• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.625-630
• /
• 2009

Researches of image-based 3D reconstruction have recently produced a number of good results, but they assumed that the accurate foreground to be reconstructed is already extracted from each input image. This paper proposes a novel approach to extract more accurate foregrounds by iteratively performing foreground extraction and 3D reconstruction in a manner similar to an EM algorithm on regions segmented in an initial stage, called segments. Here, the segments should preserve foreground boundaries to compensate for the boundary errors generated by visual hull, simple 3D reconstruction to minimize the computational time, and should also be composed of the small number of sets to minimize the user input. Therefore, we utilize image segmentation using the graph-cuts method, which minimizes energy function composed of data and smoothness terms, and the two methods are iteratively performed until the energy function is optimized. In the experiments, more accurate results of the foreground, especially in boundaries, were obtained, although the proposed method used a simple 3D reconstruction method.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.3
• /
• pp.237-246
• /
• 2001

A high speed context-free marker-controlled and minima imposition-free watershed transform is proposed for efficient multi-object detection and segmentation from a complex background. The context-free markers are extracted from a complex backgrounded multi-object image using a noise tolerant attention operator. These make marker-controlled watershed possible for the over-segmentation reduction without region merging. The proposed method presents a marker-constrained labeling that can speed up the segmentation of a marker-controlled watershed transform by eliminating the necessity of the minima imposition. Simulation results show that the proposed method can efficiently detects and segments multiple objects from a complex background while reducing over- segmentation and the computation time.

• Journal of Broadcast Engineering
• /
• v.27 no.4
• /
• pp.561-568
• /
• 2022

Most deep learning-based video object segmentation methods perform the segmentation with past prediction information stored in external memory. In general, the more past information is stored in the memory, the better results can be obtained by accumulating evidence for various changes in the objects of interest. However, all information cannot be stored in the memory due to hardware limitations, resulting in performance degradation. In this paper, we propose a method of storing new information in the external memory without additional memory allocation. Specifically, after calculating the attention score between the existing memory and the information to be newly stored, new information is added to the corresponding memory according to each score. In this way, the method works robustly because the attention mechanism reflects the object changes well without using additional memory. In addition, the update rate is adaptively determined according to the accumulated number of matches in the memory so that the frequently updated samples store more information to maintain reliable information.

• The KIPS Transactions:PartB
• /
• v.9B no.3
• /
• pp.359-368
• /
• 2002

In this paper, we propose effective boundary line extraction algorithm for moving objects by matching error image and moving vectors, and fast tracking algorithm for moving object by partial boundary lines. We extracted boundary line for moving object by generating seeds with probability distribution function based on Watershed algorithm, and by extracting boundary line for moving objects through extending seeds, and then by using moving vectors. We processed tracking algorithm for moving object by using a part of boundary lines as features. We set up a part of every-direction boundary line for moving object as the initial feature vectors for moving objects. Then, we tracked moving object within current frames by using feature vector for the previous frames. As the result of the simulation for tracking moving object on the real images, we found that tracking processing of the proposed algorithm was simple due to tracking boundary line only for moving object as a feature, in contrast to the traditional tracking algorithm for active contour line that have varying processing cost with the length of boundary line. The operations was reduced about 39% as contrasted with the full search BMA. Tracking error was less than 4 pixel when the feature vector was $(15\times{5)}$ through the information of every-direction boundary line. The proposed algorithm just needed 200 times of search operation.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.3
• /
• pp.687-696
• /
• 2014

This paper presents a semantic object extraction method using user's stroke input, color, and depth information. It is supposed that a semantically meaningful object is surrounded with a few strokes from a user, and has similar depths all over the object. In the proposed method, deciding the region of interest (ROI) is based on the stroke input, and the semantically meaningful object is extracted by using color and depth information. Specifically, the proposed method consists of two steps. The first step is over-segmentation inside the ROI using color and depth information. The second step is semantically meaningful object extraction where over-segmented regions are classified into the object region and the background region according to the depth of each region. In the over-segmentation step, we propose a new marker extraction method where there are two propositions, i.e. an adaptive thresholding scheme to maximize the number of the segmented regions and an adaptive weighting scheme for color and depth components in computation of the morphological gradients that is required in the marker extraction. In the semantically meaningful object extraction, we classify over-segmented regions into the object region and the background region in order of the boundary regions to the inner regions, the average depth of each region being compared to the average depth of all regions classified into the object region. In experimental results, we demonstrate that the proposed method yields reasonable object extraction results.

• Smart Media Journal
• /
• v.9 no.2
• /
• pp.9-15
• /
• 2020

In this paper, we propose a network model composed of Multi path Encoder-Decoder branches that can recognize each instance from the image. The network has two branches, Dot branch and Segmentation branch for finding the center point of each instance and for recognizing area of the instance, respectively. In the experiment, the CVPPP dataset was studied to distinguish leaves from each other, and the center point detection branch(Dot branch) found the center points of each leaf, and the object segmentation branch(Segmentation branch) finally predicted the pixel area of each leaf corresponding to each center point. In the existing segmentation methods, there were problems of finding various sizes and positions of anchor boxes (N > 1k) for checking objects. Also, there were difficulties of estimating the number of undefined instances per image. In the proposed network, an effective method finding instances based on their center points is proposed.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.11a
• /
• pp.100-103
• /
• 2015

본 논문에서는 실내에서 RGBD 영상을 이용하여 물체를 검출하는 방법을 제안한다. 특정 물체가 아닌 일반적인 여러 가지 물체에 대한 특징을 규정하기 어려우므로 본 논문에서는 영상 정보에 의존하기 보다 물체와 픽셀의 기하학적 구조에 기반하여 물체를 검출한다. 우선 컬러 정보를 이용하여 대략적인 영상 영역분할을 하고 이를 같은 레이블로 분류하여 물체와 배경의 후보를 얻는다. 대체로 실내 환경에서 바닥은 평면이라 가정할 수 있으므로 바닥의 평면 모델을 만들어서 물체 후보에서 이를 제외시킨다. 또한, 물체에 대한 간단한 가정을 통해 바닥 이외의 배경 역시 물체와 구분하여서 물체 후보들을 가려낸다. 최종적으로 3 차원 공간에서 가까이 위치하는 레이블을 하나로 통합하는 과정을 통해 최종적인 물체 영역을 검출하고 이를 bounding box 로 표시한다. 직접 촬영한 몇몇 실내 RGBD 영상에서 실험한 결과, 제안하는 방법이 기존 방법들에 비해 물체 검출 성능이 좋은 것을 확인하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.04a
• /
• pp.1037-1041
• /
• 2000

본 논문에서는 웨이블릿 변환을 이용하여 추정된 변위 벡터와 이를 이용한 물체의 분할을 통해 특징 점을 추출하고 3차원 와이어 프레임(wire-frame)을 생성하는 알고리즘을 제안한다. 우선, 웨이블릿 변환을 이용하여 빠른 시간 안에 변위를 측정하고, 이를 통해 배경과 물체를 분리해 내었다. 그런 뒤에, 변위 벡터를 이용하여, 깊이 정보를 추정해 내고, 동시에 물체로부터 두드러진 특징 값들을 추출하여 3차원 와이어 프레임 생성을 위한 거리 값으로 사용하였다. 마지막으로, 일반적인 delaunay triangulation에서 생길 수 있는 오 정합을 본 논문에서 제안하는 전경/배경 분할 알고리즘을 이용하여 제거 하여 정확한 3차원 모델을 생성하였다. 아울러, 본 논문에서 제안하는 웨이블릿을 이용한 빠른 3D 모델링 방법을 원 영상을 이용한 방법과 비교하여, 더 좋은 결과를 보여줌으로써, 계산 시간 뿐만 아니라 정확성에서도 만족할 만한 결과를 얻을 수 있었다.

• Journal of the Korea Computer Graphics Society
• /
• v.7 no.1
• /
• pp.1-9
• /
• 2001

We present a scheme and a data structure that decompose the space into adaptive-sized cells to improve the visualization of soft objects. Soft objects are visualized through the evaluation of the field functions at every point of the space. According to the propsed scheme, the affecting soft objects for a point in the space is searched through the data structure called interval tree based on the bounding volume of the components, which represent a soft object whose defining primitive(skeleton) is a simple geometric object such as point or line segment. The bounding volume of each component is generated with respect to the radius of a local field function of the component, threshold value, and the relations between the components and other neighboring components. The proposed scheme can be used in many applications for soft objects such as modeling and rendering, especially in interactive modeling process.

• Proceedings of the KIEE Conference
• /
• 2009.07a
• /
• pp.1853_1854
• /
• 2009

본 논문은 스네이크 에너지에 칼라분산 성분을 추가함으로써 스네이크 알고리즘을 이용하는 강인한 영상분할기법을 제안한다. 일반적인 스네이크 알고리즘은 영상의 밝기 값만을 고려하여 관심영역을 분할하기 때문에 인접하는 영역과 다른 칼라정보를 갖더라도 인접하는 물체와 유사한 밝기 값을 가지면 영상분할하기 어렵다. 제안하는 알고리즘은 복잡한 배경에서 인접하는 영역과 칼라성분이 다른 관심영역을 효율적으로 분할하기 위해, 기존의 snake 알고리즘에 칼라분산(color variance) 에너지 요소를 추가하였다. 특정 칼라 값을 갖는 물체들이 섞여있는 복잡한 배경 영상들의 실험을 통해 제안하는 칼라분산 기반 확장 스네이크 알고리즘의 우수성을 입증하였다.