• 한국멀티미디어학회논문지
• /
• 제22권10호
• /
• pp.1149-1159
• /
• 2019

We present a novel deep learning architecture for obtaining a latent image from a single blurry image, which contains dynamic motion blurs through object/camera movements. The proposed architecture consists of two sub-modules: blur image restoration and optical flow estimation. The tasks are highly related in that object/camera movements make cause blurry artifacts, whereas they are estimated through optical flow. The ablation study demonstrates that training multi-task architecture simultaneously improves both tasks compared to handling them separately. Objective and subjective evaluations show that our method outperforms the state-of-the-arts deep learning based techniques.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.896-902
• /
• 2004

The purpose of the study of multi-robot system is to realize multi-robot system easy for the control of robot system in case robot is adapted in the complicated environment of task structure. The purpose of the study of multi-robot system is to realize multi-robot system easy for the control of robot system in case robot is adapted in the complicated environment of task structure. To make real time control possible by making effective use of recognized information in this dynamic environment, suitable distribution of tasks should be made in consideration of function and role of each performing robots. In this paper, IHMA (Intelligent Hybrid Modular Architecture) of Intelligent combined control architecture which utilizes the merits of deliberative and reactive controllers will be suggested and its efficiency will be evaluated through the adaptation of control architecture to representative multi-robot system.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2020년도 추계학술대회
• /
• pp.25-28
• /
• 2020

Automatic segmentation of brain tissues such as WM, GM, and CSF from brain MRI scans is helpful for the diagnosis of many neurological disorders. Accurate segmentation of these brain structures is a very challenging task due to low tissue contrast, bias filed, and partial volume effects. With the aim to improve brain MRI segmentation accuracy, we propose an end-to-end convolutional based U-SegNet architecture designed with multi-scale kernels, which includes cascaded dilated convolutions for the task of brain MRI segmentation. The multi-scale convolution kernels are designed to extract abundant semantic features and capture context information at different scales. Further, the cascaded dilated convolution scheme helps to alleviate the vanishing gradient problem in the proposed model. Experimental outcomes indicate that the proposed architecture is superior to the traditional deep-learning methods such as Segnet, U-net, and U-Segnet and achieves high performance with an average DSC of 93% and 86% of JI value for brain MRI segmentation.

• 한국자동차공학회논문집
• /
• 제24권2호
• /
• pp.127-136
• /
• 2016

The camera based object detection systems should satisfy the recognition performance as well as real-time constraints. Particularly, in safety-critical systems such as Autonomous Emergency Braking (AEB), the real-time constraints significantly affects the system performance. Recently, multi-core processors and system-on-chip technologies are widely used to accelerate the object detection algorithm by distributing computational loads. However, due to the advanced hardware, the complexity of system architecture is increased even though additional hardwares improve the real-time performance. The increased complexity also cause difficulty in migration of existing algorithms and development of new algorithms. In this paper, to improve real-time performance and design complexity, a task scheduling strategy is proposed for visual object tracking systems. The real-time performance of the vision algorithm is increased by applying pipelining to task scheduling in a multi-core processor. Finally, the proposed task scheduling algorithm is applied to crosswalk detection and tracking system to prove the effectiveness of the proposed strategy.

• International Journal of Computer Science & Network Security
• /
• 제21권2호
• /
• pp.1-8
• /
• 2021

Cloud computing has proven its efficiency, especially after the increasing number of cloud services offered by a wide range of cloud providers, from different domains. Despite, these cloud services are mostly heterogeneous. Consequently, and due to the rising interest of cloud consumers to adhere to a multi-cloud environment instead of being locked-in to one cloud provider, the need for semantically interconnecting different cloud services from different cloud providers is a crucial and important task to ensure. In addition, considerable research efforts proposed interoperability solutions leading to different representation models of cloud services. In this work, we present our solution to overcome this limitation, precisely in the IAAS service model. This solution is a framework permitting the semantic interoperability of different IAAS resources in a multi-cloud environment, in order to assist cloud consumers to retrieve the cloud resource that meets specific requirements.

• Journal of Mechanical Science and Technology
• /
• 제15권5호
• /
• pp.544-554
• /
• 2001

A shop floor can be considered as an important level to develop Computer Integrated Manufacturing system (CIMs). However, a shop floor is a dynamic environment where unexpected events continuously occur, and impose changes to the planned activities. To deal with this problem, a shop floor should adopt an appropriate control system that is responsible for the coordination and control of the manufacturing physical flow and information flow. In this paper, a hybrid control system is described with a shop floor activity methodology called Multi-Layered Task Initiation Diagram (MTD). The architecture of the control model contains three levels: i.e., he shop floor controller (SFC), the intelligent agent controller (IAC) and the equipment controller (EC). The methodology behind the development of the control system is an intelligent multi-agent paradigm that enables the shop floor control system to be an independent, an autonomous, and distributed system, and to achieve an adaptability to change of the manufacturing environment.

• 한국공작기계학회논문집
• /
• 제14권5호
• /
• pp.27-34
• /
• 2005

To accomplish various and complex tasks by intelligent robots, improvement is needed not only in mechanical system architecture but also in control system architecture. Hybrid control architecture has been suggested as a mutually complementing architecture of the weak points of a deliberative and a reactive control. This paper addresses a control architecture of robots, and a behavior representation methodology. The suggested control architecture consists of three layers of deliberative, sequencing, and reactive as hybrid control architecture. Multi-layer behavior model is employed to represent desired tasks. 3D simulation will be conducted to verify the applicability of suggested control architecture and behavior representation method.

• 디지털콘텐츠학회 논문지
• /
• 제19권6호
• /
• pp.1219-1224
• /
• 2018

사물인터넷 (Internet of Things)은 우리의 실생활에서 그 범위가 급격히 커지면서, 스마트 모바일 장치들에 대용량 실시간 데이터를 모바일 환경에서 고속으로 처리 및 전송하기에 적합한 처리능력이 요구되고 있다. 배터리 파워가 중요한 모바일 기기에서 성능과 에너지 보존성을 높이기 위해 big.LITTLE 멀티코어 구조와 같은 비대칭 멀티코어 구조가 널리 사용되고 있다. 에너지 보존성을 높이기 위해서는 에너지 효율이 높은 LITTLE 코어의 활용도를 높여하며, 이룰 위해 본 논문에서는 실시간 태스크를 대상으로 하여 마감 시간을 보장하는 범위 내에서 LITTLE 코어에 우선적으로 할당하는 코어 선택 알고리즘을 제안하다. 또한, 시뮬레이션을 통하여 기존 기법에 비해 마감시간을 보장하면서 에너지 소비량을 줄 있 수 있음을 보였다.

• 한국멀티미디어학회논문지
• /
• 제24권8호
• /
• pp.1000-1011
• /
• 2021

In recent years, using Deep Learning methods to apply for medical and biomedical image analysis has seen many advancements. In clinical, using Deep Learning-based approaches for cancer image analysis is one of the key applications for cancer detection and treatment. However, the scarcity and shortage of labeling images make the task of cancer detection and analysis difficult to reach high accuracy. In 2015, the Unet model was introduced and gained much attention from researchers in the field. The success of Unet model is the ability to produce high accuracy with very few input images. Since the development of Unet, there are many variants and modifications of Unet related architecture. This paper proposes a new approach of using Unet++ with pretrained EfficientNet as backbone architecture for breast tumor cell nuclei segmentation and uses the multi-organ transfer learning approach to segment nuclei of breast tumor cells. We attempt to experiment and evaluate the performance of the network on the MonuSeg training dataset and Triple Negative Breast Cancer (TNBC) testing dataset, both are Hematoxylin and Eosin (H & E)-stained images. The results have shown that EfficientUnet++ architecture and the multi-organ transfer learning approach had outperformed other techniques and produced notable accuracy for breast tumor cell nuclei segmentation.

• 대한임베디드공학회논문지
• /
• 제2권4호
• /
• pp.242-250
• /
• 2007

Wireless sensor networks are subject to highly heterogeneous system requirements in terms of their functionality and performance due to their broad application areas. Though the heterogeneity hinders the opportunity of developing a single universal platform for sensor networks, efforts to provide uniform, inter-operable and scalable ones for sensor networks are still essential for the growth of the industry as well as their technological advance. As a part of our work to develop such a robust platform, this paper presents the software architecture for sensor nodes with focus on our sensor node operating system and its configuration methodology. Addressing principle issues in its design space which includes programming, execution, task scheduling and software layer models, our architecture is highly reconfigurable with respect to system resources and functional requirements and also highly efficient in supporting multi-threading under small system resources.