• Journal of Broadcast Engineering
• /
• v.25 no.1
• /
• pp.113-116
• /
• 2020

This paper proposes a Quality of Experience (QoE) evaluation experiment to measure the effects of 360-degree video and sensory effects on the subject's degree of immersion, satisfaction, and sense of presence. The test subject responds to a questionnaire about the degree of immersion, satisfaction, and sense of presence after experiencing a 360-degree video accompanied by sensory effects while wearing a head-mounted display (HMD) with a scent diffusion device. As a result of the response analysis, it was confirmed that the proposed experimental method is suitable for measuring the subject's degree of immersion, satisfaction, and sense of presence about 360-degree video and sensory effects. On the other hand, inserting a gray screen for comparison experiments while watching a 360-degree video was found to cause a significant decrease in immersion and realism.

• KIPS Transactions on Software and Data Engineering
• /
• v.13 no.1
• /
• pp.17-27
• /
• 2024

Video frame interpolation is an important technique used in the field of video and media, as it increases the continuity of motion and enables smooth playback of videos. In the study of video frame interpolation using deep learning, Kernel Based Method captures local changes well, but has limitations in handling global changes. In this paper, we propose a new U-Net structure that applies feature map differentiation and two directions to focus on capturing major changes to generate intermediate frames more accurately while reducing the number of parameters. Experimental results show that the proposed structure outperforms the existing model by up to 0.3 in PSNR with about 61% fewer parameters on common datasets such as Vimeo, Middle-burry, and a new YouTube dataset. Code is available at https://github.com/Go-MinSeong/SF-AdaCoF.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.6
• /
• pp.263-268
• /
• 2013

A stereoscopic image is made via 3 dimensional image processing for combining two images from left and right camera. In this case, it is very important to synchronize input images from two cameras. The synchronization method for two camera input images is proposed in this paper. A software system is used to support various video format. And it will be used in the system for glassless stereoscopic images using several cameras.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.5A
• /
• pp.726-742
• /
• 2000

A novel rte control algorithm consisting of two major components, i.e. a variable encoding frame rate method and a hybrid DCT/wavelet I-frame coding scheme, is proposed in this work for low bit rate video coding. Most existing rate control algorithms for low bit rate video focus on bit allocation at the macroblock level under a constant frame rate assumption. The proposed rate control algorithm is able to adjust the encoding frame rate at the expense of tolerable time-delay. Furthermore, an R-D optimized hybrid DCT/wavelet scheme is used for effective I-frame coding. The new rate-control algorithm attempts to achieve a good balance between spatial quality and temporal quality to enhance the overall human perceptual quality at low bit rates. It is demonstrated that the rate control algorithm achieves higher coding efficiency at low bit rates with a low additional computational cost. The variable frame rate method and hybrid I-frame coding scheme are compatible with the bi stream structure of H.263+.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.47-54
• /
• 2022

Recently, with the development of deep learning technology, research on recognizing human behavior is in progress. In this paper, a study was conducted to recognize risky behaviors that may occur in a single-person household environment using deep learning technology. Due to the nature of single-person households, personal privacy protection is necessary. In this paper, we recognize human dangerous behavior in privacy protection video with Gaussian blur filters for privacy protection of individuals. The dangerous behavior recognition method uses the YOLOv5 model to detect and preprocess human object from video, and then uses it as an input value for the behavior recognition model to recognize dangerous behavior. The experiments used ResNet3D, I3D, and SlowFast models, and the experimental results show that the SlowFast model achieved the highest accuracy of 95.7% in privacy-protected video. Through this, it is possible to recognize human dangerous behavior in a single-person household environment while protecting individual privacy.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.620-622
• /
• 2013

Real-time Video communication technology using a Web browser today is on the rise. Video communication system The existing A method of providing an Video communication via a program for a specific server on the service provider, respectively. By using the server of the company that provides an Video communication solutions, were limited by using its own network that you can use to build a separate server for performing Video communication another, using specific software and user groups it was a mechanism for using the Video communication environment. In addition, must be installed separately and ActiveX, plug-in and, use of the service has become possible. Therefore, in this paper, utilizing the real-time Video communication Web-based technology without installing the plug-in, real-time through a Web browser or Active-X of another using a script HTML5 and the Web on the Internet Using HTTP in an environment in the Internet is possible, I've implemented a system capable of Video communication.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.4
• /
• pp.276-280
• /
• 2017

This paper presents computationally efficient image compression for wireless transmission of high-definition video, to adaptively utilize available channel bandwidth and improve image quality. The method indirectly predicts an unknown available channel bandwidth by monitoring encoder buffer status, and adaptively controls a quantization parameter to fully utilize the bandwidth. Experimental results show that the proposed method is robust to variations in channel bandwidth.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.47-50
• /
• 2022

In this paper, we proposed a method for Video-based point cloud compression reference software TMC2 encoder with an option for empty partitions in point cloud encoding. This encoder option allows tile initialization and process for an empty partition. The proposed method provides the TMC2 encoder the robustness to process dynamic point clouds.

• Journal of Broadcast Engineering
• /
• v.27 no.6
• /
• pp.861-871
• /
• 2022

The moving picture experts group (MPEG) developed the MPEG immersive video (MIV) standard for efficient compression of multiple immersive videos representing natural contents and computer graphics. The MIV compresses multiple immersive videos and generates multiple output videos which are defined as atlases. However, there is a synchronization issue of multiple decoders in a legacy device when decoding multiple encoded atlases. This paper proposes and implements the geometry packing method for adaptive control of decoder instances for low-end and high-end devices. The proposed method on the recent version of the MIV reference software worked correctly.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.5
• /
• pp.217-228
• /
• 2023

Video instance segmentation is an intelligent visual task with high complexity because it not only requires object instance segmentation for each image frame constituting a video, but also requires accurate tracking of instances throughout the frame sequence of the video. In special, human instance segmentation in drama videos has an unique characteristic that requires accurate tracking of several main characters interacting in various places and times. Also, it is also characterized by a kind of the class imbalance problem because there is a significant difference between the frequency of main characters and that of supporting or auxiliary characters in drama videos. In this paper, we introduce a new human instance datatset called MHIS, which is built upon drama videos, Miseang, and then propose a novel video data augmentation method, CDVA, in order to overcome the data imbalance problem between character classes. Different from the previous video data augmentation methods, the proposed CDVA generates more realistic augmented videos by deciding the optimal location within the background clip for a target human instance to be inserted with taking rich spatio-temporal context embedded in videos into account. Therefore, the proposed augmentation method, CDVA, can improve the performance of a deep neural network model for video instance segmentation. Conducting both quantitative and qualitative experiments using the MHIS dataset, we prove the usefulness and effectiveness of the proposed video data augmentation method.