• Title/Summary/Keyword: broadcast environment

Search Result 581, Processing Time 0.029 seconds

Luminance enhancement in single image dehazing

  • Bui, Minh-Trung;Kim, Won-Ha
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 2013.06a
    • /
    • pp.322-324
    • /
    • 2013
  • Haze is an extreme reason of the reduction of contrast when capturing image in the outdoor. Recently, there are several single image dehazing techniques, but they are not robust in dynamic variations of natural environment caused by the thickness, coverage of haze and appearance of sunlight. In this paper, we propose an effective and robust method to enhance luminance for image dehazing depending on histogram analysis. Compare with conventional methods, our proposal have better performance in term of contrast, and computation time.

  • PDF

V2P Communications for Safety

  • Eyobu, Odongo Steven;Joo, Jhihoon;Han, Dong Seog
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 2015.07a
    • /
    • pp.13-16
    • /
    • 2015
  • In any mobile ad hoc environment, collision amongst mobile objects is always likely to occur unless there is a certain level of intelligence to detect and avoid the collision. This phenomenon of detection and avoidance is the key attribute for safety applications in vehicle to pedestrian (V2P) communications systems. In this paper, we propose a V2P communications concept for collision detection and avoidance.

  • PDF

Human Recognition using CNN under Indoor Environment (합성곱 신경망을 이용한 실내 공간에서의 사람 인식)

  • Lee, Seungsoo;Kim, Manbae
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 2017.11a
    • /
    • pp.36-37
    • /
    • 2017
  • 실내공간에서 사람 검출 및 인식은 지능영상정보 시스템에서 중요한 기능중의 하나이다. 실내공간에서 사람검출을 위한 트랙킹 과정에서 발생하는 표류(drifting)는 성능 저하의 큰 원인을 제공한다. 표류로 인한 비사람의 트랙킹을 방지하기 위해서 사람여부를 결정하는 것이 필요하다. 이를 위해서 합성곱 신경망을 적용한 결과 80%의 사람 인식율을 얻었다.

  • PDF

Mental Image Expression by Media Integration ~COMICS (Computer Organized Media Integration & Communication System)

  • Inoue, Seiki
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 1996.06b
    • /
    • pp.122-127
    • /
    • 1996
  • We introduce the outline of our research plans concerning mental image expression for the purpose of communication. We are studying the Computer Organized Media Integration & Communication System (COMICS)as a flexible media handling environment. The system can expand the potential of mental image expression by freely handling and integrating various kinds of media. An experimental COMICS is also introduced.

  • PDF

Restoring Degradation of Hazy Image in HSI Color Space

  • Bui, Minh-Trung;Kim, Won-Ha
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 2012.11a
    • /
    • pp.5-8
    • /
    • 2012
  • Haze is an extreme reason of the reduction of contrast when capturing image in the outdoor. Recently, there are several single image dehazing techniques, but they are not robust in dynamic variations of natural environment caused by the thickness, coverage of haze and appearance of sunlight. In this paper, we propose an effective and robust method to restore degradation of hazy image. Compare with conventional methods, our proposal have better performance and computation time.

  • PDF

Bandwidth-Adaptive Video Transmission Method for Heterogeneous Network Environment

  • Sakazawa, S.;Takishima, Y.;Wada, M.;Amano, K.
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 1997.06a
    • /
    • pp.49-54
    • /
    • 1997
  • For the purpose of a flexible coded video transmission over a heterogeneous network, we propose a new packetization method for coded video data. The proposed method achieves small degradation of coded picture quality in case of packet discard at the network node and does not require heavy processing load for bitrate control operation. Computer simulation results show that the bitrate reduction from 384 kb/s to 192 kb/s does not cause severe degradation in picture quality.

  • PDF

Histogram-based luminance enhancement for image dehazing

  • Bui, Minh-Trung;Kim, Won-Ha
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 2012.07a
    • /
    • pp.16-18
    • /
    • 2012
  • Haze is an extreme reason of the reduction of contrast when capturing image in the outdoor. Recently, there are several single image dehazing techniques, but they are not robust in dynamic variations of natural environment caused by the thickness, coverage of haze and appearance of sunlight. In this paper, we propose an effective and robust method to enhance luminance for image dehazing depending on histogram analysis. Compare with conventional methods, our proposal have better performance in term of contrast, and computation time.

  • PDF

Interoperable DRM Tool Technology for communication and broadcasting conversions environment (통방융합환경에서의 상호운용적 DRM 툴 기술)

  • Choi, Beom-Seok;Byun, Yeong-Bae;Nam, Je-Ho
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 2005.11a
    • /
    • pp.225-228
    • /
    • 2005
  • DRM 기술의 호환성 부재는 콘텐츠 소비 활성화에 큰 장애물로 부각되고 있다. 현재 상호운용적인 DRM 기술 개발을 위하여 다양한 산업체와 기관들이 DRM 기술에 대한 표준화 단체를 조성하고 이 문제를 해결하기 위해 노력하고 있다. 본 논문에서는 툴 개념을 기반으로 서로 다른 DRM 간의 상호운용성(interoperability)을 지원하는 방법에 대하여 설명한다.

  • PDF

Human and Nonhuman Classification using CNN under Indoor Environment (실내 공간에서의 합성곱 신경망 기반 사람과 비사람의 분류)

  • Lee, Seungsoo;Kim, Manbae
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 2018.11a
    • /
    • pp.9-10
    • /
    • 2018
  • 실내공간에서 사람 검출 및 인식은 지능영상정보 시스템에서 중요한 기능중의 하나이다. 실내공간에서 사람검출을 위한 트랙킹 과정에서 발생하는 표류(drifting)는 성능 저하의 큰 원인을 제공한다. 표류로 인한 비사람의 트랙킹을 방지하기 위해서 사람여부를 결정하는 것이 필요하다. 이를 위해서 합성곱 신경망을 적용한 결과 80%의 사람 인식율을 얻었다.

  • PDF

A Face Verification using Iterative Light Enhancement in Low Light Environment (저조도 환경에서의 반복적 조도 향상을 이용한 얼굴 검증)

  • Lee, Sanghoon
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 2022.06a
    • /
    • pp.1222-1225
    • /
    • 2022
  • 본 논문에서는 저조도 환경에서 촬영된 영상의 조도를 개선하여 얼굴 검증 정확도를 높이는 방법을 제안하였다. 입력 이미지의 조도 개선을 통해 얼굴 검출 정확도를 개선하며, 검출된 얼굴의 반복적인 조도 향상을 통해 생성된 다수의 특징 벡터를 이용하여 얼굴 검증에 이용하였다. 얼굴 검출 및 검증 정확도 측정을 위해 K-FACE 데이터셋을 이용하였다. 저조도 환경에서 촬영된 검증 이미지에 대하여, 제안하는 특징 벡터 합성 방법으로 인해, 동일인 쌍 및 타인 쌍의 유사도 점수 분포의 표준 편차가 줄어드는 경향을 확인했으며, 이로 인해 검증 성능이 높아지는 결과를 얻었다.

  • PDF