• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.5
• /
• pp.959-968
• /
• 2019

In the agricultural industry, wireless sensor network technology has being applied by utilizing various sensors and embedded systems. In particular, a lot of researches are being conducted to diagnose diseases of crops early by using sensor network. There are some difficulties on traditional research how to diagnose crop diseases is not practical for agriculture. This paper proposes the algorithm which enables to investigate and analyze the crop leaf image taken by image camera and detect the infected area within the image. We applied the enhanced k-means clustering method to the images captured at horticulture facility and categorized the areas in the image. Then we used the edge detection and edge tracking scheme to decide whether the extracted areas are located in inside of leaf or not. The performance was evaluated using the images capturing tomato leaves. The results of performance evaluation shows that the proposed algorithm outperforms the traditional algorithms in terms of classification capability.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1604-1611
• /
• 2020

Light field image captured by a microlens array-based camera has many limitations in practical use due to its low spatial resolution and angular resolution. High spatial resolution images can be easily acquired with a single image super-resolution technique that has been studied a lot recently. But there is a problem in that high angular resolution images are distorted in the process of using disparity information inherent among images, and thus it is difficult to obtain a high-quality angular resolution image. In this paper, we propose light field angular super-resolution that extracts an initial feature map using an dilated convolutional neural network in order to effectively extract the view difference information inherent among images and generates target image using a residual neural network. The proposed network showed superior performance in PSNR and subjective image quality compared to existing angular super-resolution networks.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.51-57
• /
• 2021

In this paper, we propose a method to find the DoF(Depth of field) that is blurred in an image by focusing and out-focusing the camera through a efficient convolutional neural network. Our approach uses the RGB channel-based cross-correlation filter to efficiently classify the DoF region from the image and build data for learning in the convolutional neural network. A data pair of the training data is established between the image and the DoF weighted map. Data used for learning uses DoF weight maps extracted by cross-correlation filters, and uses the result of applying the smoothing process to increase the convergence rate in the network learning stage. The DoF weighted image obtained as the test result stably finds the DoF region in the input image. As a result, the proposed method can be used in various places such as NPR(Non-photorealistic rendering) rendering and object detection by using the DoF area as the user's ROI(Region of interest).

• Convergence Security Journal
• /
• v.22 no.2
• /
• pp.59-66
• /
• 2022

Recently, smart home technology has been developed with a great response due to the convenience of home automation. Smart home technology provides various services by connecting various Internet of Things (IoT) and sensors to a home network through wired/wireless networks. In addition, the smart home service easily and conveniently controls lighting, energy, environment, and door cameras through a wall pad. However, while it has become a social issue due to the recent hacking accident of wall pads, personal information leakage and privacy infringement are expected. Accordingly, it is necessary to prepare preventive and countermeasures against security vulnerability factors of wall pads. Therefore, this study expects that it can be used as basic data for future smart home application and response technology development by examining the weak causes and countermeasures related to wall pads.

• 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.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.05a
• /
• pp.709-712
• /
• 2006

다양한 종류의 컴퓨터가 사람, 사물, 환경 속에 내재되어 있고, 이들이 서로 연결되어, 필요한 곳에서 활용할 수 있는 유비쿼터스 환경에서는 홈 네트워크를 통해 이 기종 기기간 다양한 데이터 교환을 요구한다. 더욱이 원활한 영상 데이터의 처리, 전송, 모니터링 기술은 핵심적 요소가 아닐 수 없다. 공간 및 시간적인 해상도, 컬러의 표현 그리고 화질의 측정방법 등 고전적 영상 처리 연구 분야뿐만 아니라 국한된 대역폭을 갖는 홈네트워크의 전송체계에서 전송률 문제에 대한 심도 있는 연구가 필요하다. 본 논문에서는 홈네트워크 상황에서 콘텐츠의 중심이 되는 영상 데이터의 전송과 처리 그리고 제어를 위하여 새로운 움직임 추정 알고리즘을 제안한다. 각도, 거리등 다양한 환경에서 전송되어지는 스테레오 카메라의 영상데이터들은 축소, 확대, 이동, 보정 등 전처리 후 제안된 변형계층 모션벡터 추정 알고리즘을 이용하여 압축 처리, 전송된다. 기존 모션벡터 추정 알고리즘의 장점을 계승하고 단점을 보완한 변형계층 알고리즘은 비정형, 소형 매크로 블록을 이용하여 휘도의 편차가 큰 영상의 효율적 움직임 추정에 이용된다. 본 논문에서 제안한 변형계층 알고리즘과 이를 이용해 구현된 영상시스템은 유비쿼터스 환경에서 다양하게 활용될 수 있다.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1952-1953
• /
• 2011

본 논문에서는 다항식 기반 Radial Basis Function(RBF)신경회로망(Polynomial based Radial Basis function Neural Network)을 설계하고 이를 n-클래스 패턴 분류 문제에 적용한다. 제안된 다항식기반 RBF 신경회로망은 입력층, 은닉층, 출력층으로 이루어진다. 입력층은 입력 벡터의 값들을 은닉층으로 전달하는 기능을 수행하고 은닉층과 출력층사이의 연결가중치는 상수, 선형식 또는 이차식으로 이루어지며 경사 하강법에 의해 학습된다. Networks의 최종 출력은 연결가중치와 은닉층 출력의 곱에 의해 퍼지추론의 결과로서 얻어진다. 패턴분류기의 최적화는 PSO(Particle Swarm Optimization)알고리즘을 통해 이루어진다. 그리고 제안된 패턴분류기는 실제 얼굴인식 시스템으로 응용하여 직접 CCD 카메라로부터 입력받은 데이터를 영상 보정, 얼굴 검출, 특징 추출 등과 같은 처리 과정을 포함하여 서로 다른 등록인물의 n-클래스 분류 문제에 적용 및 평가되어 분류기로써의 성능을 분석해본다.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.984-988
• /
• 2009

LCD를 이용해 화면상에 다양한 이미지를 제공하는 디지털액자는 디지털 카메라 사용의 대중화에 따라 지속적인 매출 증가를 보이고 있다. 디지털액자는 디지털 사진을 볼 수 있는 액정표시장치(LCD)로 된 제품으로써 현재는 디스플레이 시장 및 디지털 액자시장 성장, 디지털 기술 발전과 함께 다양한 포맷의 동영상을 지원하고, 음악을 재생하는가 하면 네트워크 기술까지 탑재한 다기능 디바이스(device)로 탈바꿈되고 있어 사용자를 위한 디지털 액자의 사용목적 및 기능에 따른 디지털 액자 형태의 세분화와 디자인 콘셉트는 더욱 다양화 될 것이다. 본 연구는 기존의 디지털 액자와 차별화 된 스마트픽쳐(Smart Picture)라는 제품 개발 콘셉트(Concept) 연구를 목적으로 한다. 스마트픽쳐(Smart Picture)라 함은 기존 디지털액자에서의 사진 및 동영상 보여주기 기능이외에도 전용화된 아트웍 (Artwork)형태의 전용화된 콘텐츠와 차별화된 형태와 재질을 가진 디지털액자를 뜻한다. 본 연구는 스마트픽쳐(Smart Picture) 개발을 위한 선행연구의 일환으로 제품 개발을 위한 콘셉트 디자인(Concept Design)연구를 목적으로 현재 시판되는 다양한 디지털액자와 관련된 사례분석과 디스플레이(Display)가 활용되는 분야 및 사용 콘텐츠(Contents) 사례 연구 조사, 디스플레이 활용분야, 미디어 작품 사례 조사를 통해 자료를 수집 및 아이디어 방향을 설정하고, 설정된 방향을 바탕으로 스마트픽쳐(Smart Picture)에 반영될 수 있는 아이디어 요소 도출 및 구체화 후에 스마트픽쳐(Smart Picture) 콘셉트 디자인 개념 제안까지를 연구 방향으로 한다.

• Journal of Korea Multimedia Society
• /
• v.7 no.8
• /
• pp.1058-1065
• /
• 2004

Embedded system is widely used in various applications from simple monitor to a set-top box with CPU, memory and hard disk drives. Specially, embedded OS is ported in moveable or small machinery since it ordinarily transmits multimedia data. In this paper, we propose Null copy scheme on the embedded linux system for multimedia service, which can reduce memory copy overhead from user address space to kernel one, and vice versa. Since embedded system for networked multimedia service has low level computing power as well as memory, the Null copy scheme can provide more improved QoS. Our image transmission experiment results on embedded linux target board(CPU utilization an Deadline miss rates) installed a web camera have shown that the proposed scheme can increase fast response and lower CPU overhead.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.23 no.1
• /
• pp.125-131
• /
• 2009

In this paper, we proposed the remote visual monitoring system on mobile robot platform. The proposed system is composed of ARM9 core PXA255 processor, micro CMOS camera and wireless network and the captured visual image is transmitted via 803.11b/g wireless LAN(WLAN) for remote visual monitoring operations. Robot platform maneuvering command is transmitted via WLAN from host and the $640{\times}480$, $320{\times}240$ pixel fixed visual image is transmitted to host at the rate of $3{\sim}10$ frames per second. Experimental system is implemented on Linux OS base and tested for remote visual monitoring operation and verified the proposed objects.