• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.181-184
• /
• 2005

기존의 비디오 분할 방법은 밝기의 변화가 큰 영상이나 움직임이 큰 영상에 대해서는 정확한 분할이 이루어지지 않았다. 본 논문은 움직임 정보를 이용하여 움직임이 큰 영상에서 좀 더 정확하게 비디오를 분할할 수 있는 방법을 제안한다. 이를 위해 블록 정합 알고리즘을 이용하여 얻어진 움직임 벡터로부터 움직임 유사도를 찾는 방법을 제안한다. 또 연속된 프레임에서 픽셀의 차이 값을 계산할 때 motion blur 로 생기는 오차를 각 블록의 움직임 크기로 보상하여 좀 더 정확한 픽셀의 차이 값을 계산하는 방법을 제안한다. 이렇게 얻어진 두 가지 정보를 이용하여 discontinuity value 를 계산한다. 움직임이 많은 액션 영화 3 편에 대해 실험한 결과 제안한 방법이 기존의 움직임 유사도와 픽셀 차이 값을 구하여 샷 경계 검출을 하는 방법보다 좀 더 정확한 샷 경계 검출을 하고 있다는 것을 보여준다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.4 s.310
• /
• pp.74-86
• /
• 2006

This paper proposes a robust and computationally efficient algorithm for automatic video object segmentation. For implementing the spatio-temporal segmentation, which aims for efficient combination of the motion segmentation and the color segmentation, an SOM-based hierarchical clustering method in which the segmentation process is regarded as clustering of feature vectors is employed. As results, problems of high computational complexity which required for obtaining exact segmentation results in conventional video object segmentation methods, and the performance degradation due to noise are significantly reduced. A measure of motion vector reliability which employs MRF-based MAP estimation scheme has been introduced to minimize the influence from the motion estimation error. In addition, a noise elimination scheme based on the motion reliability histogram and a clustering validity index for automatically identifying the number of objects in the scene have been applied. A cross projection method for effective object tracking and a dynamic memory to maintain temporal coherency have been introduced as well. A set of experiments has been conducted over several video sequences to evaluate the proposed algorithm, and the efficiency in terms of computational complexity, robustness from noise, and higher segmentation accuracy of the proposed algorithm have been proved.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.279-282
• /
• 2001

본 논문에서는 가상의 블루스크린(Virtual Blue Screens, VBS)을 이용한 반자동 영상분할 기법을 제안한다. 가상 블루스크린은 동영상에서 배경영역을 특정한 값으로 채워 만든 참조영상으로 정의한다. 반자동 영상 분할 기법은 크게 화면내 영상분할과 화면간 영상분할의 두 단계로 이루어진다. 화면내 영상분할은 VBS와 원영상의 형태학적 분할 기법을 사용하고, 화면간 영상 분할은 두개의 연속하는 화면에서 변화검출(Change Detection)로 이루어진다 [1]. 본 논문에서는 효과적인 변화검출을 위하여 제안된 VBS를 사용한다. VBS를 이용한 영상분할에서는 우선, 이전화면에서 만들어진 VBS를 참조하여 다음화면에서 움직임 영역을 예측한다. 이렇게 예측된 영상과 원영상에 대해 형태학적 분할 기법(Morphological Segmentation Technique)을 이용해서 각각에 대한 레이블 마스크(Label Mask)를 얻는다 [2]. 두개의 레이블 마스크 사이에는 서로 공통된 영역들이 존재하게 되는데, 이런 공통된 영역을 추출함으로써 움직임 객체를 검출한다. 현재화면에서 검출된 움직임 객체는 다음화면을 위한 가상의 블루 스크린을 만드는데 사용한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2003.11a
• /
• pp.47-50
• /
• 2003

본 논문에서는 동영상을 효율적으로 부호화하기 위한 새로운 다중해상도 움직임 보상 방법과 잉여 양자화 방법을 제안한다. 본 논문에서 제안하는 동영상 부호화기는 다단계 이산웨이브렛 분해 움직임 예측 및 움직임 보상 블록 Tree 의 구성 및 블록 분할. 적응적 산술 부호화기로 구성된다 제안된 동영상 부호화기는 단순하면서도 낮은 연산량을 필요로 하며, 임베디드 특성과 SNR 계위 부호화 특성과 같은 좋은 기능을 제공한다. 또한 기존에 제안되었던 이산웨이브렛변환을 이용하는 동영상 부호화 방법과 비교하여 우수한 성능을 제공한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.12C
• /
• pp.1147-1153
• /
• 2009

We propose a novel image segmentation and segment-based stereo matching technique using color, depth, and motion information. Proposed technique firstly splits reference images into foreground region or background region using depth information from depth camera. Then each region is segmented into small segments with color information. Moreover, extracted segments in current frame are tracked in the next frame in order to maintain depth consistency between frames. The initial depth from the depth camera is also used to set the depth search range for stereo matching. Proposed segment-based stereo matching technique was compared with conventional one without foreground and background separation and other conventional one without motion tracking of segments. Simulation results showed that the improvement of segment extraction and depth estimation consistencies by proposed technique compared to conventional ones especially at the static background region.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.1
• /
• pp.1-16
• /
• 1996

In this paper, by combining the motion compensated transform coding with the sub-band decomposition technique, we present a motion compensated sub-band coding technique(MCSBC) for image sequence coding. Several problems related to the MCSBC, such as a scheme for motion compensation in each sub-band and the efficient VWL coding of the DCT coefficients in each sub-band are discussed. For an efficient coding, the motion estimation and compensation is performed only on the LL sub-band, but the discrete cosine transform(DCT) is employed to encode all sub-bands in our approach. Then, the transform coefficients in each sub-band are scanned in a different manner depending on the energy distributions in the DCT domain, and coded by using separate 2-D Huffman code tables, which are optimized to the probability distributions in the DCT domain, and coded by using separate 2-D Huffman code tables, which are optimized to the probability distribution of each sub-band. The performance of the proposed MCSBC technique is intensively examined by computer simulations on the HDTV image sequences. The simulation results reveal that the proposed MCSBC technique outperforms other coding techniques, especially the well-known motion compensated transform coding technique by about 1.5dB, in terms of the average peak signal to noise ratio.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.1
• /
• pp.30-38
• /
• 2003

This paper presents an efficient region-based motion segmentation method for segmenting of moving objects in a traffic scene with a focus on a Video Monitoring System (VMS). The presented method consists of two phases: motion detection and motion segmentation. Using the adaptive thresholding technique, the differences between two consecutive frames are analyzed to detect the movements of objects in a scene. To segment the detected regions into meaningful objects which have the similar intensity and motion information, the regions are initially segmented using a k-means clustering algorithm and then, the neighboring regions with the similar motion information are merged. Since we deal with not the whole image, but the detected regions in the segmentation phase, the computational cost is reduced dramatically. Experimental results demonstrate robustness in the occlusions among multiple moving objects and the change in environmental conditions as well.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.308-309
• /
• 2008

본 논문에서는 추적하고자 하는 관심객체를 일정한 크기의 블록으로 나누어 각 블록이 독립적으로 추적을 수행한다. 나누어진 각 블록들은 NCC(Normalized Cross Correlation)를 사용하여 통계적인 특성을 고려하여 움직임을 추정한다. 추정된 블록들의 움직임 벡터 중 평한 벡터보다 일정 값 이상 큰 블록은 관심객체 움직임 벡터 추정 시 제외시킴으로써 잘못된 추정으로 인한 에러를 줄인다. 선택된 블록들의 추정 에러값에 따라 추정값이 높은 블록의 움직임 벡터는 높은 가중치를 적용하고 추정값이 낮은 블록의 움직임 벡터는 낮은 가중치를 적용하여 추적 신뢰도를 높였다. 실험결과, 제안된 알고리즘은 강건한 실시간 추적이 가능함을 보여준다.

• Journal of Korea Multimedia Society
• /
• v.15 no.4
• /
• pp.485-491
• /
• 2012

This paper proposes 'Coding Unit Tree' based on quadtree efficiently with motion vector to represent splitting information of a Coding Unit (CU) in HEVC. The new international video coding, High Efficiency Video Coding (HEVC), adopts various techniques and new unit concept: CU, Prediction Unit (PU), and Transform Unit (TU). The basic coding unit, CU is larger than macroblock of H.264/AVC and it splits to process image-based quadtree with a hierarchical structure. However, in case that there are complex motions in CU, the more signaling bits with motion information need to be transmitted. This structure provides a flexibility and a base for a optimization, but there are overhead about splitting information. This paper analyzes those signals and proposes a new algorithm which removes those redundancy. The proposed algorithm utilizes a type code, a dominant value, and residue values at a node in quadtree to remove the addition bits. Type code represents a structure of an image tree and the two values represent a node value. The results show that the proposed algorithm gains 13.6% bit-rate reduction over the HM-1.0.

• Journal of Korea Multimedia Society
• /
• v.7 no.9
• /
• pp.1240-1245
• /
• 2004

This paper presents the moving objects segmentation algorithms from the sequence images in the stationary backgrounds such as surveillance camera and video phone and so on. In this paper, the moving object area is extracted with proposed object searching algorithm and then moving object is segmented within the moving object area. Also the proposed algorithms have the robustness against noise problems and results show the proposed algorithm is able to efficiently segment and track the moving object area.