• Journal of the Korea Institute of Military Science and Technology
• /
• v.18 no.5
• /
• pp.510-516
• /
• 2015

This paper describes an approach to detect interesting objects using satellite images. This paper focuses on the interesting objects that have common special patterns but do not have identical shapes and sizes. The previous technologies are still insufficient for automatic finding of the interesting objects based on operation of special pattern analysis. In order to overcome the circumstances, this paper proposes a methodology to obtain the special patterns of interesting objects considering their common features and their related characteristics. This paper applies MSER(Maximally Stable Extremal Regions) for the region detection and corner detector in order to extract the features of the interesting object. This paper conducts a case study and obtains the experimental results of the case study, which is efficient in reducing processing time and efforts comparing to the previous manual searching.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.14 no.5
• /
• pp.462-471
• /
• 1989

Two-dimensional median filters were affectively supprssing the noise in image processing with the adge smearing decreased. However, if the window were large as necessary in noise then the filter had tendency to cut off corners. An estimate of gradient was used to decide how the ouputs of the filters were calculated. For parallel to the gradient direction we used edge preserving median operation and orthogonal to that averaging subfilters over which medians were then chosen. Four different algorithms were introduced.

• Transactions of Materials Processing
• /
• v.3 no.2
• /
• pp.178-188
• /
• 1994

A design methodology is applied for manufacturing a disk-brake piston component. The design criteria are the limit drawing ratio and the forging load within the available press limit. Also, the final product should not have any geometrical defect. The rigid-plastic FEM has been applied to simulate the conventional four stage manufacturing processes, which include deep drawing and forging process. Simulation of one stage process from a selected stock to the final product shape is performed for generating information on additional requirements for metal flow. Two stage forming processes with different punch corner and nose geometries are also simulated to identify the possible best solutions. Finally, the best manufacturing process is selected, which is using a hemispherical punch int he deep drawing process.

• Transactions of Materials Processing
• /
• v.7 no.4
• /
• pp.382-392
• /
• 1998

Computer simulations and test trials were carried out to obtain the optimal stamping conditions of the die design of the laser welded automotive body. The stamping process including gravity deflection bead calibration binder wrap, forming and spring back was simulated and compared with the results obtained from test trials. The production variables were determined from a preliminary operation and they were investigated in the simulation and the test trials. The formability was tested under the various conditions, such as the initial position of blank, blank holding force, corner radius and the shape of drawbead. Sound products without fracture, wrinkling and excessive weldline movement were produced by applying results obtained this investigation.

• Transactions of Materials Processing
• /
• v.3 no.2
• /
• pp.202-214
• /
• 1994

An upper bound elemental technique(UBET) is applied to predict the forging load and die-cavity filling for non-axisymmetric ring forging. In order to analyze the process easily, it is suggested that the finial product is divided into three different deformation regions. That is axisymmetric part in corner, lateral plane-strain part and shear deformation on boundaries between them. the place-strain and axisymmetric part are combinded by building block method. Also the total energy is computered through combination of three deformation part. Experiments have been carried out with pure plasticine billets at room temperature. The theoretical predictions of the forging load and the flow pattern are in good agreement with the experimental results.

• Transactions of Materials Processing
• /
• v.13 no.4
• /
• pp.334-341
• /
• 2004

In this study, a remeshing algorithm adapted to the mesh density map using the Delaunay mesh generation method is developed. In the finite element simulation of forging process, the numerical error increases as the process goes on because of discrete property of the finite elements and distortion of elements. Especially, in the region where stresses and strains are concentrated, the numerical error will be highly increased. However, it is not desirable to use a uniformly fine mesh in the whole domain. Therefore, it is necessary to reduce the analysis error by constructing locally refined mesh at the region where the error is concentrated such as at the die corner. In this paper, the point insertion algorithm is used and the mesh size is controlled by using a mesh density map constructed with a posteriori error estimation. An optimized smoothing technique is adopted to have smooth distribution of the mesh and improve the mesh element quality.

• Transactions of Materials Processing
• /
• v.16 no.5 s.95
• /
• pp.381-385
• /
• 2007

In order to examine the effect of the blank holding force on the friction behavior in the sheet metal forming, a sheet metal friction tester is designed and manufactured, which can measure friction forces in various forming conditions such as lubrication, die roughness, drawing speed, radius of die corner, blank holding force, etc., and the friction tests are performed, in which friction coefficients in various blank holding forces and pulling speeds are calculated using Coulomb's friction law. The friction test reveals that friction coefficient decreases as the blank holding force, the drawing speed and lubricant viscosity increase together or individually.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.05a
• /
• pp.69-72
• /
• 2011

In this paper, we propose a method to track the movement of camera from the video sequences. This method is useful for video analysis and can be applied as pre-processing step in some application such as video stabilizer and marker-less augmented reality. First, we extract the features in each frame using corner point detection. The features in current frame are then compared with the features in the adjacent frames to calculate the optical flow which represents the relative movement of the camera. The optical flow is then analyzed to obtain camera movement parameter. The final step is camera movement estimation and correction to increase the accuracy. The method performance is verified by generating a 3D map of camera movement and embedding 3D object to the video. The demonstrated examples in this paper show that this method has a high accuracy and rarely produce any jitter.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.919-920
• /
• 2008

In this paper, we present early processing techniques for visual inspection of metallic parts. Since metallic surfaces give rise to specular reflections, it is difficult to extract object boundaries using elementary segmentation techniques such as edge detection or binary thresholding. In this paper, we present two techniques for finding object boundaries on micro bit images. First, we explain a technique for detecting blade boundaries using a directional correlation mask. Second, a line and angle extraction technique based on Harris corner detector and Hough transform is described. These techniques have been effective for detecting blade boundaries, and a number of experimental results are presented using real images.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.63.2-63
• /
• 2001

It is necessary to distance measurement to detect about obstacles and front vehicles to autonomously navigate. In this paper, we propose an algorithm using stereo vision. It is as follows this algorithm´s procedure. First, It has detected a front vehicle´s common edges from left and right images by image processing. We select number plate of a front vehicle as edges. Then, we estimate distance by triangle measurement method after stereomatching using corner points of the plate´s edges as feature-based points. Experimental results show errors and values compand with experimental ones after set up distance between vehicles in advance.