• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.8
• /
• pp.3647-3653
• /
• 2012

In active noise control filter, IIR filter structure which used for control filter assures the stability property. The stability characteristics of IIR filter structure is mainly determined by pole location of control filter within unit disc, so stable selection of the value of control filter coefficient is very important. In this paper, we proposed novel adaptive stabilized Filtered_U LMS algorithms with IIR filter structure which has better convergence speed and less computational burden than conventional FIR structures, for multi-channel active noise control with vehicle enclosure signal case. For better convergence speed in adaptive algorithms, fuzzy LMS algorithms where convergence coefficient computed by a fuzzy PI type controller was proposed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• pp.1996-2015
• /
• 2023

High-definition (HD) maps can provide precise road information that enables an autonomous driving system to effectively navigate a vehicle. Recent research has focused on leveraging semantic segmentation to achieve automatic annotation of HD maps. However, the existing methods suffer from low recognition accuracy in automatic driving scenarios, leading to inefficient annotation processes. In this paper, we propose a novel semantic segmentation method for automatic HD map annotation. Our approach introduces a new encoder, known as the convolutional transformer hybrid encoder, to enhance the model's feature extraction capabilities. Additionally, we propose a multi-level fusion module that enables the model to aggregate different levels of detail and semantic information. Furthermore, we present a novel decoupled boundary joint decoder to improve the model's ability to handle the boundary between categories. To evaluate our method, we conducted experiments using the Bird's Eye View point cloud images dataset and Cityscapes dataset. Comparative analysis against stateof-the-art methods demonstrates that our model achieves the highest performance. Specifically, our model achieves an mIoU of 56.26%, surpassing the results of SegFormer with an mIoU of 1.47%. This innovative promises to significantly enhance the efficiency of HD map automatic annotation.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.71-80
• /
• 2024

In this study, a proposed ensemble learning technique aims to enhance the semantic segmentation performance of images captured by Unmanned Aerial Vehicles (UAVs). With the increasing use of UAVs in fields such as urban planning, there has been active development of techniques utilizing deep learning segmentation methods for land cover segmentation. The study suggests a method that utilizes prominent segmentation models, namely U-Net, DeepLabV3, and Fully Convolutional Network (FCN), to improve segmentation prediction performance. The proposed approach integrates training loss, validation accuracy, and class score of the three segmentation models to enhance overall prediction performance. The method was applied and evaluated on a land cover segmentation problem involving seven classes: buildings,roads, parking lots, fields, trees, empty spaces, and areas with unspecified labels, using images captured by UAVs. The performance of the ensemble model was evaluated by mean Intersection over Union (mIoU), and the results of comparing the proposed ensemble model with the three existing segmentation methods showed that mIoU performance was improved. Consequently, the study confirms that the proposed technique can enhance the performance of semantic segmentation models.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.2
• /
• pp.225-231
• /
• 2013

A bird's-eye view is an elevated view of an object from above, with a perspective as though the observer were a bird, often used in the making of blueprints, floor plans and maps. It can be used under severe weather conditions when visibility is poor. Under low visibility environments, drivers can communicate each other using V2V communication to get each vehicle's status to prevent collision and other accidents. Ubiquitous transportation sensor networks(u-TSN) and its application are emerging rapidly as an exciting new paradigm to provide reliable and comfortable transportatione services. The ever-growing u-TSN and its application will provide an intelligent and ubiquitous communication and network technology for traffic safety area.

• Journal of Information Technology Services
• /
• v.12 no.2
• /
• pp.171-184
• /
• 2013

Frequently faced with dangerous situations, for evidentiary purpose in case of civil and criminal liability challenges, car drivers in Korea have been armed with so-called 'black boxes'; however, which are just video recorders in vehicles rather than real 'black boxes' that are equipped in the airplanes. In the United States, they are called EDRs(Event Data Recorders), more technically, which means that they record data of events happened while driving, such as velocity changes, airbags deployment, seatbelt wearing etc. just like in the airplanes. EDR technology is quickly becoming more advanced, more widely available, and less expensive; however, new concerns are emerging : the privacy of drivers. In U. S., vehicle manufacturers and insurance companies and the governmental agencies including the courts and legislatures are the main parties in terms of the EDR concerns. In order to determine the best way to regulate EDR, it is necessary to balance all the merits, such as safety, privacy, truth, justice and efficiency, to support a legal framework regulating the EDR concerns. This article, in light of the regulation of EDR and experience therof in the United States, examines EDR technology itself, particularly with respect to the automobile industry, describing its history, its current state, and trends that may change it in the future; and explains how the National Highway Transportation Safety Agency (NHTSA), legislatures, courts have approached EDR data. At the early stage of regulation on EDRs in Korea, examining U. S. legal framework and usages would help for successful establishment of legislation and regulation.

• Journal of Navigation and Port Research
• /
• v.35 no.3
• /
• pp.197-204
• /
• 2011

The authors adopt the Unmanned Undersea Vehicle(UUV), the shape of which is like a manta. They call here it Manta UUV. Manta UUV has been designed from the similar concept of the UUV called Manta Test Vehicle(MTV), which was originally built by the Naval Undersea Warfare Center of USA(Lisiewicz and French, 2000; Simalis et al., 2001; U.S. Navy, 2004). The present study deals with the effect of Reynolds numbers on hydrodynamic forces acting on Manta UUV at large angles of attack. The large angles of attack cover the whole range of 0 to ${\pm}$ 180 degrees in horizontal plane and in vertical plane respectively. Static test at large attack angles has been carried out with two Manta UUV models in circulating water channel. The authors assume that the experimental results of hydrodynamic forces (lateral force, yaw moment, vertical force and pitch moment) are analyzed into two components, which are lift force component and cross-flow drag component. First of all, Based on two dimensional cross-flow drag coefficient at 90 degrees of attack angle, the cross-flow drag component at whole range of attack angles is calculated. Then the remainder is assumed to be the lift force component. The only cross-flow drag component is assumed to be subject to Reynolds number.entstly the authors suggest the methodology to predict hydrodynamic derivertives acting on the full-scale Manta UUV.

• Journal of Korean Society of Transportation
• /
• v.27 no.4
• /
• pp.167-173
• /
• 2009

It is important to study on the traffic accident severity reduction because traffic accident is an issue that is directly related to human life. Therefore, this research developed countermeasure to reduce traffic accident severity considering various factors that affect the accident severity. This research developed the Accident Severity Prediction Model using the collected accident data from Seohaean Expressway in 2004~2006. Through this model, we can find the influence factors and methodology to reduce accident severity. The results show that speed limit violation, vehicle defects, vehicle to vehicle accident, vehicle to person accident, traffic volume, curve radius CV(Coefficient of variation) and vertical slope CV were selected to compose the accident severity model. These are certain causes of the severe accident. The accidents by these certain causes present specific sections of Seohaean Expressway. The results indicate that we can prevent severe accidents by providing selected traffic information and facilities to drivers at specific sections of the Expressway.

• Journal of Korean Society of Transportation
• /
• v.28 no.5
• /
• pp.91-106
• /
• 2010

Recently, interest in supply chain management is rising along with the increasing oil prices and traffic congestion. In particular, people started studying the issue, but realized that advantageous strategies for suppliers and retailers are not always advantageous to a carrier. Therefore, in this study the atuhors set up a simulation scenario to understand delivery vehicle routing problems under various inventory policies, namely Economic Order Quantity (EOQ) and Periodic Order Quantity (POQ) and network configurations. First, the authors made a virtual supply chain. Then they analyzed characteristics of delivery vehicle routing under various inventory policies (EOQ and POQ) and network configurations. As a result, the POQ inventory policy decreases the number of vehicles, the number of drivers, and the service time of vehicles. Also, the centralized network increases the load factor of vehicles and decreases the service time of vehicles. In other words, the centralized network and the POQ inventory policy are better for the carrier. These results show a savings of 15,556,806 won ($13,389.10) in a month: a reduction of 17%.

• Electronics and Telecommunications Trends
• /
• v.22 no.1 s.103
• /
• pp.114-118
• /
• 2007

국내외적으로 지능형 차량 및 텔레매틱스/ITS 연구 개발을 통해서 차량에 IT 기술 접목을 위한 노력을 가속화하고 있다. 우리나라의 경우 산업자원부가 미래 10대 전략품목으로 자동차 부분에서 지능형 차량을 선정하였으며, 정보통신부는 u-IT839의 핵심서비스로 텔레매틱스/ITS 서비스를 추진하고 있다. EU는 i2010 Flagship에서 intelligentcar initiative 프로젝트를 통해 지능형 차량 및 보안을 위한 전략 수립과 세부과제를 수행하고 있다. 또한, IEEE 802.11p/P1609(WAVE)와 ISO TC204/WG16CALM에서는 차량 통신 보안 및 서비스에 대해서 고려하고 있다. 현재 지능형 차량과 관련하여서는 다양한 사업 모델이 제시되고 있으며, 자동차 업계의 BM과 이동통신 업계의 AM이 동반 성장하고 있다. 본 기고문은 지능형 차량 및 텔레매틱스/ITS와 관련한 보안 기술 동향을 살펴본다.

• Journal of Korean Institute of Industrial Engineers
• /
• v.36 no.4
• /
• pp.243-247
• /
• 2010

Every products, which made by mass production, is not identical in their size but have variations in some intervals specified by tolerance dimensions. Tolerances play major role in standardization of part and its quality, and also make a huge impact on manufacturing cost. The optimal condition for tolerances is giving the values as loose as possible for low production cost while satisfying quality specification, which usually demand tight control of tolerances. Tolerance analysis is necessary to get an optimal solution for this conflict situation. This paper have studied tolerance analysis for universal joint assembly of vehicle steering system and tried to find useful results of the study for product design and quality control.