• Title/Summary/Keyword: 계층전파

Search Result 109, Processing Time 0.029 seconds

A Multiresolution Stereo Matching with Modified Census Transform and Adaptive Window (변형된 Census 변환과 적응적 윈도우를 이용한 다해상도 스테레오 정합)

  • Hong, Seok-Keun;Cho, Seok-Je
    • Annual Conference of KIPS
    • /
    • 2012.11a
    • /
    • pp.572-575
    • /
    • 2012
  • 본 논문은 스테레오 시각에서 3차원 정보를 얻기 위해 변형된 Census 변환과 적응적 윈도우를 이용한 다해상도 스테레오 영상 정합 방법을 제안하고자 한다. 영역 기반 기법으로 스테레오 영상의 대응점을 찾기 위해 탐색 화소 주변 영역의 기울기를 계산하여 윈도우의 크기 및 모양을 적응적으로 결정하고, 윈도우 영역의 정합 비용 함수는 변형된 Census 변환과 AD 연산 결과의 가중합으로 구한다. 정합 과정에서 계산복잡도를 줄이기 위해 계층적 다해상도 구조를 적용하여 영상 피라미드를 만들고, 정합의 정확성을 향상시키기 위해 정합 영역에 변위 평활성과 같은 제약 조건을 적용하여 변위를 전파하는 방법을 사용한다. 실험을 통해 제안한 방법이 변위 탐색 시간을 감소시킬 뿐만 아니라 정합의 타당성이 보장됨을 확인하고자 한다.

A Multiresolution Stereo Matching Using a Bilateral Filter Based on Graph-Cut (Bilateral 필터를 이용한 그래프 컷 기반의 다해상도 스테레오 정합)

  • Hong, Seok-Keun;Kim, Jeong-Yeop;Won, Jong-Woon;Cho, Seok-Je
    • Annual Conference of KIPS
    • /
    • 2013.11a
    • /
    • pp.1528-1531
    • /
    • 2013
  • 본 논문은 스테레오 시각에서 3차원 정보를 얻기 위해 bilateral filter를 이용한 그래프 컷 기반의 다해상도 스테레오 영상 정합 방법을 제안하고자 한다. 제안한 방법은 변위도에서 물체의 경계를 명확히 구분하기 위해 bilateral filter를 이용하여 그래프의 각 노드들을 연결하는 경로의 가중치를 결정하고 정합 비용을 통합한다. 정합 과정에서 계산복잡도를 줄이기 위해 계층적 다해상도 구조를 적용하여 영상 피라미드를 만들고, 정합의 정확성을 향상시키기 위해 정합 영역에 변위 평활성과 같은 제약 조건을 적용하여 변위를 전파하는 방법을 사용한다. 실험을 통해 제안한 방법이 변위 탐색 시간을 감소시킬 뿐만 아니라 기존의 그래프 컷의 단점을 보완할 수 있음을 확인하고자 한다.

Analysis of Input Factors of DNN Forecasting Model Using Layer-wise Relevance Propagation of Neural Network (신경망의 계층 연관성 전파를 이용한 DNN 예보모델의 입력인자 분석)

  • Yu, SukHyun
    • Journal of Korea Multimedia Society
    • /
    • v.24 no.8
    • /
    • pp.1122-1137
    • /
    • 2021
  • PM2.5 concentration in Seoul could be predicted by deep neural network model. In this paper, the contribution of input factors to the model's prediction results is analyzed using the LRP(Layer-wise Relevance Propagation) technique. LRP analysis is performed by dividing the input data by time and PM concentration, respectively. As a result of the analysis by time, the contribution of the measurement factors is high in the forecast for the day, and those of the forecast factors are high in the forecast for the tomorrow and the day after tomorrow. In the case of the PM concentration analysis, the contribution of the weather factors is high in the low-concentration pattern, and that of the air quality factors is high in the high-concentration pattern. In addition, the date and the temperature factors contribute significantly regardless of time and concentration.

A Multiresolution Stereo Matching Based Genetic Algorithm Using Local Feature Information (지역적 특징 정보를 이용한 유전 알고리즘 기반의 다해상도 스테레오 정합)

  • Hong, Seok-Keun;Cho, Seok-Je
    • Annual Conference of KIPS
    • /
    • 2010.11a
    • /
    • pp.758-761
    • /
    • 2010
  • 본 논문은 스테레오 시각에서 3차원 정보를 얻기 위해 지역적 특징 정보를 이용한 유전 알고리즘 기반의 다해상도 스테레오 영상 정합 방법을 제안하고자 한다. 스테레오 영상에서 대응점을 찾아 변위를 계산하는 문제는 최적화 기법으로 해결할 수 있다. 최적화 문제 해결에 우수한 유전 알고리즘을 이용해 조밀한 변위도를 구하고 정합의 효율성을 위해 계층적 다해상도 구조를 적용하여 영상 피라미드를 만든다. 그리고 변위도의 정확도를 높이기 위해 변위 전파 과정에서 지역적 특징 정보를 추출하여 이용한다. 실험을 통해 제안한 방법이 변위 탐색 시간을 감소시킬 뿐만 아니라 정합의 타당성이 보장됨을 확인하고자 한다.

Adaptive MAP Selection Method in HMIPv6 (계층적 Mobile IPv6에서의 적응적 MAP 선택방안)

  • Lee, Sang-Gun;Yu, Ji-Eun
    • Annual Conference of KIPS
    • /
    • 2008.05a
    • /
    • pp.808-811
    • /
    • 2008
  • HMIPv6는 핸드오버시 시그널링 오버헤드와 패킷 손실을 감소시키는데 목적이 있다. 그러나 HMIPv6는 성능 평가면에서 기존의 MIPv6보다 우수하지 못하다. HMIPv6 환경하에서 새로운 도메인에 진입한 MN이 MAP 선택시 최상위 MAP을 선택하여 CN과 통신할 경우 최상위 MAP에 부하가 집중되고 MN이 빈번하게 이동하거나 대용량서비스를 이용하게 되면 성능이 저하되고, 반대로 MN이 최하위 MAP을 선택하여 CN과 통신할 경우에는 HA나 CN에 대한 Binding Update 시그널 증가로 성능이 저하된다. 이에 본 논문에서는 MN이 MAP 선택시 Distance, 노드사용율 및 대역폭 사용율을 바탕으로 MAP을 선택하는 적응적 MAP을 선택하는 방안에 대해서 논하고자 한다.

Improved AR-FGS Coding Scheme for Scalable Video Coding (확장형 비디오 부호화(SVC)의 AR-FGS 기법에 대한 부호화 성능 개선 기법)

  • Seo, Kwang-Deok;Jung, Soon-Heung;Kim, Jin-Soo;Kim, Jae-Gon
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.31 no.12C
    • /
    • pp.1173-1183
    • /
    • 2006
  • In this paper, we propose an efficient method for improving visual quality of AR-FGS (Adaptive Reference FGS) which is adopted as a key scheme for SVC (Scalable Video Coding) or H.264 scalable extension. The standard FGS (Fine Granularity Scalability) adopts AR-FGS that introduces temporal prediction into FGS layer by using a high quality reference signal which is constructed by the weighted average between the base layer reconstructed imageand enhancement reference to improve the coding efficiency in the FGS layer. However, when the enhancement stream is truncated at certain bitstream position in transmission, the rest of the data of the FGS layer will not be available at the FGS decoder. Thus the most noticeable problem of using the enhancement layer in prediction is the degraded visual quality caused by drifting because of the mismatch between the reference frame used by the FGS encoder and that by the decoder. To solve this problem, we exploit the principle of cyclical block coding that is used to encode quantized transform coefficients in a cyclical manner in the FGS layer. Encoding block coefficients in a cyclical manner places 'higher-value' bits earlier in the bitstream. The quantized transform coefficients included in the ealry coding cycle of cyclical block coding have higher probability to be correctly received and decoded than the others included in the later cycle of the cyclical block coding. Therefore, we can minimize visual quality degradation caused by bitstream truncation by adjusting weighting factor to control the contribution of the bitstream produced in each coding cycle of cyclical block coding when constructing the enhancement layer reference frame. It is shown by simulations that the improved AR-FGS scheme outperforms the standard AR-FGS by about 1 dB in maximum in the reconstructed visual quality.

A Dynamic Reorganization Method using the Hierarchical Structure in the Grid Database (그리드 데이터베이스에서 계층 구조를 이용한 동적 재조직 기법)

  • Cheon, Jong-Hyeon;Jang, Yong-Il;Cho, Sook-Kyoung;Lee, Soon-Jo;Bae, Hae-Young
    • Journal of Korea Spatial Information System Society
    • /
    • v.8 no.1 s.16
    • /
    • pp.93-106
    • /
    • 2006
  • A Grid Database is a database management system to process effectively and use the distributed data in a grid computing environment. Spatial data is more important than other general data according to the local characteristics and requires a large storage. The grid database can be used as the optimal system for the management of the spatial data. However, contrary to the conventional distributed database systems, the Grid Database which guarantees the local autonomy has a possibility not to provide an effective system, or it is impossible to use a centralized management environment. In order to allow flexible responses to a dynamically changing environment, it is required to use effectively reorganized method. In this paper, hierarchical reorganization method is presented for dynamic reorganization in a grid database. When the reorganization is conducted, an organizer is created to collect the information of databases. In addition, the organizer which is constructed by the hierarchical structure supports information communication and reorganization, and then it allows the support of regional reorganization operation and effective balance control. The performance assessment of the proposed method shows that the processing capacity is increased after the reorganization.

  • PDF

A Study on How to Kill Airborne Bacteria and Viruses in Elementary Schools (초등학교내 공기중 부유세균 및 바이러스 사멸방법에 대한 연구)

  • Lee, Su Yeon;Kim, Chang Soo;Kwak, Eun Mi;Im, Jong Eon;Jeon, Jae Hwan;Kwon, Jun Ho
    • Journal of the Society of Disaster Information
    • /
    • v.18 no.3
    • /
    • pp.566-573
    • /
    • 2022
  • Purpose: This study attempted to verify the effectiveness of the application of air sterilizers in elementary schools at risk of group infection among vulnerable groups in order to address fears of new infectious diseases that have increased since the outbreak of Middle East Respiratory Syndrome (MERS) and Coronavirus infection-19 (COVID-19). Method: One air sterilizer was installed in each classroom, cafeteria, and bathroom of an elementary school in Seoul, and surface and air samples were collected at a distance of 2m from the air sterilizer, and the bacterial reduction effect was analyzed compared to the uninstalled control group. Result: The sterilization effect on the surface was less than 2log CFU/cm2 in both the control group and the test group, and the test group showed 54 to 87% less general bacterial colony formation than the control group. In addition, the sterilization effect in the air differed depending on the location of the air sterilizer, and the wall installation showed a reduction effect of up to 91% compared to the control group, and the central installation showed a reduction effect of up to 93%. Conclusion: As a result of the study, it is expected that the prevention of infectious diseases can be increased by maintaining the current quarantine program in elementary schools that conduct regular disinfection while applying air sterilizers. In addition, it is considered desirable to facilitate the inflow of air into the air sterilizer.

Interference and Capacity Approximation using Riemann-Zeta Function in Multi-Tier CDMA Cellular Systems (다중 셀 CDMA 셀룰라 시스템에서 Riemann-Zeta 함수를 이용한 간섭과 용량 근사식)

  • 김호준
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.28 no.7A
    • /
    • pp.503-510
    • /
    • 2003
  • In CDMA cellular system, because all users share the frequency resource the signals of other user becomes interference which influences the communication quality. The system capacity defined the number of connected users within a cell is determined by the amount of interference, therefore the exact estimation of interference is important to system performance evaluation. In this paper, we propose an approximated function which calculates other cell interference in terms of Riemann-Zeta function in CDMA cellular systems, and compare with simulation results in other to verify its usefulness. The upper and lower bounds of system capacity calculated with the proposed approximated function gives almost alike result with the simulation. The proposed interference bounds are useful to calculate system capacity and to evaluate some algorithm in a hierarchical cellular systems where various propagation environments are mixed.

An Energy-Efficient Clustering Protocol Based on The Cross-Layer Design in Wireless Sensor Networks (무선 센서 네트워크에서 크로스 레이어 기반의 에너지 효율적인 클러스터링 프로토콜)

  • Kim, Tae-Kon;Lee, Hyung-Keun
    • Journal of IKEEE
    • /
    • v.11 no.4
    • /
    • pp.165-170
    • /
    • 2007
  • The main goal of research concerning clustering protocols is to minimize the energy consumption of each node and maximize the network lifetime of wireless sensor networks. However, most existing clustering protocols mainly focused on the design and formation of clusters, leaving the consideration of communication between the cluster head and the sink behind. In this paper, we propose efficient multi path routing algorithm by using MAC-NET Cross-layering. multi path needed only one tiny packet from sink to setup. In addition proposed algorithm can be used for any cluster-based hierarchical inter-clustering routing algorithm. The simulation results demonstrate that proposed algorithm extended the overall survival time of the network by reducing the load of cluster heads. The performance of proposed algorithm is less affected by the extension of sensing field than other inter-clustering operation.

  • PDF