• Journal of Korea Multimedia Society
• /
• v.19 no.2
• /
• pp.264-270
• /
• 2016

In this paper, we proposed a method which can detect pedestrians from CCTV video and estimate the height of the detected objects. We separate the foreground using Gaussian mixture model and the pedestrian is detected using the conditions such as the width-height ratio and the size of the candidate objects. In order to obtain the optimal model for estimating the height of pedestrian, we get many training data from the pedestrian whose height is known. Using these training data, we designed optimal Wiener height estimator and used to estimate the height of pedestrians. The height of the pedestrian at various distance is estimated and the accuracy is evaluated. In the experimental results, proposed method shows that it can estimate the height of pedestrian for various positions effectively.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.5
• /
• pp.259-265
• /
• 2023

Pedestrian detection is used to effectively detect pedestrians in various situations based on deep learning. Pedestrian detection has difficulty detecting pedestrians due to problems such as camera performance, pedestrian description, height, and occlusion. Even in the same pedestrian, performance in detecting them can differ according to the height of the pedestrian. The height of general pedestrians encompasses various scales, such as those of infants, adolescents, and adults, so when the model is applied to one group, the extraction of data becomes inaccurate. Therefore, this study proposed a pedestrian detection method that fine-tunes the pedestrian area by Refining Layer and Feature Concatenation to consider various heights of pedestrians. Through this, the score and location value for the pedestrian area were finely adjusted. Experiments on four types of test data demonstrate that the proposed model achieves 2-5% higher average precision (AP) compared to Faster R-CNN and DRPN.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.5
• /
• pp.54-61
• /
• 2016

This paper try to identify the minimum speed of vehicles in collision between pedestrian head and windshield at vehicle-pedestrian accidents. The MADYMO program was used with NF Sonata vehicle and pedestrian in height of 160cm, 170cm, and 180cm. From the simulation results, it was found that the minimum speed of vehicle was different for each pedestrian height : 49km/h for 160cm, 41km/h for 170cm, and 29km/h for 180cm. The results could be used in speed estimating process when there is a collision trace between pedestrian head and windshield at vehicle- pedestrian accident investigation.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.6 no.3
• /
• pp.105-111
• /
• 2007

The type of pedestrian accident can be characterized by vehicular frontal shape and the height of pedestrian. The trajectory of pedestrian after collision by passenger car is different from that by bus due to vehicular frontal shape. The frontal shape of SUV vehicles is dissimilar to passenger car and bus. So, the trajectory and throw distance of pedestrian by SUV vehicles is not the same of passenger car and bus. In this paper, a series of pedestrian kinetic simulation were conducted to inspect the difference in throw distance between SUV vehicle and passenger car and bus by PC-CRASH that is the program for kinetic analysis of articulated body. From the results, if the height of pedestrian is taller than 1.70m, there is no difference in throw distance between SUV vehicle and passenger car, but if the height of pedestrian is about 1.55m throw distance of SUV vehicle is about 4m longer than that of passenger car at each impact speed. The throw distance of pedestrian by Bus is shorter than that of passenger car and SUV at each impact speed.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.9
• /
• pp.1035-1042
• /
• 2014

Object recognition is one of the key technologies of the monitoring system for the prevention of various intelligent crimes. The height is one of the physical information of a person, and it may be important information for identification of the person. In this paper, a method which can detect pedestrians from CCTV images and estimate the height of the detected objects, is proposed. In this method, GMM (Gaussian Mixture Model) method was used to separate the moving object from the background and the pedestrian was detected using the conditions such as the width-height ratio and the size of the candidate objects. The proposed method was applied to the CCTV video, and the height of the pedestrian at far-distance, middle- distance, near-distance was estimated for the same person, and the accuracy was evaluated. Experimental results showed that the proposed method can estimate the height of the pedestrian as the accuracy of 97% for the short-range, 98% for the medium-range, and more than 97% for the far-range. The image sizes for the same pedestrian are different as the position of him in the image, it is shown that the proposed algorithm can estimate the height of pedestrian for various position effectively.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.20 no.6
• /
• pp.67-72
• /
• 2012

Novel Front End Module(FEM) with improved pedestrian protection is very important to reduce the severity of pedestrian injury. The FEM needs to have enough space from hood to absorb the energy from any pedestrian collision. In this study, the cooling performance of the FEM to cool the engine was investigated under 25% height reduction. The results indicated that the cooling performance analysis was about 86% level compared to that of the conventional FEM. Also, good qualitative agreement between CFD predictions and experimental measurements was found. This FEM needs the cooling performance enhancement for changed air flow path at the frontal part of vehicle. Therefore, we showed an improved performance using air guide setup and shape modification under the high load condition.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.5
• /
• pp.85-95
• /
• 2017

This study aims to identify the throw distance in terms of truck weight, bumper height, and speed in a truck and pedestrian collision, and to propose a model for throw distance estimates. For this purpose, a simulation analysis is performed using the PC-crash program with the following experiment conditions: Truck weight of 5t, 15t, and 25t, Bumper height from 0.3m to 0.6m by 0.1m, and speed from 10km/h to 100km/h by 10 km/h. Experimental results show that the truck speed and bumper height are found to be significant factors for pedestrian throw distance, but truck weight is not a significant factor. Also, a regression model is developed for pedestrian throw distance estimate from the multiple regression analysis. The adjusted $R^2$ value of the model is 93.3%, which is very good explanatory power.

• Journal of Power System Engineering
• /
• v.13 no.2
• /
• pp.56-62
• /
• 2009

The fatalities of pedestrian account for about 40.0% of all fatalities in Korea 2005. Vehicle-Pedestrian accident generates trajectory of pedestrian. In pedestrian involved accident, the most important data to inspect accident is throw distance of pedestrian. The throw distance of pedestrian can be influenced by many variables. But existing studies have been done for simple factors. The variables that influence trajectory of pedestrian can be classified into vehicular factors, pedestrian factors, and road factors. The trajectory of pedestrian, dynamic characteristics of multi-body were analyzed by PC-CRASH, a kinetic analysis program for a traffic accident. PC-CRASH enables an analyst to investigate the effect of many variables. The influence of the offset of impact point was analyzed by Working Model. Based on the results, the variables that influence trajectory of pedestrian were vehicular frontal shape, vehicular impact speed, the offset of impact point, the height of pedestrian, friction coefficients of pedestrian. However the weight of pedestrian did not affect trajectory of pedestrian considerably.

• KIEAE Journal
• /
• v.14 no.5
• /
• pp.89-96
• /
• 2014

This study provides the basic resource for establishing the environment design policies around elementary school for the students and analyzes the actual pedestrian environment conditions of elementary school in order to improve safety of from crime for them. For this, the field survey are conducted on risk of from crime in 10 sidewalks of 5 elementary schoolin Ilsan new town. The result of this are the followings ;1) There are schools which have difference between the height of road and the height of pedestrian path. 2) There are schools which are insufficient distance for securing front sight because of shape of pedestrian path. 3) In entrance there are facilities interfering with natural surveillance within school boundaries such as stone written school motto, storehouse, wash room, doorpost. 4) In entrance there are schools with no security office, emergency bell and CCTV. 4) The openness in the bottom of fence is lower than that of upper because of shrubs and material of fence. 5) There are concealed places and cars in back gate area interfering with natural surveillance.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.19 no.3
• /
• pp.9-15
• /
• 2011

This study analyzed contributing factors affecting leg injury severity in pedestrian-vehicle crashes. A Binary Logistic Regression (BLR) method was used to identify the factors. Independent variables include characteristics for pedestrian, vehicle, road, and environmental conditions. The leg injury severity is classified into two classes, which are dependent variables in this study, such as 'severe' and 'minor' injuries. Pedestrian age, collision speed, and the height of vehicle were identified as significant factors for the leg injury. The probabilistic outcome of predicting leg injury severity can be effectively used in not only deriving pedestrian-related safety policies but also developing advanced vehicular technologies for pedestrian protection.