학회논문집
• /
• 제36권2호
• /
• pp.259-268
• /
• 2016

대중교통중심개발(TOD)을 위한 핵심전략은 철도역을 중심으로 보행권내에서 고밀도의 복합토지이용을 유도하는 방안을 마련하는 것이다. 해외에서는 이미 역세권을 중심으로 보행시설의 통합정비를 위한 제도를 마련하고, TOD를 효과적으로 추진해왔다. 그러나 국내는 종합적인 보행정비의 중요성에도 불구하고, 역세권 중심의 통합보행인프라 구축에 대한 방향설정이 부족하다. 따라서 우선 역세권 주변의 보행시설의 통합정비에 대한 평가기준을 마련하여 TOD 개선에 대한 판단근거로 활용하는 것이 시급하다. 본 연구는 TOD의 효과 평가를 위해 역사 건물내부와 주변지역을 통합하여 보행의 원활한 정도를 평가하는 네트워크 모형을 제안한다. 모형은 철도 역사와 주변지역을 일체화된 보행 네트워크 상의 흐름으로 간주한다. 보행자가 선택한 경로는 최소시간 경로라고 정의하여 Wardrop의 이용자 균형(1952) 개념을 확대 적용하였다. 보행통로의 혼잡상황, 엘리베이터의 용량한계, 횡단보도의 대기와 같이 보행시설에서 나타나는 다양한 행태를 고려하기 위해서 변동부등식기반의 보행자 균형배정모형을 제안한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권7호
• /
• pp.2321-2338
• /
• 2021

Compared with vehicle trajectories, pedestrian trajectories have stronger degrees of freedom and complexity, which poses a higher challenge to trajectory prediction tasks. This paper designs a mode to divide the trajectory of pedestrians at a traffic intersection, which converts the trajectory regression problem into a trajectory classification problem. This paper builds a deep model for pedestrian trajectory prediction at intersections for the task of pedestrian short-term trajectory prediction. The model calculates the spatial correlation and temporal dependence of the trajectory. More importantly, it captures the interactive features among pedestrians through the Attention mechanism. In order to improve the training speed, the model is composed of pure convolutional networks. This design overcomes the single-step calculation mode of the traditional recurrent neural network. The experiment uses Vulnerable Road Users trajectory dataset for related modeling and evaluation work. Compared with the existing models of pedestrian trajectory prediction, the model proposed in this paper has advantages in terms of evaluation indicators, training speed and the number of model parameters.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권3호
• /
• pp.1464-1480
• /
• 2019

Robust tracking of infrared (IR) pedestrian targets with various backgrounds, e.g. appearance changes, illumination variations, and background disturbances, is a great challenge in the infrared image processing field. In the paper, we address a new tracking method for IR pedestrian targets via multi-feature local sparse representation (SR), which consists of three important modules. In the first module, a multi-feature local SR model is constructed. Considering the characterization of infrared pedestrian targets, the gray and edge features are first extracted from all target templates, and then fused into the model learning process. In the second module, an effective tracker is proposed via the learned model. To improve the computational efficiency, a sliding window mechanism with multiple scales is first used to scan the current frame to sample the target candidates. Then, the candidates are recognized via sparse reconstruction residual analysis. In the third module, an adaptive dictionary update approach is designed to further improve the tracking performance. The results demonstrate that our method outperforms several classical methods for infrared pedestrian tracking.

• 전기전자학회논문지
• /
• 제17권4호
• /
• pp.469-477
• /
• 2013

본 논문은 특징 정보 예측을 통한 빠른 보행자 검출 기법을 제안한다. 다양한 크기의 보행자를 검출하기 위해 보행자 모델의 크기나 입력영상의 크기를 변화시킨다. 보행자 모델의 크기를 변화시킬 경우 크기별 모델이 필요하며, 보행자 모델의 크기의 축소시키는 경우 모델 정보를 손상시킨다. 보행자 모델의 다양한 크기별 보행자의 특징을 추출해야 하므로 보행자 특징의 추출은 전체 수행시간 중 가장 많은 시간을 필요로 한다. 따라서 본 논문은 영상 크기에 따라 특징 추출을 반복하지 않고 입력영상에서 얻어진 특징 정보의 예측을 통해 보행자 검출의 특징추출을 수행한다. 제안하는 방법의 효율성을 검증하기 위해 다양한 채널을 가진 ChnFtrs 특징 및 Adaboost 알고리즘을 사용과 학습과 실험을 위한 영상으로 INRIA 보행자 DB를 사용하였다.