• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.640-641
• /
• 2016

There are a number of reported papers about detection and tracking of pedestrian for urban design. While related studies have not dealt with various environmental situations, this paper proposes a pedestrian counting system using pedestrian pattern for overcoming technical limitations. The Pedestrian Algorithm uses four steps to count the number of pedestrians for analyzing the pedestrian pattern according to the characteristics of the foot patterns of pedestrians.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.24 no.1
• /
• pp.24-32
• /
• 2016

The mortality rate of car-pedestrian accidents is quite high, compared to the frequency of accidents. Researches on pedestrian protection are being actively performed worldwide. The A-pillar and lower part of the wind shield cause the most serious damage to the pedestrians. Typical devises to protect the pedestrians are the hood lift system and pedestrian airbag. The design of such devices for an sport utility vehicle is performed based on a design process using design of experiments (DOE). The design results are obtained by an orthogonal array (OA), analysis of mean (ANOM) and analysis of variance (ANOVA). A metamodel is also used in the design process.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.808-810
• /
• 2018

Pedestrian tracking is a particular problem of object tracking, and an important component in various vision-based applications, such as autonomous cars or surveillance systems. After several years of development, pedestrian tracking in videos is still a challenging problem because of various visual properties of objects and surrounding environment. In this research, we propose a tracking-by-detection system for pedestrian tracking, which incorporates Convolutional Neural Network (CNN) and color information. Pedestrians in video frames are localized by a CNN, then detected pedestrians are assigned to their corresponding tracklets based on similarities in color distributions. The experimental results show that our system was able to overcome various difficulties to produce highly accurate tracking results.

• International Journal of High-Rise Buildings
• /
• v.7 no.4
• /
• pp.409-415
• /
• 2018

Recently, many countries around the world began to show interest in safety against terrorism, fire, and natural disasters. This study aimed to propose a quantitative measurement system for emergency evacuation and safety for various kinds of terrorism and fire within high-rise multi-purpose facilities, which can measure the pedestrians' ordinary walking patterns in the concourse with the highest pedestrian volume out of all the spaces within multi-story buildings, predict pedestrians' evacuation walking lines when a sudden disaster breaks out, and analyze the gait coefficient, occupant density, and evacuation behavior time.

• Journal of Information Processing Systems
• /
• v.15 no.4
• /
• pp.1017-1028
• /
• 2019

Pedestrian tracking is a particular object tracking problem and an important component in various vision-based applications, such as autonomous cars and surveillance systems. Following several years of development, pedestrian tracking in videos remains challenging, owing to the diversity of object appearances and surrounding environments. In this research, we proposed a tracking-by-detection system for pedestrian tracking, which incorporates a convolutional neural network (CNN) and color information. Pedestrians in video frames are localized using a CNN-based algorithm, and then detected pedestrians are assigned to their corresponding tracklets based on similarities between color distributions. The experimental results show that our system is able to overcome various difficulties to produce highly accurate tracking results.

• Journal of Auto-vehicle Safety Association
• /
• v.12 no.4
• /
• pp.23-30
• /
• 2020

Recently, self-driving research has been actively studied in various institutions. Accurate recognition is important because information about surrounding objects is needed for safe autonomous driving. This study mainly deals with the signal processing of LiDAR among sensors for object recognition. LiDAR is a sensor that is widely used for high recognition accuracy. First, we clustered and tracked objects by predicting relative position and speed of objects. The characteristic points of all objects were extracted using point cloud data of each objects through proposed algorithm. The Classification between vehicle and pedestrians is estimated using number of characteristic points and distances among characteristic points. The algorithm for classifying cars and pedestrians was implemented and verified using test vehicle equipped with LiDAR sensors. The accuracy of proposed object classification algorithm was about 97%. The classification accuracy was improved by about 13.5% compared with deep learning based algorithm.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1987.10a
• /
• pp.47-52
• /
• 1987

• Transportation Technology and Policy
• /
• v.9 no.1
• /
• pp.49-55
• /
• 2012

• Transportation Technology and Policy
• /
• v.9 no.1
• /
• pp.57-66
• /
• 2012

• Transportation Technology and Policy
• /
• v.13 no.5
• /
• pp.41-47
• /
• 2016