• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.4
• /
• pp.264-272
• /
• 2016

In previous research, we analyzed traffic accident characteristics in the Chungcheong region through factor analysis, cluster analysis, and a questionnaire using traffic accident analysis system data to enhance Korea's traffic safety. Based on the analysis results, we investigated the design and application of traffic safety technology in non-urban areas in this study. Three technologies are proposed to improve traffic safety facilities for the region: a recognition light at pedestrian crossing works, a recognition light on the road for the underprivileged in traffic works, and a safety LED sign for operation of agricultural machine works. Each technology complements the light pollution problem about snow removal and road safety when applied to existing facilities in the non-urban areas. Solar-based indigenous technology is expected to contribute to road safety in rural areas.

• Smart Media Journal
• /
• v.1 no.2
• /
• pp.12-22
• /
• 2012

Today we are witnessing an increasingly widespread use of cameras in our lives for video surveillance, robot vision, and mobile phones. This has led to a renewed interest in computer vision in general and an on-going boom in human activity recognition in particular. Although not particularly fancy per se, human gait is inarguably the most common and frequent action. Early on this decade there has been a passing interest in human gait recognition, but it soon declined before we came up with a systematic analysis and understanding of walking motion. This paper presents a set of DBN-based models for the analysis of human gait in sequence of increasing complexity and modeling power. The discussion centers around HMM-based statistical methods capable of modeling the variability and incompleteness of input video signals. Finally a novel idea of extending the discrete state Markov chain with a continuous density function is proposed in order to better characterize the gait direction. The proposed modeling framework allows us to recognize pedestrian up to 91.67% and to elegantly decode out two independent gait components of direction and posture through a sequence of experiments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.8
• /
• pp.1248-1254
• /
• 2022

Efforts are being made to prevent traffic accidents in the school zone in advance. However, traffic accidents in school zones continue to occur. If the driver can know the situation information in the child protection area in advance, accidents can be reduced. In this paper, we design a camera that eliminates blind spots in school zones and a number recognition camera system that can collect pre-traffic information. It is designed by improving the LIDAR system that recognizes vehicle speed and pedestrians. It collects and processes pedestrian and vehicle image information recognized by cameras and LIDAR, and applies artificial intelligence time series analysis and artificial intelligence algorithms. The artificial intelligence traffic accident prevention system learned by deep learning proposed in this paper provides a forced push service that delivers school zone information to the driver to the mobile device in the vehicle before entering the school zone. In addition, school zone traffic information is provided as an alarm on the LED signboard.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.197-205
• /
• 2024

Development of AI and big data-based algorithms to advance and optimize the recognition and detection performance of various static/dynamic vehicles in front and around the vehicle at a time when securing driving safety is the most important point in the development and commercialization of autonomous vehicles. etc. are being studied. However, there are many research cases for recognizing the same vehicle by using the unique advantages of radar and camera, but deep learning image processing technology is not used, or only a short distance is detected as the same target due to radar performance problems. Therefore, there is a need for a convergence-based vehicle recognition method that configures a dataset that can be collected from radar equipment and camera equipment, calculates the error of the dataset, and recognizes it as the same target. In this paper, we aim to develop a technology that can link location information according to the installation location because data errors occur because it is judged as the same object depending on the installation location of the radar and CCTV (video).

• Journal of the Korean housing association
• /
• v.27 no.6
• /
• pp.1-8
• /
• 2016

This study is focusing on Territoriality which is supposed to be one of the most important elements to activate open spaces in apartment communities. Case analysis with onsite visit is selected as the research method of this study targeting 6 apartment complexes in Bukgu and Gwangsangu, Gwangju city which accommodate over 500 households up to 800 households, which show high occupancy ratio and which were built after 2006 to minimize the physical environment variable. The result of this study is concluded as follows. First, we need the elements which can induce various action and the use of floor surface in color, pattern, and material should be considered in the stance of pedestrian for easy recognition of Territoriality change. Second, To secure the view, we should consider to plant shrubs or to plant trees wider apart. In most cases, enclosure is secured by using trees of Vertical Boundary for safety and comfort, but overuse in some cases make residents feel fear of enclosed spaces and insecurity. Third, Various and harmonious design elements can be recommended to increase aesthetic impression, to induce positive response for design, and to be used consistently. Finally, Unique space using notable landmark or design elements should be considered.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.34 no.2 s.115
• /
• pp.57-71
• /
• 2006

The purpose of this study was to find common characteristics in everyday landscape cognition that the residents share and to restore the resulting characteristics through citizen-participatory town design. Through the residents participatory workshop supported by the Gwangju Buk-gu District Autonomy and Citizen Academy of Gwangju YMCA, 304 people from eight administrative districts participated in three programs. In each program, photographed landscape images representing everyday conditions of the townscape were presented in several ways: in program 1, the residents' mental map was studied; in program 2, landscape images of real places were matched to locations on a map; and in program 3, the landscapes were scored on a scale from 1 to 5 according to five descriptive categories. The elements that were recognized as common landscape features were public facilities, pedestrian spaces, school areas, and parks and natural green spaces. Additional results including recognition of the participants affection for the village and a common landscape image shared by the people, as inhabitants looked around at the space of their own lives. It seems possible that more creative townscapes can be created by residents through participatory programs.

• KIEAE Journal
• /
• v.7 no.4
• /
• pp.23-30
• /
• 2007

In Korea, the top priority of the exterior space in the urban commercial street has been put on the road and parking for cars, not on the street for pedestrians, because of the lack of institutional urban planning, the land use of high density, the pursuit of maximum commercial profit, etc. Also, it is true that the form and facade of the street buildings which form the characteristics of the commercial street are regarded as the consumption-stimulating tool and, subsequently, are symbolized for commercial profit. This study starts from the recognition of reality, and, with the perspective of general plan for urban exterior space, tries to improve the environmental design of street space. Also, this study searches the ways to enhance the cultural, art, aesthetic and functional values of a city, as well as the ways to promote commercial activities and to perform commercial symbolism and pedestrian functions. This study aims at exploring the importance of street environmental design and the information of environmental design, so that the problems of current street environment, which generates the disorder and chaos of information, may be solved. Also, this study aims at promoting the continuous development for the future street environmental design and design plan.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.10a
• /
• pp.950-953
• /
• 2007

The Intelligent Space(ISpace) provides challenging research fields for surveillance, human-computer interfacing, networked camera conferencing, industrial monitoring or service and training applications. ISpace is the space where many intelligent devices, such as computers and sensors, are distributed. According to the cooperation of many intelligent devices, the environment, it is very important that the system knows the location information to offer the useful services. In order to achieve these goals, we present a method for representing, tracking and human following by fusing distributed multiple vision systems in ISpace, with application to pedestrian tracking in a crowd.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.12
• /
• pp.1053-1060
• /
• 2016

As location recognition for autonomous vehicles develops, the need for a precise map for autonomous driving has increased. A precise map must be built based upon accurate position. Recent studies have accelerated research in this area by using various sensors that calculate the accurate position by comparing and recognizing objects around the roads. However, application of such methods is limited because these studies only take objects with significant verticality into consideration. Thus, new research is needed to overcome the limitations: a method that is not constrained by the existence of certain types of surrounding objects shall be proposed. Most roads contain road marking information, such as lanes, direction signs, and pedestrian crossings. Such information on the road surface is a valuable resource for building a precise map. This paper proposes a method of building a precise map by using road marking information.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.25-27
• /
• 2021

With the recent development of deep learning technology, computer vision-based AI technologies have been studied to analyze the abnormal behavior of objects in image information acquired through CCTV cameras. There are many cases where surveillance cameras are installed in dangerous areas or security areas for crime prevention and surveillance. For this reason, companies are conducting studies to determine major situations such as intrusion, roaming, falls, and assault in the surveillance camera environment. In this paper, we propose a real-time abnormal behavior analysis algorithm using object detection and tracking method.