• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권3호
• /
• pp.1434-1449
• /
• 2019

Video object segmentation is a significant task in computer vision, but its performance is not very satisfactory. A method of video object segmentation using weakly temporal information is presented in this paper. Motivated by the phenomenon in reality that the motion of the object is a continuous and smooth process and the appearance of the object does not change much between adjacent frames in the video sequences, we use a feed-forward architecture with motion estimation to predict the mask of the current frame. We extend an additional mask channel for the previous frame segmentation result. The mask of the previous frame is treated as the input of the expanded channel after processing, and then we extract the temporal feature of the object and fuse it with other feature maps to generate the final mask. In addition, we introduce multi-mask guidance to improve the stability of the model. Moreover, we enhance segmentation performance by further training with the masks already obtained. Experiments show that our method achieves competitive results on DAVIS-2016 on single object segmentation compared to some state-of-the-art algorithms.

• 방송공학회논문지
• /
• 제24권1호
• /
• pp.182-185
• /
• 2019

본 논문에서는 프로그래머블 멀티포맷 비디오 복호화기를 구성하기 위한 기본 모듈들의 요구 성능을 분석하고 제안하였다. 제안한 플랫폼의 목적은 고성능 FHD 비디오 복호화기 구성이다. 제안한 복호화기는 재구성 가능한 프로세서, 전용 비트스트림 코프로세서, 메모리 제어기, 움직임 보상용 캐쉬 및 플렉서블 하드웨어 가속기 등으로 구성되었다. 300MHz 클럭을 사용했을 때 HEVC로 부호화된 초당 30 장의 FHD를 복호화 할 수 있는 모듈들의 성능에 대해서 분석하고 기본 성능을 제안하였다.

• Journal of information and communication convergence engineering
• /
• 제21권1호
• /
• pp.75-81
• /
• 2023

Video platforms, including YouTube, have a structure in which the number of video views is directly related to the publisher's profits. Therefore, video publishers induce viewers by using provocative titles and thumbnails to garner more views. The conventional technique used to limit such harmful videos has low detection accuracy and relies on follow-up measures based on user reports. To address these problems, this study proposes a technique to improve the accuracy of filtering harmful media using thumbnails, titles, and audio data from videos. This study analyzed these three pieces of multimodal information; if the number of harmful determinations was greater than the set threshold, the video was deemed to be harmful, and its upload was restricted. The experimental results showed that the proposed multimodal information extraction technique used for harmfulvideo filtering achieved a 9% better performance than YouTube's Restricted Mode with regard to detection accuracy and a 41% better performance than the YouTube automation system.

• 한국멀티미디어학회논문지
• /
• 제6권3호
• /
• pp.488-495
• /
• 2003

멀티미디어 통신은 네트워크의 발달로 인하여 날로 그 응용분야가 발전되어 가고 있다. 일반 가정에서 사용되는 가전제품의 원격 제어에서부터 특수분야인 의료, 게임, 화상 회의와 화상채팅에 이르기까지 우리 생활의 전역에 사용되어지고 있다. 이러한 멀티미디어 통신의 필수적인 요건은 많은 양의 데이터를 고속으로 전송해야 한다는 것이다. 그러나 고속의 네트워크 환경에서 통신망의 전송률이 데이터를 처리하는 프로세서의 처리속도를 초과하는 경우 네트워크의 성능을 저하하는 병목현상이 각 노드에 발생하여 데이터 전송의 속도가 느려지고, 많은 양의 패킷 손실을 유발하는 주요 원인으로 지목되어져 왔다. 본 논문에서는 이러한 병목현상을 완화하기 위하여 클라이언트 프로세서의 처리능력을 감안, 수신능력을 예측하고 그에 따른 흐름제어방법을 제시하며 실제 구현을 통하여 성능을 평가하였다.

• 한국간호교육학회지
• /
• 제19권4호
• /
• pp.508-517
• /
• 2013

Purpose: The purpose of this study was to evaluate the effectiveness of infant CPR (Cardiopulmonary Resuscitation) immediate remediation[LAB2]. Methods: This is a quasi-experimental study with a non-equivalent comparison group pre-post test design. Participants were 73 child care teachers in J district in Seoul. The experimental group (35) received immediate remediation with video learning [LAB3]for infant CPR education and the control group (38) received video learning only. We investigated confidence of infant CPR and tested single-rescuer infant CPR performance depending on a checklist (8 items). Data were collected before and right after to evaluate the confidence of infant CPR and before, right after and 2 weeks after the education to evaluate the skill performance and final acceptance. Results: There was a significant increase in confidence of infant CPR in the experimental group and control group. There was a statistically significant difference in the degree of skill performance between groups according to the amount time (F=10.58, p<.001). The degree of skill performance was tested two weeks after the education and immediate remediation was 5.35 times more effective compared to the video image demonstration (B=1.677, p<.001). Conclusion: The findings provide the necessity of immediate remediation education of infant CPR to increase confidence and skill performance ability.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2008년도 춘계종합학술대회 A
• /
• pp.306-309
• /
• 2008

A system realization for video surveillance with interframe probability distribution analysis is presented in this paper. The system design is based on a high performance DSP processor, video surveillance is implemented by analyzing interframe probability distribution for scanning objects in a restricted area and the video analysis algorithm is decided for forming a different image from the probability distribution of several frames compressed by the standardized JPEG. The algorithm processing time of D1($720{\times}480$) image per frame is 85ms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권8호
• /
• pp.2833-2850
• /
• 2014

This paper proposes a novel framework for traffic video classification based on chaotic features. First, each pixel intensity series in the video is modeled as a time series. Second, the chaos theory is employed to generate chaotic features. Each video is then represented by a feature vector matrix. Third, the mean shift clustering algorithm is used to cluster the feature vectors. Finally, the earth mover's distance (EMD) is employed to obtain a distance matrix by comparing the similarity based on the segmentation results. The distance matrix is transformed into a matching matrix, which is evaluated in the classification task. Experimental results show good traffic video classification performance, with robustness to environmental conditions, such as occlusions and variable lighting.

• ETRI Journal
• /
• 제23권4호
• /
• pp.190-198
• /
• 2001

The performance of Motion Compensated Discrete Cosine Transform (MC-DCT) video coding is improved by using the region adaptive subband image coding [18]. On the assumption that the video is acquired from the camera on a moving platform and the distance between the camera and the scene is large enough, both the motion of camera and the motion of moving objects in a frame are compensated. For the compensation of camera motion, a feature matching algorithm is employed. Several feature points extracted using a Sobel operator are used to compensate the camera motion of translation, rotation, and zoom. The illumination change between frames is also compensated. Motion compensated frame differences are divided into three regions called stationary background, moving objects, and newly emerging areas each of which is arbitrarily shaped. Different quantizers are used for different regions. Compared to the conventional MC-DCT video coding using block matching algorithm, our video coding scheme shows about 1.0-dB improvements on average for the experimental video samples.

• ETRI Journal
• /
• 제30권1호
• /
• pp.101-112
• /
• 2008

In this paper, we present a method to customize the ground color in outdoor sports video to provide TV viewers with a better viewing experience or subjective satisfaction. This issue, related to content personalization, is becoming critical with the advent of mobile TV and interactive TV. In outdoor sports video, such as soccer video, it is sometimes observed that the ground color is not satisfactory to viewers. In this work, the proposed algorithm is focused on customizing the ground color to deliver a better viewing experience for viewers. The algorithm comprises three modules: ground detection, shot classification, and ground color customization. We customize the ground color by considering the difference between ground colors from both input video and the target ground patch. Experimental results show that the proposed scheme offers useful tools to provide a more comfortable viewing experience and that it is amenable to real-time performance, even in a software-based implementation.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -1
• /
• pp.607-610
• /
• 2002

Even though digital video coding techniques have been developed very rapidly, rate controlling is still an unsolved problem. This paper presents a new scene adaptive video encoding scheme for MPEG-1 and MPEG-2 video encoders. Degradation of picture quality at scene changes due to poor prediction of global complexity measure is addressed. The proposed scheme determines the picture types adaptively based on scene contents of each video frame. The effective placement of reference and inter-reference frames is studied at sudden scene changes and gradual scene changes respectively. Results show that the proposed scheme demonstrates a significant improvement in performance compared to TM5〔1〕.