• ETRI Journal
• /
• 제29권3호
• /
• pp.353-362
• /
• 2007

In this paper, we propose a novel unsupervised video object extraction algorithm for individual images or image sequences with low depth of field (DOF). Low DOF is a popular photographic technique which enables the representation of the photographer's intention by giving a clear focus only on an object of interest (OOI). We first describe a fast and efficient scheme for extracting OOIs from individual low-DOF images and then extend it to deal with image sequences with low DOF in the next part. The basic algorithm unfolds into three modules. In the first module, a higher-order statistics map, which represents the spatial distribution of the high-frequency components, is obtained from an input low-DOF image. The second module locates the block-based OOI for further processing. Using the block-based OOI, the final OOI is obtained with pixel-level accuracy. We also present an algorithm to extend the extraction scheme to image sequences with low DOF. The proposed system does not require any user assistance to determine the initial OOI. This is possible due to the use of low-DOF images. The experimental results indicate that the proposed algorithm can serve as an effective tool for applications, such as 2D to 3D and photo-realistic video scene generation.

• 한국멀티미디어학회논문지
• /
• 제12권6호
• /
• pp.785-793
• /
• 2009

This paper proposes a signature using dominant singular values for video sequence matching. By considering the input image as matrix A, a partition procedure is first performed to separate the matrix into non-overlapping sub-images of a fixed size. The SVD(Singular Value Decomposition) process decomposes matrix A into a singular value-singular vector factorization. As a result, singular values are obtained for each sub-image, then k dominant singular values which are sufficient to discriminate between different images and are robust to image size variation, are chosen and normalized as the signature for each block in an image frame for matching between the reference video clip and the query one. Experimental results show that the proposed video signature has a better performance than ordinal signature in ROC curve.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.337-351
• /
• 2021

Automatically recognizing facial expressions in video sequences is a challenging task because there is little direct correlation between facial features and subjective emotions in video. To overcome the problem, a video facial expression recognition method using spatiotemporal recurrent neural network and feature fusion is proposed. Firstly, the video is preprocessed. Then, the double-layer cascade structure is used to detect a face in a video image. In addition, two deep convolutional neural networks are used to extract the time-domain and airspace facial features in the video. The spatial convolutional neural network is used to extract the spatial information features from each frame of the static expression images in the video. The temporal convolutional neural network is used to extract the dynamic information features from the optical flow information from multiple frames of expression images in the video. A multiplication fusion is performed with the spatiotemporal features learned by the two deep convolutional neural networks. Finally, the fused features are input to the support vector machine to realize the facial expression classification task. The experimental results on cNTERFACE, RML, and AFEW6.0 datasets show that the recognition rates obtained by the proposed method are as high as 88.67%, 70.32%, and 63.84%, respectively. Comparative experiments show that the proposed method obtains higher recognition accuracy than other recently reported methods.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.435-436
• /
• 2006

When working with multi-view images, imbalances between multi-view images occur a serious problem in multi-view video coding because they decrease the performance of disparity estimation. To overcome this problem, we propose inter-view balanced disparity estimation for multi-view video coding. In general, the imbalance problem can be solved by a preprocessing step that transforms reference images linearly. However, there are some problems in pre-processing such as the transformation of the original images. In order to obtain a balancing effect among the views, we perform block-based disparity estimation, which includes several balancing parameters.

• 한국통신학회논문지
• /
• 제35권11B호
• /
• pp.1732-1737
• /
• 2010

현재 군에서 무인기를 운용하는 주목적 중 하나는 적에 대한 감시/정찰이다. 이를 위해 무인기는 정보감시/정찰(ISR) 장비들을 탑재하여, 감시/정찰 대상에 대한 영상 데이터를 획득한 후 지상통제소로 전송한다. 지상통제소는 전송된 영상 데이터를 수신한 후, 다양한 사용자에게 배포하게 되는 데, 이 때 품질 보장을 유지하는 것이 중요하다. 본 논문에서는 DDS 표준 프로토콜을 사용하여 무인기의 영상전송 및 품질보장을 관리하는 방안을 제시하였다. 이에 대해 H.264 및 JPEG2000 영상 데이터를 이용하여 영상전송 실험결과 DDS 표준이 UAS 운용에 활용 가능함을 보였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2005년도 추계종합학술대회
• /
• pp.549-552
• /
• 2005

This paper presents a 3D video content generation technique and system that uses the multi-view images and the depth map. The proposed uses 3-view video and depth inputs from the 3-view video camera and depth camera for the 3D video content production. Each camera is calibrated using Tsai's calibration method, and its parameters are used to rectify multi-view images for the multi-view stereo matching. The depth and disparity maps for the center-view are obtained from both the depth camera and the multi-view stereo matching technique. These two maps are fused to obtain more reliable depth map. Obtained depth map is not only used to insert a virtual object to the scene based on the depth key, but is also used to synthesize virtual viewpoint images. Some preliminary test results are given to show the functionality of the proposed technique.

• 한국환경과학회지
• /
• 제25권9호
• /
• pp.1223-1231
• /
• 2016

To create urban landscapes that take human emotion into consideration, the present study verified the psychological effects of artificial waterscape facilities on users, as these facilities significantly impact their psychological comfort. Data was collected using the SD scales and POMS of 60 male and 60 female participants after they watched a video of four waterscape facilities. Participants deemed the video clip of a fountain waterscape to be artificial and linked it with changeable images that increased their vigor. The video clip of waterfall stimulated various impressions (e.g., vital, liked, active, etc.) and changed participant' mood states by increasing their vigor and decreasing fatigue. The video clip of the pond yielded familiar impressions, produced less free images, and decreased tension among participants. Finally, the video clip of the stream stimulated quiet and comfortable images as well as reduced negative feelings of anger, confusion, and depression among participants. Furthermore, males experienced more positive effects than females, regardless of the type of waterscape facility. The study findings indicate that the four different waterscape facilities influenced participants' mood states. Additionally, the psychological effects differed by gender. The data suggest that landscape planners need to carefully consider their choice of waterscape facility when designing green spaces to ensure that the space is psychologically comforting to users.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2022년도 하계학술대회
• /
• pp.825-828
• /
• 2022

In this paper, we propose an efficient image size selection method for video-based point cloud compression. The current MPEG video-based point cloud compression reference encoding process configures a threshold on the size of images while converting point cloud data into images. Because the converted image is compressed and restored by the legacy video codec, the size of the image is one of the main components in influencing the compression efficiency. If the image size can be made smaller than the image size determined by the threshold, compression efficiency can be improved. Here, we studied how to improve the compression efficiency by selecting the best-fit image size generated during video-based point cloud compression. Experimental results show that the proposed method can reduce the encoding time by 6 percent without loss of coding performance compared to the test model 15.0 version of video-based point cloud encoder.

• 한국항행학회논문지
• /
• 제14권4호
• /
• pp.553-561
• /
• 2010

본 논문에서는 로봇의 시각시스템에 효과적으로 적용할 수 있는 얼굴 추적 방법을 제안하였다. 제안한 알고리즘은 동영상의 움직임 영역을 검출한 후 얼굴 영역을 추적한다. 동영상의 움직임 검출은 연속되는 2개의 프레임을 사용하여 차영상을 구한 후, 잡음을 제거하기 위한 방법으로 메디안 필터와 침식 및 팽창연산을 사용하여 움직임 영역을 검출한다. 움직임 영역에서 피부색을 추출하기 위하여 표본영상의 칼라 정보를 이용하였다. 칼라정보의 MIN-MAX값을 퍼지화 데이터로 멤버십 함수를 생성한 후, 유사도를 평가하여 피부색 영역과 배경영역을 분리하였다. 얼굴 후보영역에 대하여 CMY 칼라 공간 C 채널에서 눈을 검출하고, YIQ 칼라 공간 Q 채널에서 입을 검출하였다. 지식기반으로 검출된 눈과 입의 특징을 찾아가며 얼굴영역을 추적하였다. 실험영상으로는 10명 각각에 대하여 150프레임의 동영상 총 1,500프레임을 입력받아 실험한 결과, 1,435프레임의 영상에 대하여 움직임 영역이 검출되어 95.7%의 프레임 검출율을 보였으며, 1,401개에 대한 얼굴을 추적 97.6%의 우수한 얼굴 추적결과를 나타내었다.

• 스마트미디어저널
• /
• 제1권3호
• /
• pp.36-42
• /
• 2012

요즘 스마트폰과 스마트 TV와 같은 스마트 기기에 대한 관심이 높아짐에 따라 보다 다양한 기능을 포함하는 영상장치가 주목받고 있다. 특히, 스마트 TV는 3차원 영상을 서비스함에 따라 보다 고화질의 3차원 영상을 효율적으로 부호화하는 것이 중요하다. 최근 MPEG(moving picture experts group) 그룹에서는 다시점 영상과 깊이 영상을 동시에 압축하여 부호화하는 표준화 작업이 진행되고 있다. 제한된 수의 시점을 이용하여 편안한 3차원 입체 영상을 재현하기 위해서는, 충분한 수의 중간시점의 영상을 생성해야 한다. 깊이정보를 이용하여 3차원 워핑을 수행하면 가상시점의 영상을 합성할 수 있는데, 깊이값의 정확도에 따라 화질이 달라진다. 스테레오 정합 기술을 이용하여 깊이맵을 획득할 때 객체의 경계와 같은 깊이값 불연속 영역에서 깊이값 오류가 발생할 수 있다. 이러한 오류는 생성한 중간영상의 배경에 원치 않는 잡음을 생성한다. 본 논문에서는 편안한 3차원 비디오 재현을 위하여 깊이맵을 기반으로 중간시점의 영상을 생성할 때 발생하는 경계 잡음을 제거하는 방법을 제안한다. 중간시점의 영상을 합성할 때 비폐색 영역을 합성한 후 경계 잡음이 발생할 수 있는 영역을 구별한 다음, 잡음이 없는 참조영상으로 대체함으로써 경계 잡음을 제거할 수 있다. 실험 결과를 통해 배경 잡음이 사라진 자연스러운 합성영상을 생성했다.