• Journal of KIISE:Software and Applications
• /
• v.35 no.11
• /
• pp.671-680
• /
• 2008

Motion capture devices have been utilized in producing several contents, such as movies and video games. However, since motion capture devices are expensive and inconvenient to use, motions segmented from captured data was recycled and synthesized to utilize it in another contents, but the motions were generally segmented by contents producers in manual. Therefore, automatic motion segmentation is recently getting a lot of attentions. Previous approaches are divided into on-line and off-line, where ow line approaches segment motions based on similarities between neighboring frames and off-line approaches segment motions by capturing the global characteristics in feature space. In this paper, we propose a graph-based high-level motion segmentation method. Since high-level motions consist of repeated frames within temporal distances, we consider similarities between neighboring frames as well as all similarities among all frames within the temporal distance. This is achieved by constructing a graph, where each vertex represents a frame and the edges between the frames are weighted by their similarity. Then, normalized cuts algorithm is used to partition the constructed graph into several sub-graphs by globally finding minimum cuts. In the experiments, the results using the proposed method showed better performance than PCA-based method in on-line and GMM-based method in off-line, as the proposed method globally segment motions from the graph constructed based similarities between neighboring frames as well as similarities among all frames within temporal distances.

• Journal of KIISE:Software and Applications
• /
• v.36 no.11
• /
• pp.936-946
• /
• 2009

A graph cuts method has recently attracted a lot of attentions for image segmentation, as it can globally minimize energy functions composed of data term that reflects how each pixel fits into prior information for each class and smoothness term that penalizes discontinuities between neighboring pixels. In previous approaches to graph cuts-based automatic image segmentation, GMM(Gaussian mixture models) is generally used, and means and covariance matrixes calculated by EM algorithm were used as prior information for each cluster. However, it is practicable only for clusters with a hyper-spherical or hyper-ellipsoidal shape, as the cluster was represented based on the covariance matrix centered on the mean. For arbitrary-shaped clusters, this paper proposes graph cuts-based image segmentation using mean shift analysis. As a prior information to estimate the data term, we use the set of mean trajectories toward each mode from initial means randomly selected in $L^*u^*{\upsilon}^*$ color space. Since the mean shift procedure requires many computational times, we transform features in continuous feature space into 3D discrete grid, and use 3D kernel based on the first moment in the grid, which are needed to move the means to modes. In the experiments, we investigate the problems of mean shift-based and normalized cuts-based image segmentation methods that are recently popular methods, and the proposed method showed better performance than previous two methods and graph cuts-based automatic image segmentation using GMM on Berkeley segmentation dataset.

• Journal of the Semiconductor & Display Technology
• /
• v.16 no.2
• /
• pp.70-74
• /
• 2017

Given two stereo images of a scene, it is possible to recover a 3D understanding of the scene. This is the primary way that the human visual system estimates depth. This process is useful in applications like robotics, where depth sensors may be expensive but a pair of cameras is relatively cheap. In this work, we combined our interests to implement a graph cut algorithm for stereo correspondence, and performed evaluation against a baseline algorithm using normalized cross correlation across a variety of metrics. Experimental trials revealed that the proposed descriptor exhibited a significant improvement, compared to the other existing methods.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.522-526
• /
• 2008

모션 캡쳐 장비는 사람의 자연스러운 행동이나 동작 정보를 정밀하게 얻기 위해 널리 사용되며, 영화나 게임과 같은 콘텐츠에서 자주 활용되고 있다. 하지만 모션 캡쳐 장비가 고가이기 때문에 한번 입력받은 데이터를 모션별로 분할하고 상황에 맞게 재결합하여 사용할 필요가 있으며, 입력 데이터를 모션별로 분할하는 것은 대부분 수동으로 이루어진다. 이 때문에 캡쳐된 데이터를 자동으로 분할하기 위한 연구들이 다양하게 시도되고 있다. 기존의 연구들은 크게 전역적 특성에 대한 고려없이 이웃하는 프레임만을 고려하는 온라인 방식과 데이터를 전역적으로 고려하나 이웃하는 프레임 사이의 관계를 고려하지 않는 오프라인 방식으로 나누어진다. 본 논문에서는 온라인과 오프라인 방식을 병합한 그래프 기반의 모션 분할 방법을 제안한다. 분할을 위해 먼저 모션데이터를 기반으로 그래프를 생성하며, 그래프는 이웃하는 각 프레임사이의 유사도뿐만 아니라 시간축을 기반으로 일정시간내의 프레임들의 유사도를 모두 고려하였다. 이렇게 생성된 그래프를 분할하기 위해 분할된 모션내의 유사도 합을 최소화하고 각 모션간의 유사도는 최대화할 수 있는 normalized cuts을 이용하였다. 실험에서 제안된 방법은 기존의 오프라인 방식 중 하나인 GMM과 온라인 방식 중 하나인 국부최소값 분할 방법보다 좋은 결과를 보였으며, 이는 각 프레임 사이의 유사도뿐만 아니라 일정시간내의 유사도를 전역적으로 고려하기 때문이다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.437-438
• /
• 2011

Spectral segmentation is a major trend in image segmentation. Specially, constrained spectral segmentation, inspired by the user-given inputs, remains its challenging task. Since it makes use of the spectrum of the affinity matrix of a given image, its overall quality depends mainly on how to design the graphical model. In this work, we propose a sparse, multi-layer graphical model, where the pixels and the over-segmented regions are the graph nodes. Here, the graph affinities are computed by using the must-link and cannot-link constraints as well as the likelihoods that each node has a specific label. They are then used to simultaneously cluster all pixels and regions into visually coherent groups across all layers in a single multi-layer framework of Normalized Cuts. Although we incorporate only the adjacent connections in the multi-layer graph, the foreground object can be efficiently extracted in the spectral framework. The experimental results demonstrate the relevance of our algorithm as compared to existing popular algorithms.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1996.06c
• /
• pp.780-791
• /
• 1996

A hybrid image processing system which automatically distinguished lean tissues in the image of a complex beef cut surface and generated the lean tissue contour has been developed. Because of the in homegeneous distribution and fuzzy pattern of fat and lean tissue on the beef cut, conventional image segmentation and contour generation algorithm suffer from a heavy computing requirement, algorithm complexity and poor robustness. The proposed system utilizes an artificial neural network enhance the robustness of processing. The system is composed of pre-network , network and post-network processing stages. At the pre-network stage, gray level images of beef cuts were segmented and resized to be adequate to the network input. Features such as fat and bone were enhanced and the enhanced input image was converted tot he grid pattern image, whose grid was formed as 4 X4 pixel size. at the network stage, the normalized gray value of each grid image was taken as the network input. Th pre-trained network generated the grid image output of the isolated lean tissue. A training scheme of the network and the separating performance were presented and analyzed. The developed hybrid system showed the feasibility of the human like robust object segmentation and contour generation for the complex , fuzzy and irregular image.