• Smart Structures and Systems
• /
• v.24 no.6
• /
• pp.723-732
• /
• 2019

Globally road transport networks are subjected to continuous levels of stress from increasing loading and environmental effects. As the most popular mean of transport in the UK the condition of this civil infrastructure is a key indicator of economic growth and productivity. Structural Health Monitoring (SHM) systems can provide a valuable insight to the true condition of our aging infrastructure. In particular, monitoring of the displacement of a bridge structure under live loading can provide an accurate descriptor of bridge condition. In the past B-WIM systems have been used to collect traffic data and hence provide an indicator of bridge condition, however the use of such systems can be restricted by bridge type, assess issues and cost limitations. This research provides a non-contact low cost AI based solution for vehicle classification and associated bridge displacement using computer vision methods. Convolutional neural networks (CNNs) have been adapted to develop the QUBYOLO vehicle classification method from recorded traffic images. This vehicle classification was then accurately related to the corresponding bridge response obtained under live loading using non-contact methods. The successful identification of multiple vehicle types during field testing has shown that QUBYOLO is suitable for the fine-grained vehicle classification required to identify applied load to a bridge structure. The process of displacement analysis and vehicle classification for the purposes of load identification which was used in this research adds to the body of knowledge on the monitoring of existing bridge structures, particularly long span bridges, and establishes the significant potential of computer vision and Deep Learning to provide dependable results on the real response of our infrastructure to existing and potential increased loading.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.9
• /
• pp.49-55
• /
• 2021

In this paper, an enhanced 2-stage vehicle license plate detection scheme using object segmentation is proposed to detect accurately the rotated license plates due to the inclined photographing angles in real-road situations. With the previous 3-stage vehicle license plate detection pipeline model, the detection accuracy is likely decreased as the license plates are declined. To resolve this problem, we propose an enhanced 2-stage model by replacing the frontal two processing stages which are for detecting vehicle area and vehicle license plate respectively in only rectangular shapes in the previous 3-stage model with one step to detect vehicle license plate in arbitrarily shapes using object segmentation. According to the comparison results in terms of the detection accuracy of the proposed 2-stage scheme and the previous 3-stage pipeline model against the rotated license plates, the accuracy of the proposed 2-stage scheme is improved by up to about 20% even though the detection process is simplified.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.3
• /
• pp.1-11
• /
• 2021

NC Soft will continue to dream of an entertainment innovation world where customers are connected through game and contents. NC Soft images an expansion in entertainment industry which open doors to the future of enjoy break through innovative online game and creative AI & IT technologies, focused on new business opportunities that are solely NC's own. This study starts with the implication on why focusing on exploration innovation and exploitation strategy at the same time in NC Soft is so challenging. NC Soft manages to their online & mobile gaming competencies in the long term and achieves their sustainable growth by incremental innovation (e.g. game planning, game programming, and graphic design). Also, for innovative success, pursuing exploration strategy is essential. NC Soft have built a strategic alliance spanning K-POP, digital contents platform, movie, and animation, sharing the connectivity of entertainment domains with major contents corporations. The findings of this study would also beneficial to entertainment and contents corporation executives and could provide some road-map on managing the dual challenges of exploration and exploitation implementations.

• Smart Media Journal
• /
• v.12 no.9
• /
• pp.159-170
• /
• 2023

It takes a lot of time and manpower to search for the missing. As part of the solution, a missing person search AI system was implemented using a YOLO-based model. In order to train object detection models, the model was learned by collecting recognition images (road fixation) of drone mobile objects from AI-Hub. Additional mountainous terrain datasets were also collected to evaluate performance in training datasets and other environments. In order to optimize the missing person search AI system, performance evaluation based on model size and hyperparameters and additional performance evaluation for concerns about overfitting were conducted. As a result of performance evaluation, it was confirmed that the YOLOv5-L model showed excellent performance, and the performance of the model was further improved by applying data augmentation techniques. Since then, the web service has been applied with the YOLOv5-L model that applies data augmentation techniques to increase the efficiency of searching for missing people.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.59-64
• /
• 2024

Recently, research on the convergence of drones and artificial intelligence technologies have been conducted in various industrial fields. In this paper, we propose an illegal parking vehicle recognition model using deep learning-based object recognition and classification algorithms. The model of object recognition and classification consist of YOLOv8 and ResNet18, respectively. The proposed model was trained using image data collected in general road environment, and the trained model showed high accuracy in determining illegal parking. From simulation results, it was confirmed that the proposed model has generalization performance to identify illegal parking vehicles from various images.

• Economic and Environmental Geology
• /
• v.57 no.1
• /
• pp.17-23
• /
• 2024

Ground penetrating radar (GPR) survey is a geophysical method that utilizes electromagnetic waves reflecting from a boundary where the electromagnetic property changes. As the frequency of the antenna is about 25 MHz ~ 1 GHz, it is effective to acquire high resolution images of underground pipe, artificial structure, underground cavity, and underground structure. In this study, we analyzed the change of signals reflected from the same underground objects according to the arrangement of transceiver antennas used in ground penetrating radar survey. The antenna used in the experiment was 200 MHz, and the survey was performed in the vertical direction across the sewer and the parallel direction along the sewer to the sewer buried under the road, respectively. A total of five antenna array methods were applied to the survey. The most used arrangement is when the transmitting and receiving antennas are all perpendicular to the survey line (PR-BD). The PR-BD arrangement is effective when the object underground is a horizontal reflector with an angle of less than 30°, such as the sewer under investigation. In this case study, it was confirmed that the transmitter and receiver antennas perpendicular to the survey line (PR-BD) are the most effective way to show the underground structure. In addition, in the case where the transmitting and receiving antennas are orthogonal to each other (XPOL), no specific reflected wave was observed in both experiments measured across or parallel to the sewer. Therefore, in the case of detecting undiscovered objects in the underground, the PR-BD array method in which the transmitting and receiving antennas are aligned in the direction perpendicular to the survey line taken as a reference and the XPOL method in which the transmitting and receiving antennas are orthogonal to each other are all used, it can be effective to apply both of the above arrangements after setting the direction to 45° and 135°.

• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.1-10
• /
• 2024

Individuals with visual impairments face numerous challenges in their daily lives, with navigating streets and public spaces being particularly daunting. The inability to identify safe crossing locations and assess the feasibility of crossing significantly restricts their mobility and independence. Globally, an estimated 285 million people suffer from visual impairment, with 39 million categorized as blind and 246 million as visually impaired, according to the World Health Organization. In Saudi Arabia alone, there are approximately 159 thousand blind individuals, as per unofficial statistics. The profound impact of visual impairments on daily activities underscores the urgent need for solutions to improve mobility and enhance safety. This study aims to address this pressing issue by leveraging computer vision and deep learning techniques to enhance object detection capabilities. Two models were trained to detect objects: one focused on street crossing obstacles, and the other aimed to search for objects. The first model was trained on a dataset comprising 5283 images of road obstacles and traffic signals, annotated to create a labeled dataset. Subsequently, it was trained using the YOLOv8 and YOLOv5 models, with YOLOv5 achieving a satisfactory accuracy of 84%. The second model was trained on the COCO dataset using YOLOv5, yielding an impressive accuracy of 94%. By improving object detection capabilities through advanced technology, this research seeks to empower individuals with visual impairments, enhancing their mobility, independence, and overall quality of life.

• Journal of the Korean Society of Safety
• /
• v.39 no.1
• /
• pp.62-69
• /
• 2024

Ensuring swift on-site access to fire engines is crucial in preserving the golden time and minimizing damage. However, various mobility constraints in alleyways hinder the timely entry of fire engines to the fire scene, significantly impairing their initial response capabilities. Therefore, this study analyzed the significant mobility constraints of fire engines, focusing on Seoul, which has many old town areas. By leveraging survey responses from firefighting experts and actual observations, this study quantitatively assessed the frequency and severity of mobility constraint factors affecting the disaster responses of fire engines. Survey results revealed a consistent set of top five factors regarding the frequency and disturbance level, including illegally parked cars, narrow paths, motorcycles, poles, and awnings/banners. A comparison with actual road-view images showed notable consistency between the survey and observational results regarding the appearance frequency of mobility constraint factors in vulnerable areas in Seoul. Furthermore, the study emphasized the importance of tailored management strategies for each mobility constraint factor, considering its characteristics, such as dynamic or static. The findings of this study can serve as foundational data for creating more detailed fire safety maps and advancing technologies that monitor the mobility of fire engines through efficient vision-based inference using CCTVs in the future.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.41 no.1
• /
• pp.1-11
• /
• 2013

In nature, to change the consciousness of those who wish to pursue something new, the road is turning function-oriented 'Walking Path' into purpose-oriented 'Walking Trails'. Though 'Walking Trails' is a long linear journey that leads people to see, to feel and to experience while walking on the trail, but considering on the landscape of trails when selecting routes is lacking. Landscapes, which are felt and perceived while walking on the trail, provide a purpose, and can be an important factor to improve visitor satisfaction. However, the study is insufficient in terms of landscape of trails. Therefore, it is the purpose of this study to find ways to help improving visitors' satisfaction in selecting routes, by analyzing the images and preferences of trails landscapes that are visually perceived, by analyzing the correlation between visitors' satisfaction and them. For this study, landscape assessment was carried out after selecting representative landscape photos of BukhansanDulegil 13 sections and landscape images adjectives for landscape assessment. Through the assessment, analyze landscape images of each section, landscape images factors affecting a wish to walk and landscape preferences, relationship between visitors' satisfaction and them. 'Refreshing' image was higher on the path with many trees and less artificial elements; 'urban' image was higher on the path with artificial elements. 'A wish to walk' and 'landscape preference' was higher on the path showed 'refreshing' and 'pastoral' image with many natural elements. Factors affecting 'a wish to walk' were "refreshing-unpleasant", "impressive-ordinary", factors affecting 'landscape preference' were "refreshing-unpleasant", "comfortable-uncomfortable". In addition, landscape preference was found to have a high correlation with visitors' satisfaction.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.23 no.3
• /
• pp.1-11
• /
• 2020

The purpose of this study is to conduct an analysis for classification of unexecuted urban planning facilities using the Geographic Information System(GIS) to prepare measures for systematic and efficient management of unexecuted urban planning facilities and to find ways to establish national territory information for continuous management and operation by database of spatial data of classified unexecuted urban planning facilities. For this purpose, the present state of urban management plan, thematic map, cadastral map, satellite image of Korea Land Information System(KLIS) were collected from Miryang City, and qualitative analysis of the execution and non-execution of urban planning facilities was conducted by combining the layer of urban planning facilities, satellite images, and continuous cadastral layers of cadastral maps with classified and processed owner attribute information. According to the analysis, the unexecuted facilities were derived as unexecuted facilities, as most of the private land, without any current status roads or facilities created in satellite imagery. In addition, although the current status road was opened, the facilities that included some private land were derived as facilities that were recognized and executed by the local government as the de facto controlling entity through public transportation. The derived unexecuted urban planning facilities were divided into layers of shape data and the unexecuted property data were organized to quickly and accurately identify the status of non-executed and statistical information. In this study, we proposed an analysis plan that introduced GIS technology for scientific and rational analysis of unexecuted urban planning facilities and the establishment of reliable spatial data, and proposed a plan to establish a database for connection with existing systems and use of information.