• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.109-123
• /
• 2024

Research into vision-based end-to-end autonomous driving systems utilizing deep learning and reinforcement learning has been steadily increasing. These systems typically encode continuous and high-dimensional vehicle states, such as location, velocity, orientation, and sensor data, into latent features, which are then decoded into a vehicular control policy. The complexity of urban driving environments necessitates the use of state representation learning through networks like Variational Autoencoders (VAEs) or Convolutional Neural Networks (CNNs). This paper analyzes the impact of different image state encoding methods on reinforcement learning performance in autonomous driving. Experiments were conducted in the CARLA simulator using RGB images and semantically segmented images captured by the vehicle's front camera. These images were encoded using VAE and Vision Transformer (ViT) networks. The study examines how these networks influence the agents' learning outcomes and experimentally demonstrates the role of each state representation technique in enhancing the learning efficiency and decision- making capabilities of autonomous driving systems.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.6
• /
• pp.85-92
• /
• 2010

In this paper, we propose a Clustering-based Cooperative Routing using OFDM (CCRO) for supporting transmission efficiency in mobile wireless sensor networks. The main features and contributions of the proposed method are as follows. First, the clustering method which uses the location information of nodes as underlying infrastructure for supporting stable transmission services efficiently is used. Second, cluster-based cooperative data transmission method is used for improving data transmission and reliability services. Third, OFDM based data transmission method is used for improving data transmission ratio with channel efficiency. Fourth, we consider realistic approach in the view points of the mobile ad-hoc wireless sensor networks while conventional methods just consider fixed sensor network environments. The performance evaluation of the proposed method is performed via simulation using OPNET and theoretical analysis. The results of performance evaluation show improvement of transmission efficiency.

• Journal of the Korea Institute of Construction Safety
• /
• v.2 no.2
• /
• pp.63-69
• /
• 2019

Building Construction projects are getting higher and larger. Therefore, the use of Tower Crane, which is more productive than any other lifting plan shows a trend of continuous increases. However as equipment for transporting heavy goods, are is too expensive for the monthly rent and used inefficiently for construction. site so it is analyzed that it has problems of reducing productivity and efficiency of lifting work. Inefficient situations are arising like poor communications between operator and worker, occurrence of blind spots, securing the shortest distance of fire during movement after lifting plan, influences of weather, location of materials, movement radius of tower crane by each locations and ever-changing working environments. Therefore, in this study, we first made a list of tower cranes that are inefficiently used at the site, and then we made a checklist. After that, through field visits, we derived checklist for Tower Crane to comprehensive data value.

• Journal of the Korea Convergence Society
• /
• v.6 no.1
• /
• pp.7-16
• /
• 2015

A segmentation process extracts an interesting area of barcode in an image and gives a crucial impart on the performance of barcode verifier. Previous segmentation methods occurs some issues as follows. First, it is very hard to determine a threshold of length in Hough Line transform because it is sensitive. Second, Morphology transform delays the process when you conduct dilation and erosion operations during the image extraction. Therefore, we proposes a novel Converged Harris Corner detection-based segmentation method to detect an interesting area of barcode in Data Matrix. In order to evaluate the performance of proposed method, we conduct experiments by a dataset of barcode in accordance with size and location in an image. In result, our method solves the problems of delay and surrounding environments, threshold setting, and extracts the barcode area 100% from test images.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.775-778
• /
• 2008

Augmented Reality is a growing area in virtual reality research, The world environment around us provides a wealth of information that is difficult to duplicate in a computer. This evidenced by the worlds used in virtual environments. An augmented reality system generates a composite view for the user. It is a combination of the real scene viewed by the user and a virtual scene generated by the computer that augments the scene with addition information. The registration method represent to the user enhances that person's performance in and perception of the world. It decide the direction and location between real world and 3D graphic objects. The registration method devide two method, Model based tracking and Move-Matching. This paper researched at to generate a commerce correlation using a tracking object method, using at a color distribution and information, in the sequence scene.

• The Journal of the Korea Contents Association
• /
• v.9 no.11
• /
• pp.80-89
• /
• 2009

The importance of personalized services has been attracted in smart home environments according to the development of ubiquitous computering. In this paper, we proposed the smart home personalized service system based on context information using the speech recognition. The proposed service consists of an OSGi framework based service mobile manager, service manager, voice recognition manager, and location manager. Also, this study defines the smart home space and configures the commands of units, sensor information, and user information that are largely used in the defined space as context information. In particular, this service identifies users who exist in the same space that shows a difficulty in the identification using RFID through the training model and pattern matching in voice recognition and supports the personalized service of smart home applications. In the results of the experiment, it was verified that the OSGi based automated and personalized service can be achieved through verifying users in the same space.

• The KIPS Transactions:PartC
• /
• v.16C no.5
• /
• pp.621-628
• /
• 2009

Wireless sensor networks (WSNs) have been considered as a promising method for reliably monitoring both civil and military environments under hazardous or dangerous conditions. Due to the special property and difference from the traditional wireless network, the lifetime of the whole network is the most important aspect. The bottleneck nodes widely exist in WSNs and lead to decrease the lifetime of the whole network. In order to find out the bottleneck nodes, the traditional centralized bottleneck detection method MINCUT has been proposed as a solution for WSNs. However they are impractical for the networks that have a huge number of nodes. This paper first proposes a distributed algorithm called DBND (Distributed Bottleneck Node detection) that can reduce the time for location information collection, lower the algorithm complexity and find out the bottleneck nodes quickly. We also give two simple suggestions of how to solve the bottleneck problem. The simulation results and analysis show that our algorithm achieves much better performance and our solutions can relax the bottleneck problem, resulting in the prolonging of the network lifetime.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.3
• /
• pp.77-85
• /
• 2017

Tangible Space is a new emerging interaction space with mobile AR/VR computing and ubiquitous computing environment with IoT. Tangible Space spans from a physical environment augmented with virtual entities to immersive virtual environments mirroring the physical environment. Interacting with Tangible Space is logged just like interacting with the Web. By webizing Tangible Space, we can gain persistence as a by-product so that human life experience in the physical environment can be logged and shared just like the information being created and shared in the current Web. The result is a powerful future direction of the web from a World Wide Web of Information to World Wide Web of Life experiences.

• Journal of the Korea Institute of Building Construction
• /
• v.13 no.6
• /
• pp.557-564
• /
• 2013

Unsafe and dangerous factors or environments on building construction sites often cause safety accidents. Sometimes, accidents happen despite the existence of warning and caution signs. Such warning signs are likely to be hidden by stacked materials or temporary facilities on site. If workers cannot see the signs when moving or working, they could be injured, sometimes fatally. Many studies have focused on each worker's position, and various systems have been developed using GPS signals and sensors. This paper suggests a method for identifying the problem of worker inability to see the unsafe factors, to manage the problem in the construction planning phase by considering things from the worker's perspective. The method uses CAD software to investigate the relation between the height of stacked materials and the visible ratio of the unsafe factor. The results of a sample project show that the changes in the height and location of stacked materials make the site safer.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.1
• /
• pp.77-82
• /
• 2004

In this paper we present a barcode reader to decode two-dimensional symbology PDF417 and propose a novel method to extract the bar-space Patterns directly from the gray-level barcode image, which employs the location and the distance between extreme points of each row or column of the barcode image. This algerian proves to be very robust from the high convolutional distortion environments such as defocussing and warping, even under badly illuminating condition. If the scanned barcode image is a result of the convolution of a Gaussian-shaped point spread function with a hi-level image, popular image segmentation methods such as image thresholding can not distinguish between very narrow bar-space patterns. The Proposed algorithm shows improved Performance over current barcode readers.