• Title/Summary/Keyword: video filtering

Search Result 254, Processing Time 0.032 seconds

Detection Algorithm of Shoot Scenes in Soccer Video for Real-time Content Filtering (실시간 필터링을 위한 축구 비디오의 장면 검출)

  • Cho Jun Ho;Jin Sung Ho;Ro Yong Man;Kang Kyeongok
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 2004.11a
    • /
    • pp.229-232
    • /
    • 2004
  • 축구 비디오의 슛 장면과 같은 이벤트 검출에는 많은 연구가 있었으나 기존의 방법은 정확성과 실시간으로 필터링하는 부분에서는 문제가 있다 이에 대해서 본 논문은 현재 실시간으로 가장 딸이 방송되는 스포츠 장르 중 축구 비디오에 대한 효율적인 슛 장면 검출 알고리즘을 제안하고자 한다. 제안한 방법은 우선 입력 프레임으로부터 뷰 타입을 결정한다. 슛 장면에 대한 뷰 타입 패턴 변화, 리 플레이의 검출과 오디오 파워의 변화를 이용하여 필터링을 수행한다. 실험 결과를 통하여 제안한 방법이 효율적이고 효과적으로 슛 장면을 검출하였고 다채널의 디지털 방송환경에서 실시간으로 컨텐츠를 필터링하는 서비스가 가능함을 보였다.

  • PDF

Novel Parallel Approach for SIFT Algorithm Implementation

  • Le, Tran Su;Lee, Jong-Soo
    • Journal of information and communication convergence engineering
    • /
    • v.11 no.4
    • /
    • pp.298-306
    • /
    • 2013
  • The scale invariant feature transform (SIFT) is an effective algorithm used in object recognition, panorama stitching, and image matching. However, due to its complexity, real-time processing is difficult to achieve with current software approaches. The increasing availability of parallel computers makes parallelizing these tasks an attractive approach. This paper proposes a novel parallel approach for SIFT algorithm implementation using a block filtering technique in a Gaussian convolution process on the SIMD Pixel Processor. This implementation fully exposes the available parallelism of the SIFT algorithm process and exploits the processing and input/output capabilities of the processor, which results in a system that can perform real-time image and video compression. We apply this implementation to images and measure the effectiveness of such an approach. Experimental simulation results indicate that the proposed method is capable of real-time applications, and the result of our parallel approach is outstanding in terms of the processing performance.

Motion analysis for Home Surveillance of the Aged who Lives Alone based on Video Images (비디오 기반의 독거노인 위급 상황 탐지를 위한 행동 분석)

  • Kim, Young-Baek;Rhee, Sang-Yong
    • Journal of Institute of Control, Robotics and Systems
    • /
    • v.13 no.6
    • /
    • pp.537-641
    • /
    • 2007
  • In this paper, motion analysis algorithm is presented for home surveillance of the aged who lives alone. For the first step, we acquire images from a camera. To enhance the image, we use median filtering and binarize it to reduce processing time. And then morphological operations are performed to remove small blobs and small holes. At the forth step, blobs are analysed to extracts tor foreground region. Then, motions are predicted from these images by using optical tlow technique, and the predicted motion data are refined by comparing our cardboard models so as to judge behavior pattern.

Digital Watermarking by Rearranging and Modifying DCT Coefficients

  • Lee, Hee sup;Oh, Sang-Heun;Lee, Keun-Young
    • Proceedings of the IEEK Conference
    • /
    • 2000.07b
    • /
    • pp.902-905
    • /
    • 2000
  • Because of the rapid growth of Internet and multimedia applications, how to protect IPR (intellectual property rights) has become a critical issue. Is one of the ways to overcome the problem of the protection of IPR. Digital watermarking call be applied to multimedia data, such as digital images, digital video, and digital audio. In this paper, we propose a digital watermarking technique for digital images to authenticate an owner or an image by embedding visually recognizable patterns, such as logos, signatures, or stamps into images In BDCT (block discrete cosine transform) frequency domain. The proposed method sorts the components of an original image twice. At the same time, the method, also, rearranges the components of a watermark twice in order to be more robust, and finally embeds the watermark into the image. From the experimental results, the conjunction of three similarity measurements shows that our proposed method is robust to image cropping, image filtering, and JPEG (the Joint Photographic Experts Group) both subjectively and objectively.

  • PDF

Animal Tracking in Infrared Video based on Adaptive GMOF and Kalman Filter

  • Pham, Van Khien;Lee, Guee Sang
    • Smart Media Journal
    • /
    • v.5 no.1
    • /
    • pp.78-87
    • /
    • 2016
  • The major problems of recent object tracking methods are related to the inefficient detection of moving objects due to occlusions, noisy background and inconsistent body motion. This paper presents a robust method for the detection and tracking of a moving in infrared animal videos. The tracking system is based on adaptive optical flow generation, Gaussian mixture and Kalman filtering. The adaptive Gaussian model of optical flow (GMOF) is used to extract foreground and noises are removed based on the object motion. Kalman filter enables the prediction of the object position in the presence of partial occlusions, and changes the size of the animal detected automatically along the image sequence. The presented method is evaluated in various environments of unstable background because of winds, and illuminations changes. The results show that our approach is more robust to background noises and performs better than previous methods.

The kinematics analysis of Discus throwing (원반던지기의 운동학적 분석)

  • Kim, Jong-In;Sun, Jae-Bok
    • Korean Journal of Applied Biomechanics
    • /
    • v.13 no.2
    • /
    • pp.29-47
    • /
    • 2003
  • This study is to analyze the kinematic variables in release motion of discuss throwing. For the matter, 5 people from the national team and collegiate discuss throwing in the year 2001 were chosen as the subjects and two S-VHS video cameras set in 60frames/sec were used for recording their motions. Coordinated raw positions data through digitizing are smoothing by butter-worth 's low-pass filtering method at a cut off frequency 6.0Hz. and the direct linear transformation(DLT) method was employed to obtain 3-D position coordinates. The conclusions were as follows; 1. The better record players showed the shorter approach time in the last support phase. 2. In the displacement CG, the better record players showed the shorter displacement in medial-lateral direction, and the longer displacement in horizontal direction. In the motion, the COG showed longer displacement vertical direction. 3. The better record players showed the faster horizontal velocity than vertical velocity in the release. 4. The better record players showed to take the posture of vertical axis in the release.

Steam Video Game Recommendation System using Collaborative Filtering and Personal propensity in R system (R 시스템에서 협업필터링과 개인화 요인을 사용한 스팀 비디오 게임 추천 시스템)

  • Song, Min-Hyuk;Shin, Hae-Ran;Park, Doo-Soon
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2019.10a
    • /
    • pp.56-59
    • /
    • 2019
  • 하루 평균 동시 접속자가 1,000만 명이 넘을 정도로 많은 사람이 사용하는 플랫폼은 드물다. 이러한 플랫폼 중에 스팀은 독보적인 존재이다. 스팀 내에는 수많은 게임이 있다. 그 수많은 게임 중 각 사용자에게 맞는 게임을 찾아내는 것은 매우 어렵다. 그래서 각 개인한테 맞는 게임을 추천해주는 것이 필요하다. 본 논문에서는 각 개인에 맞는 게임을 추천해주기 위하여 현재까지 가장 좋은 방법으로 알려진 협업 필터링 방법과 장르, 사용한 시간, 사용자 수를 고려하여 추천한다.

Robot-Assisted Thoracoscopic Esophagectomy with Total Mediastinal Lymphadenectomy: A Guide to a Systematic Approach Using the Concept of Fascial Plane Dissection

  • Park, Byung Jo;Kim, Dae Joon
    • Journal of Chest Surgery
    • /
    • v.54 no.4
    • /
    • pp.294-301
    • /
    • 2021
  • Recent case series and meta-analyses have suggested that robot-assisted minimally invasive esophagectomy (RAMIE) could be a useful alternative to video-assisted thoracic surgery esophagectomy. The advantages of RAMIE are a 3-dimensional view, 7 degrees of freedom, and tremor filtering, which enable more meticulous lymph node dissection with a lower incidence of complications. However, in radical esophagectomy, understanding the concepts of the fascia and compartment is crucial for successful and reliable dissection. The first RAMIE in Korea was performed by our team in July 2006, and since then, we have developed related techniques to achieve better short- and long-term outcomes. The key step in RAMIE for esophageal squamous cell carcinoma is dissection of the upper mediastinum due to the difficulty of lymph node dissection and the high incidence of nodal metastasis in the area. Herein, we describe the technique of fascial plane dissection with esophageal suspension during RAMIE.

Error filtering technology using change rate of moving object data in real-time video (실시간 영상의 이동 객체 데이터 변화율을 이용한 에러 필터링 기술)

  • Yoon, Kyoung-Ho;Kim, Dhan-Hee;Lee, Won-Suk
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2019.01a
    • /
    • pp.155-158
    • /
    • 2019
  • 최근 지능형 CCTV 관제 시스템에 대한 수요가 증가하고 있다. CCTV 영상 데이터의 양이 폭발적으로 증가하고 있어 이를 분석하기 위한 기술의 발전이 필요한 실정이다. 대부분의 지능형 CCTV 관제 시스템은 영상 속 객체를 찾고 이 객체의 메타데이터를 통해 지능형 관제 시스템을 수행한다. 하지만 영상 속 객체의 로그가 항상 정확하지 않다. 현재의 객체 인식 기술로는 CCTV 영상의 밝기, 해상도 조건에 따라 성능의 차이가 심하고, 영상의 프레임 대비 빠르게 움직인 CCTV 영상 속 모든 객체를 사람이 인식하는 정도로 인식하기 어렵다. 이러한 이동 객체의 크기, 위치를 분석한 메타데이터에는 에러가 포함되기 쉽다. 본 논문에서는 지능형 CCTV 관제 시스템에서 분석한 영상 속 객체의 프레임 메타데이터 에러를 학습기반 실시간 에러 필터링 알고리즘을 통해 개선하여 에러가 필터링된 데이터를 사용하는 지능형 관제 시스템의 정확도 향상에 기여 할 것을 기대한다.

  • PDF

Estimating parameter of adaptive spatio-temporal smoothing for noise reduction in low light surveillance video (저조도 감시 카메라 비디오의 잡음 제거를 위한 적응적 시공간 평활화 파라미터 추정에 관한 연구)

  • Kim, Dae Hoe;Choi, Jae Young;Ro, Yong Man
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2010.11a
    • /
    • pp.572-575
    • /
    • 2010
  • 본 논문은 SNR 이 매우 낮은 저조도 영상의 잡음 제거를 위한 새로운 기술을 제안한다. 제안하는 기술은 입력 영상에서 파라미터를 자동/적응적 방식으로 추정하는 알고리즘을 특징으로 한다. 제안하는 기술의 효율성을 검증하기 위해 실질적인 환경에서 취득한 저조도 동영상들을 가지고 실험을 수행하였다. 실험을 통해 제안하는 기술을 활용하여 적응적으로 추정된 파라미터가 필터링(filtering) 성능을 잘 유지시킴을 검증하였다. 또한 기존 연구들과 비교할 때 저조도 동영상의 명암대비 향상과 잡음 제거에 우수한 결과를 보임을 검증하였다.