• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.9
• /
• pp.88-96
• /
• 1996

Computer vision-based gesture recognition systems consist of image segmentation, object tracking and decision. However, it is difficult to segment an object from image for gesture in computer systems because of vaious illuminations and backgrounds. In this paper, we describe a method to learn features for segmentation, which improves the performance of computer vision-based hand-gesture recognition systems. Systems interact with a user to acquire exact training data and segment information according to a predefined plan. System provides some models to the user, takes pictures of the user's response and then analyzes the pictures with models and a prior knowledge. The system sends messages to the user and operates learning module to extract information with the analyzed result.

• Journal of Information Processing Systems
• /
• v.9 no.4
• /
• pp.592-601
• /
• 2013

Object segmentation is a challenging task in image processing and computer vision. In this paper, we present a visual attention based segmentation method to segment small sized interesting objects in natural images. Different from the traditional methods, we first search the region of interest by using our novel saliency-based method, which is mainly based on band-pass filtering, to obtain the appropriate frequency. Secondly, we applied the Gaussian Mixture Model (GMM) to locate the object region. By incorporating the visual attention analysis into object segmentation, our proposed approach is able to narrow the search region for object segmentation, so that the accuracy is increased and the computational complexity is reduced. The experimental results indicate that our proposed approach is efficient for object segmentation in natural images, especially for small objects. Our proposed method significantly outperforms traditional GMM based segmentation.

• Journal of Korea Multimedia Society
• /
• v.9 no.12
• /
• pp.1529-1541
• /
• 2006

Moving objects have been widely employed in traffic and logistic applications. Spatio-temporal aggregations mainly describe the moving object's behavior in the spatial data warehouse. The previous works usually express the object moving in some certain region, but ignore the object often moving along as the trajectory. Other researches focus on aggregation and comparison of trajectories. They divide the spatial region into units which records how many times the trajectories passed in the unit time. It not only makes the storage space quite ineffective, but also can not maintain spatial data property. In this paper, a spatio-temporal aggregation index structure for moving object trajectory in constrained network is proposed. An extended B-tree node contains the information of timestamp and the aggregation values of trajectories with two directions. The network is divided into segments and then the spatial index structure is constructed. There are the leaf node and the non leaf node. The leaf node contains the aggregation values of moving object's trajectory and the pointer to the extended B-tree. And the non leaf node contains the MBR(Minimum Bounding Rectangle), MSAV(Max Segment Aggregation Value) and its segment ID. The proposed technique overcomes previous problems efficiently and makes it practicable finding moving object trajectory in the time interval. It improves the shortcoming of R-tree, and makes some improvement to the spatio-temporal data in query processing and storage.

• The KIPS Transactions:PartB
• /
• v.8B no.5
• /
• pp.493-500
• /
• 2001

Video scene segmentation is fundamental role for content based video analysis. In this paper, we propose a new region based video scene segmentation method using continuity test for each object region which is segmented by the watershed algorithm for all frames in video data. For this purpose, we first classify video data segments into classes that are the dynamic and static sections according to the object movement rate by comparing the spatial and shape similarity of each region. And then, try to segment each sections by grouping each sections by comparing the neighbor section sections by comparing the neighbor section similarity. Because, this method uses the region which represented on object as a similarity measure, it can segment video scenes efficiently without undesirable fault alarms by illumination and partial changes.

• The Journal of Korea Robotics Society
• /
• v.4 no.2
• /
• pp.139-146
• /
• 2009

This paper describes how a person extracts a unknown object with pointing gesture while interacting with a robot. Using a stereo vision sensor, our proposed method consists of two stages: the detection of the operators' face, the estimation of the pointing direction, and the extraction of the pointed object. The operator's face is recognized by using the Haar-like features. And then we estimate the 3D pointing direction from the shoulder-to-hand line. Finally, we segment an unknown object from 3D point clouds in estimated region of interest. On the basis of this proposed method, we implemented an object registration system with our mobile robot and obtained reliable experimental results.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.10
• /
• pp.83-92
• /
• 2009

In this paper, an extended snake algorithm using color variance energy is proposed for segmenting an interest object in color image. General snake algorithm makes use of energy in image to segment images into a interesting area and background. There are many kinds of energy that can be used by the snake algorithm. The efficiency of the snake algorithm is depend on what kind of energy is used. A general snake algorithm based on active contour model uses the intensity value as an image energy that can be implemented and analyzed easily. But it is sensitive to noises because the image gradient uses a differential operator to get its image energy. And it is difficult for the general snake algorithm to be applied on the complex image background. Therefore, the proposed snake algorithm efficiently segment an interest object on the color image by adding a color variance of the segmented area to the image energy. This paper executed various experiments to segment an interest object on color images with simple or complex background for verifying the performance of the proposed extended snake algorithm. It shows improved accuracy performance about 12.42 %.

• Geophysics and Geophysical Exploration
• /
• v.25 no.1
• /
• pp.44-49
• /
• 2022

Closed-form expressions of vector gravity and gravity gradient tensor based on a line segment are derived. If a cylindrical object with axial symmetry is observed from a distance, it is possible to approximate it as a line segment; therefore, it is necessary to compute the gravity and the gravity gradient tensor due to a line source by using closed-form expressions. The gravitational potential for a line segment is defined as a one-dimensional integral, and this integral is differentiated with respect to the Cartesian coordinate system to derive the vector gravity. The expressions of the gravity gradient tensor are derived by differentiating the vector gravity once more in the same coordinate system.

• Journal of Internet Computing and Services
• /
• v.10 no.6
• /
• pp.99-111
• /
• 2009

The result of Image segmentation, an indispensable process in image processing, significantly affects the analysis of an image. Despite the significance of image segmentation, it produces some problems when the variation of pixel values is large, or the boundary between background and an object is not clear. Also, these problems occur frequently when many objects in an image are placed very close by. In this paper, when the shape of objects in an image is circular, we proposed an algorithm which segment an each object in an image using the geometric characteristic of circular shape. The proposed algorithm is composed of 4 steps. First is the boundary edge extraction of whole object. Second step is to find the candidate points for further segmentation using the boundary edge in the first step. Calculating the representative circles using the candidate points is the third step. Final step is to draw the line connecting the overlapped points produced by the several erosions and dilations of the representative circles. To verify the efficiency of the proposed algorithm, the algorithm is compared with the three well-known cell segmentation algorithms. Comparison is conducted by the number of segmented region and the correctness of the inner segment line. As the result, the proposed algorithm is better than the well-known algorithms in both the number of segmented region and the correctness of the inner segment line by 16.7% and 21.8%, respectively.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2004.03a
• /
• pp.347-347
• /
• 2004

임상도는 항공사진을 판독하여 얻어진 산림에 관한 정보를 지형도(1/25,000)에 도화 작성한 도면으로 전국 산림조사와 연계하여 10년을 주기로 순환제작 되며, 현재 제 4차 수치임상도가 제작 중에 있다 임상도는 여러 산림관련 주제도 중 가장 많이 활용되는 도면으로 산림 분야뿐만 아니라 다른 분야에서도 널리 활용되고 있다. 그러나 10년을 주기로 제작되므로 부분적으로 현실과 부합하지 않는 내용이 포함되어 있어 각종 계획수립 및 활용에 장애요인으로 작용하고 있다. 따라서 실제 임상정보를 획득할 수 있도록 지속적인 갱신이 필요하다. 그러나 임상도의 부분적 갱신을 위하여 별도의 항공사진을 촬영하는 것은 현실적인 어려움이 있으며, 최근 고해상도 위성영상이 활용 가능하게 됨에 따라 임상도의 갱신에도 활용될 수 있을 것으로 기대되고 있다. 본 연구에서는 고해상도 위성영상인 IKONOS를 이용하여 수치임상도를 갱신하는 방법을 제시하였다. 연구대상지는 제 4차 임상도의 수치화가 완료된 전라북도 완주 지역으로 1:25000 지형도의 도엽명 대아와 읍내의 일부지역이다. 영상자료는 2001년 8월 18일에 촬영된 IKONOS Multispectral 자료를 이용하였다. 영상의 기하보정을 위하여 RPC Model과 1:25000 수치지형도로부터 만들어진 DEM을 사용하였다. 기하보정된 영상을 이용하여 영상분할(Segmentation)을 실시하여 서로 중복되지 않는 동질한 지역으로 구분하였다. 이때 기존의 수치임상도를 Super-Object로 사용하여 영상을 분할할 때 형성될 수 있는 가장 큰 Segment로 제한하였으며 Super-Object의 경계를 벗어나지 않는 보다 작은 Sub-Object를 만들도록 하여 분할영상의 계층적 구조를 형성하였다. 어느 한 임상내에서 변화가 발생하면 변화가 발생한 지역은 변화가 발생하지 않은 지역과 서로 다른 분광특성을 나타내므로 별도의 Segment를 형성하게 된다. 따라서 임상도의 경계선으로부터 획득된 Super-Object의 분광반사 값과 그 안에서 형성된 Sub-Object의 분광반사값의 차이를 이용하여 임상도의 갱신을 위한 변화지역을 탐지하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1920-1925
• /
• 2004

This paper describes a new method for 3D object recognition which used surface segment-based stereo vision. The position and orientation of an objects is identified accurately enabling a robot to pick up, even though the objects are multiple and partially occluded. The stereo vision is used to get the 3D information as 3D sensing, and CAD model with its post processing is used for building models. Matching is initially performed using the model and object features, and calculate roughly the object's position and orientation. Though the fine adjustment step, the accuracy of the position and orientation are improved.