• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.07a
• /
• pp.116-118
• /
• 2010

본 논문에서는 영역 분할과 영상의 움직임 정보를 이용한 깊이맵 생성에 관한 기법을 제안하였다. 2D/3D 변환 알고리즘에서 2차원 영상에서 얻은 깊이 정보는 2차원 영상을 3차원 영상으로 변환 가능하게 하는 핵심 기술이 된다. 영역을 분할하고 계산되어진 움직임 값 (intensity)을 분할된 각 영역에 부여함으로서 깊이맵을 얻을 수 있다. 본 논문에서는 초기 단계에서 영역을 분할한 뒤, 입력 영상을 그룹화 하여 양방향 탐색을 통한 움직임 추정 연산을 수행토록 하여 보다 정확한 깊이 정보를 획득하고, 최종적으로 얻은 결과에 각 화소에 해당 되는 확률적 통계에 의한 후처리 기법을 사용하였다. 보다 정확한 깊이정보를 영역별로 지정하고, 후처리 기법을 사용함에 따라 보다 신뢰도 높은 깊이맵 영상을 생성할 수 있었다.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2780-2782
• /
• 2005

In this paper, we present a mobile robot localization solution by using a Ubiquitous Vision System (UVS). The collective information gathered by multiple cameras that are strategically placed has many advantages. For example, aggregation of information from multiple viewpoints reduces the uncertainty about the robots' positions. We construct UVS as a multi-agent system by regarding each vision sensor as one vision agent (VA). Each VA performs target segmentation by color and motion information as well as visual tracking for multiple objects. Our modified identified contractnet (ICN) protocol is used for communication between VAs to coordinate multitask. This protocol raises scalability and modularity of thesystem because of independent number of VAs and needless calibration. Furthermore, the handover between VAs by using ICN is seamless. Experimental results show the robustness of the solution with respect to a widespread area. The performance in indoor environments shows the feasibility of the proposed solution in real-time.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.26 no.7
• /
• pp.132-139
• /
• 1989

Optical flow is important not only for determining velocity and trajectory of the object but also for image segmentation and 3D information. The gradient-based method is mostly used to compute optical flow form image sequences, but it accomanies smoothing effect of velocity vectors. In this paper, an enhanced algorithm for computing optical flow using scalar edge to restrict is also applied to reduce errors both around motion boundary and in the occlusion region.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.12
• /
• pp.1115-1121
• /
• 2012

This paper proposes a method to extract accurate plane of an object in unstructured environment for a humanoid robot by using a laser scanner. By panning and tilting 2D laser scanner installed on the head of a humanoid robot, 3D depth map of unstructured environment is generated. After generating the 3D depth map around a robot, the proposed plane extraction method is applied to the 3D depth map. By using the hierarchical clustering method, points on the same plane are extracted from the point cloud in the 3D depth map. After segmenting the plane from the point cloud, dimensions of the planes are calculated. The accuracy of the extracted plane is evaluated with experimental results, which show the effectiveness of the proposed method to extract planes around a humanoid robot in unstructured environment.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.493-495
• /
• 2000

동영상에서 동작물체 영역과 배경 영역을 추출하는 방법에는 크게 원본 영상들의 특징값을 이용하는 방법, 동작벡터 혹은 광류를 이용하는 방법, 그리고 동작벡터와 원본영상을 모두 이용하는 방법의 세가지가 있다. 이중 많이 사용되고 있는 동작벡터를 이용하는 방법에는 히스토그램을 이용하는 방법과 동작벡터의 특징값에 대한 클러스터링을 이용해 분할 하는 방법이 있는데. 이들 기존 방법은 몇가지 문제점을 가지고 있다. 전자는 구현이 간단하나 세부적인 영역분할이 어렵다는 문제점이 있고, 후자는 일반적으로 높은 계산 복잡도를 가지며 초기 클러스터 개수 선정에 문제를 지니고 있다. 본 논문에서는 낮은 계산 복잡도를 가지며 클러스터 할당과 병합된 클러스터 중심 계산에 있어 보다 적응적인 Seeded Split-Merge 클러스터링 방법을 제안한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.243-243
• /
• 2000

This paper introduces a visual inspecting and monitoring system based on an image processing technique. We propose an image processing method for analyzing landslide movement in real time. The method adopts Laplacian of Gaussian operator to extract linear features for the captured images and uses a linear matching algorithm to distinguish the matching error for those features. When the algorithm is processed, motion parameters such as displacement area and its direction are computed. Once movement is recognized, displacements are estimated graphically with statistical amount in the image plane. The simulation results are shown us to verify the effectiveness of the developed method.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.2
• /
• pp.961-968
• /
• 2018

Recently, researches on automatic recognition of human activities have been actively carried out with the emergence of various intelligent systems. Since a large amount of visual data can be secured through Closed Circuit Television, it is required to recognize human behavior in a dynamic situation rather than a static situation. In this paper, we propose new intelligent human activity recognition model using the trajectory information extracted from the video sequence. The proposed model consists of three steps: segmentation and partitioning of trajectory step, feature extraction step, and behavioral learning step. First, the entire trajectory is fuzzy partitioned according to the motion characteristics, and then temporal features and spatial features are extracted. Using the extracted features, four pedestrian behaviors were modeled by decision tree learning algorithm and performance evaluation was performed. The experiments in this paper were conducted using Caviar data sets. Experimental results show that trajectory provides good activity recognition accuracy by extracting instantaneous property and distinctive regional property.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.3041-3043
• /
• 2000

GUI(graphical user interface) has been the dominant platform for HCI(human computer interaction). The GUI-based style of interaction has made computers simpler and easier to use. However GUI will not easily support the range of interaction necessary to meet users' needs that are natural, intuitive, and adaptive. In this paper we study an approach to track a hand in an image sequence and recognize it, in each video frame for replacing the mouse as a pointing device to virtual reality. An algorithm for real time processing is proposed by estimating of the position of the hand and segmentation, considering the orientation of motion and color distribution of hand region.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.2
• /
• pp.31-36
• /
• 2020

Most of the background subtraction algorithms show good performance in static scenes. In the case of dynamic scenes, they frequently cause false alarm to "temporal clutter", a repetitive motion within a certain area. In this paper, we propose a robust technique for the multiple interval pixel sampling (MIS) algorithm to handle highly dynamic scenes. An adaptive threshold scheme is used to suppress false alarms in low-confidence regions. We also utilize multiple background models in the foreground segmentation process to handle repetitive background movements. Experimental results revealed that our approach works well in handling various temporal clutters.

• Annual Conference of KIPS
• /
• 2001.10a
• /
• pp.699-702
• /
• 2001

본 논문은 연속적인 영상에서 움직임을 추적하는데 있어서 웨이브릿(Wavelets)과 투영(Projection)을 사용하여 물체의 움직임을 추적하는 기법을 제안한다. 움직임을 추적하는 방법중 웨이브릿을 이용한 방법으로는 하나의 영상에서 물체의 특징을 찾는데 2차 웨이브릿 변환이 사용되고 있으며 연속적인 영상에 대한 분석에서 시간에 대한 또 하나의 변환을 해 줌으로써 움직이는 물체의 정보를 얻어낼 수 있다. 3차 웨이브릿에서 유도된 데이터를 가지고 수평에 민감한 데이터는 X축으로 투영을, 수직에 민감한 데이터는 Y축으로 투영을 하여 물체를 영역화한 후 추적함으로써 실시간으로 물체를 추적한다. 특히 서로 다른 방향으로 민감성을 보여주는 웨이브릿 계수들은 움직이는 물체를 더욱 정확하게 영역화 하는데 많은 도움을 준다. 물체가 깊이 방향으로 움직여도 투영된 데이터로 영역화(Segmentation)한 데이터의 크기를 가지고 쉽게 분석된다. 본 논문에서 제시한 3차 웨이브릿과 투영 기법을 이용한 조합으로 분석된 실험 결과와 앞으로의 과제가 마지막 부분에 서술되었다.