• 한국HCI학회:학술대회논문집
• /
• 2007.02c
• /
• pp.318-321
• /
• 2007

This paper proposes a GPU-based approach to real-time skinning animation of large crowds, where each character is animated independently of the others. In the first pass of the proposed approach, skinning is done by a pixel shader and the transformed vertex data are written into the render target texture. With the transformed vertices, the second pass renders the large crowds. The proposed approach is attractive for real-time applications such as video games.

• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.986-1005
• /
• 2020

In this paper, we propose AnoVid, an automated video annotation tool based on deep neural networks, that automatically generates various meta data for each scene or shot in a long drama video containing rich elements. To this end, a novel meta data schema for drama video is designed. Based on this schema, the AnoVid video annotation tool has a total of six deep neural network models for object detection, place recognition, time zone recognition, person recognition, activity detection, and description generation. Using these models, the AnoVid can generate rich video annotation data. In addition, AnoVid provides not only the ability to automatically generate a JSON-type video annotation data file, but also provides various visualization facilities to check the video content analysis results. Through experiments using a real drama video, "Misaeing", we show the practical effectiveness and performance of the proposed video annotation tool, AnoVid.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.12
• /
• pp.2315-2320
• /
• 2006

A real-time frame-layer rate control algorithm with a token bucket traffic shaper is proposed for low bit rate video coding. The proposed rate control method uses a non-iterative optimization method for low computational complexity, and performs bit allocation at the frame level to minimize the average distortion over an entire sequence as well as variations in distortion between frames. In order to reduce the quality fluctuation, we use a sliding window scheme which does not require the pre-analysis process. Therefore, the proposed algorithm does not produce time delay from encoding, and is suitable for real-time low-complexity video encoder. Experimental results indicate that the proposed control method provides better visual and PSNR performances than the existing rate control method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.4B
• /
• pp.349-359
• /
• 2009

In this paper, we propose a stereo-video transmission method for reduction of delay and maximization of 3D effect. Conventional multimedia synchronization algorithms were designed to achieve minimum delay and synchronize multiple video and audio streams, however, they could not be effective for 3D video transmission. In this paper, we proposed a synchronization algorithm by considering the minimum error of time difference between streams for 3D effect. The minimum error of time difference for 3D effect was derived based on a 3D subjective quality test. We compute display time of the delivered videos within the allowed time-difference and the video are displayed according to the display time. To evaluate the performance of the proposed algorithm, we implemented a real-time video communication system and subjective quality test has been conducted with the proposed system. We found that video quality displayed by the proposed system. We found that video quality displayed by the proposed algorithm ranks 'good' and 'excellent' in the DMOS (Differential Mean Opinion Score) scale, based on the MOS (Mean Opinion Score) test.

• Journal of KIISE:Software and Applications
• /
• v.33 no.10
• /
• pp.851-861
• /
• 2006

The paper proposes a novel unsupervised video object segmentation algorithm for image sequences with low depth-of-field (DOF), which is a popular photographic technique enabling to represent the intention of photographer by giving a clear focus only on an object-of-interest (OOI). The proposed algorithm largely consists of two modules. The first module automatically extracts OOIs from the first frame by separating sharply focused OOIs from other out-of-focused foreground or background objects. The second module tracks OOIs for the rest of the video sequence, aimed at running the system in real-time, or at least, semi-real-time. The experimental results indicate that the proposed algorithm provides an effective tool, which can be a basis of applications, such as video analysis for virtual reality, immersive video system, photo-realistic video scene generation and video indexing systems.

• Journal of Korea Game Society
• /
• v.5 no.2
• /
• pp.3-9
• /
• 2005

Interactive real-time 3D enables users to explore virtual three dimensional environments and also experience contents in an absorbing fashion. Unlike other media, Interactive real-time 3D users take an active role in the process of "real-time fashion" where action and reaction occur instantly in a digital 3D structure. Once the components and origins of interactive real-time 3D is made, it is possible making principles of the beauty that help decide success or failure of real-time 3D in two way system. Substantial real-time 3D has not yet passed 10 years so it was unable to make sufficient precedents of fundamental artistic value based upon the credibility of the media. The goal is to explain the new form of design in relation to general principles of arts at the same time to understand the technical definition better. Concepts of historical documentation are explained with an example of categorization of recent video game and recent technology. This thesis concludes with rough forecast on the future interactive real time 3D. Since the medium began relatively recently and is developing in the rapid pace, recent analyses, though clear forecast is difficult, tend to investigate potential directions to some level the field allows.

• Journal of Korea Multimedia Society
• /
• v.25 no.6
• /
• pp.807-818
• /
• 2022

In order to further improve the accuracy and time efficiency of behavior recognition in intelligent monitoring scenarios, a human behavior recognition algorithm based on YOLO combined with LSTM and CNN is proposed. Using the real-time nature of YOLO target detection, firstly, the specific behavior in the surveillance video is detected in real time, and the depth feature extraction is performed after obtaining the target size, location and other information; Then, remove noise data from irrelevant areas in the image; Finally, combined with LSTM modeling and processing time series, the final behavior discrimination is made for the behavior action sequence in the surveillance video. Experiments in the MSR and KTH datasets show that the average recognition rate of each behavior reaches 98.42% and 96.6%, and the average recognition speed reaches 210ms and 220ms. The method in this paper has a good effect on the intelligence behavior recognition.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.2148-2161
• /
• 2019

In this paper, we present a real-time cattle action recognition algorithm to detect the estrus phase of cattle from a live video stream. In order to classify cattle movement, specifically, to detect the mounting action, the most observable sign of the estrus phase, a simple yet effective feature description exploiting motion history images (MHI) is designed. By learning the proposed features using the support vector machine framework, various representative cattle actions, such as mounting, walking, tail wagging, and foot stamping, can be recognized robustly in complex scenes. Thanks to low complexity of the proposed action recognition algorithm, multiple cattle in three enclosures can be monitored simultaneously using a single fisheye camera. Through extensive experiments with real video streams, we confirmed that the proposed algorithm outperforms a conventional human action recognition algorithm by 18% in terms of recognition accuracy even with much smaller dimensional feature description.

• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.117-120
• /
• 2000

As the use of real-time multimedia applications increases, a considerable amount of “greedy” UDP traffic would easily dominate network bandwidth and packet loss. As a result, bandwidth available to TCP connections is oppressed and their performance extremely deteriorates. In or-der that both TCP and UDP sessions fairly co-exist in the Internet, it is vital that we consider the fairness among both protocols. In this work, we implement a “TCP-friendly” rate control mechanism suitable to video applications and con-sider its applicability to a real system through observation of the video quality at the receiver and the connection state. It is shown that we can achieve high-quality and stable video transfer fairly sharing the network bandwidth with TCP by applying our rate control at a control interval of 32 times as long as RTT.

• Journal of Korea Multimedia Society
• /
• v.9 no.4
• /
• pp.421-433
• /
• 2006

This paper proposes a method to insert virtual objects into a real video stream based on feature tracking and camera pose estimation from a set of single-camera video frames. To insert or modify 3D shapes to target video frames, the transformation from the 3D objects to the projection of the objects onto the video frames should be revealed. It is shown that, without a camera calibration process, the 3D reconstruction is possible using multiple images from a single camera under the fixed internal camera parameters. The proposed approach is based on the simplification of the camera matrix of intrinsic parameters and the use of projective geometry. The method is particularly useful for augmented reality applications to insert or modify models to a real video stream. The proposed method is based on a linear parameter estimation approach for the auto-calibration step and it enhances the stability and reduces the execution time. Several experimental results are presented on real-world video streams, demonstrating the usefulness of our method for the augmented reality applications.