• 한국통신학회논문지
• /
• 제27권7A호
• /
• pp.711-723
• /
• 2002

ISO/IEC MPEG-4 FGS (finer granular scalable) 비디오 스트림을 패킷손실 측면의 차등서비스 (differentiated services: DiffServ) 네트워크상에서 차별화 전송하는 시스템을 제안하고, 그 성능을 분석한다. 이를 위한 전체 제안시스템의 구조는 크게 다음의 3 부분으로 나눌 수 있다. 즉 1) 선형 근사화한 전송율-왜곡치 (rate-distortion: R-D) 모델를 사용하여 비디오 품질를 일정하게 유지하는 최적의 계층화된 전송율 적응 제어 부분, 2) 각각의 비디오 패킷이 손실될 때 전체품질에 미치는 영향을 고려하는 우선순위 패킷화 (prioritized packetization) 부분, 그리고 3) 이와 같이 우선순위화된 비디오 패킷 스트림을 차등서비스 네트워크 상에서 차별화 전송을 수행하는 부분으로 구분할 수 있다. 따라서 상기한 3 부분들이 효율적으로 연동되어 비디오 전송을 수행할 때, 동일한 네트워크 자원이 주어진 경우 얻을 수 있는 종단간 (end-to-end) 비디오 품질의 향상을 비교 분석하였다.

• 조명전기설비학회논문지
• /
• 제22권7호
• /
• pp.37-42
• /
• 2008

In this paper, a real-time multiview video coding system using fast disparity estimation is proposed. In the multiview encoder, adaptive disparity-motion estimation (DME) for an effective 3-dimensional (3D) processing are proposed. That is, by adaptively predicting the mutual correlation between stereo images in the key-frame using the proposed algorithm, the bandwidth of stereo input images can be compressed to the level of a conventional 2D image and a predicted image also can be effectively reconstructed using a reference image and adaptive disparity vectors. Also, in multiview decoder, intermediate view reconstruction (IVR) using adaptive disparity search algorithm (DSA) for real-time multiview video processing is proposed. The proposed IVR can reduce a processing time of disparity estimation by selecting adaptively disparity search range. Accordingly, the proposed multiview video coding system is able to increase the efficiency of the coding rate and improve the resolution.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권2호
• /
• pp.1118-1133
• /
• 2017

Computer vision-based human activity recognition (HAR) has become very famous these days due to its applications in various fields such as smart home healthcare for elderly people. A video-based activity recognition system basically has many goals such as to react based on people's behavior that allows the systems to proactively assist them with their tasks. A novel approach is proposed in this work for depth video based human activity recognition using joint-based motion features of depth body shapes and Deep Belief Network (DBN). From depth video, different body parts of human activities are segmented first by means of a trained random forest. The motion features representing the magnitude and direction of each joint in next frame are extracted. Finally, the features are applied for training a DBN to be used for recognition later. The proposed HAR approach showed superior performance over conventional approaches on private and public datasets, indicating a prominent approach for practical applications in smartly controlled environments.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2002년도 정기총회 및 학술대회
• /
• pp.173-176
• /
• 2002

This paper proposes a new approach for digital watermarking and secure copyright protection of video. the principal aim being to discourage illicit copying and distribution of copyrighted material. The method presented here is based on the three dimensional discrete wavelet transform of video scene. The watermark is a copyright information encoded in the form of a spread spectrum signal to ensure the system security and is embedded in the 3D DWT magnitude of video chunks. The performance of the presented technique is evaluated experimentally.

• 한국컴퓨터그래픽스학회논문지
• /
• 제9권3호
• /
• pp.15-21
• /
• 2003

An algorithm is developed for augmenting a real video with virtual graphics objects without computing Euclidean information. Real motion of the camera is obtained in affine space by a direct linear method using image matches. Then, virtual camera is provided by determining the locations of four basis points in two input images as initialization process. The four pairs of 2D location and its 3D affine coordinates provide Euclidean orthographic projection camera through the whole video sequence. Our method has the capability of generating views of objects shaded by virtual light sources, because we can make use of all the functions of the graphics library written on the basis of Euclidean geometry. Our novel formulation and experimental results with real video sequences are presented.

• International journal of advanced smart convergence
• /
• 제9권4호
• /
• pp.120-123
• /
• 2020

The surveillance system to prevent crime and accidents in advance has become a necessity, not an option in real life. Not only public institutions but also individuals are installing surveillance cameras to protect their property and privacy. However, since the installed surveillance camera cannot be monitored for 24 hours, the focus is on the technology that tracks the video after an accident occurs rather than prevention. In this paper, we propose a system model that monitors abnormal behaviors that may cause crimes through real-time video, and when a specific behavior occurs, the surveillance system automatically detects it and responds immediately through an alarm. We are a model that analyzes real-time images from surveillance cameras and uses I3D models from analysis servers to analyze abnormal behavior and deliver notifications to web servers and then to clients. If the system is implemented with the proposed model, immediate response can be expected when a crime occurs.

• 방송공학회논문지
• /
• 제13권3호
• /
• pp.388-400
• /
• 2008

본 논문에서는 다시점 비디오 부호화에서 색차 보상을 적용하여 비용면에서 효과적으로 기준 영상의 품질을 향상시키는 방법을 소개한다. 제안하는 방법은 기준 P-영상에만 적용이 되며, 그 중에서도 INTER $16{\times}16$ 모드와 SKIP 모드에만 적용된다. JVT의 공통 실험 조건을 사용하여 실험을 수행하였을 경우, 휘도 성분 신호인 Y 신호에서 거의 동일한 성능을 유지하면서, 색차 성분인 U, V 신호에 대해 평균 BD-PSNR이 각각 0.136 dB, 0127 dB 향상되었고, 저비트율 실험에서는 Y, U, V 신호에 대해 평균 BD-PSNR이 각각 0.141 dB, 0.494 dB, 0.525 dB 향상되었다. 제안하는 방법을 적용하는 기준 P-영상의 비중은 전체 영상 시퀀스에서 4.18%로 상당히 비중이 작기 때문에 필요한 계산 복잡도는 상당히 낮다고 할 수 있으며, 이에 비해 색상 정보의 부호화 효율은 매우 향상되었음을 확인할 수 있다.

• 방송공학회논문지
• /
• 제22권3호
• /
• pp.366-374
• /
• 2017

TV나 디지털 사이니지와 같은 화면표시장치들이 점점 커져감에 따라, 미디어의 종류가 UHD, 파노라마, 퍼즐형 미디어와 같은 광각의 미디어로 변하고 있다. 특히, 파노라마 및 퍼즐형 미디어는 스티칭을 통해 복수개의 카메라로 촬영된 비디오 클립을 합성한 형태로 구성된다. 그러나, 스티칭 과정의 처리 시간이 오래 걸리기 때문에 실시간 서비스에는 적용하기 어려운 문제가 있다. 따라서 본 논문에서는 스티칠 처리 시간을 감소하기 위한 방법으로, 영상간의 공간적 연관관계를 알려주는 2D Adjacency Matrix를 생성하는 것을 제안한다. Discrete Cosine Transform (DCT)를 사용하여, 비디오 소스의 각 프레임을 공간 영역에서 주파수 영역으로 변환 시킨다. 앞서 언급한 DCT 계수를 기반으로 효과적으로 이미지들의 공간적 연관관계를 알려주는 2D Adjacency Matrix를 생성한다. 본 논문에서는 각각의 비디오 클립들로부터 파노라마 영상과, 퍼즐형 미디어를 생성하기 위해 DCT를 이용한 2D Adjacency matrix 생성 방법을 제안한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권2호
• /
• pp.728-741
• /
• 2015

Stereo vision has become an important technical issue in the field of 3D imaging, machine vision, robotics, image analysis, and so on. The depth map extraction from stereo video is a key technology of stereoscopic 3D video requiring stereo correspondence algorithms. This is the matching process of the similarity measure for each disparity value, followed by an aggregation and optimization step. Since it requires a lot of computational power, there are significant speed-performance advantages when exploiting parallel processing available on processors. In this situation, multi-core CPU may allow many parallel programming technologies to be realized in users computing devices. This paper proposes parallel implementations for calculating disparity map using a shared memory programming and exploiting the streaming SIMD extension technology. By doing so, we can take advantage both of the hardware and software features of multi-core processor. For the performance evaluation, we implemented a parallel SAD algorithm with OpenMP and SSE2. Their processing speeds are compared with non parallel version on stereoscopic streaming video. The experimental results show that both technologies have a significant effect on the performance and achieve great improvements on processing speed.

• Journal of Information Processing Systems
• /
• 제14권6호
• /
• pp.1318-1330
• /
• 2018

Video captioning refers to the process of extracting features from a video and generating video captions using the extracted features. This paper introduces a deep neural network model and its learning method for effective video captioning. In this study, visual features as well as semantic features, which effectively express the video, are also used. The visual features of the video are extracted using convolutional neural networks, such as C3D and ResNet, while the semantic features are extracted using a semantic feature extraction network proposed in this paper. Further, an attention-based caption generation network is proposed for effective generation of video captions using the extracted features. The performance and effectiveness of the proposed model is verified through various experiments using two large-scale video benchmarks such as the Microsoft Video Description (MSVD) and the Microsoft Research Video-To-Text (MSR-VTT).