• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.2
• /
• pp.151-159
• /
• 2002

The method of accumulating a sequence of focused images is usually used for reconstruction of 3D object\\`s shape. To acquire a focused image, the conventional methods must calculate the focus measures of all pixels resulting in a long measurement time. This paper proposes a new method of reducing the computation time spent for deciding the focused pixels in the input image, which predicts the area in the image to calculate the focus measure based on a priori information on the object to be measured. The proposed algorithm estimates the area to consider in the next measurement based on the focused area in the present measurement. As the focus measure, Laplacian measure was used in this paper and the experiments have shown that the preposed algorithm may significantly reduce the calculation time. Although, as implied, this algorithm can be applied to only simple objects at this stage, advanced representation schemes will eliminate the restrictions on application domain.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.840-860
• /
• 2023

Aiming at the serious occlusion and slow tracking speed in pedestrian target tracking and recognition in complex scenes, a target tracking method based on improved YOLO v5 combined with Deep SORT is proposed. By merging the attention mechanism ECA-Net with the Neck part of the YOLO v5 network, using the CIoU loss function and the method of CIoU non-maximum value suppression, connecting the Deep SORT model using Shuffle Net V2 as the appearance feature extraction network to achieve lightweight and fast speed tracking and the purpose of improving tracking under occlusion. A large number of experiments show that the improved YOLO v5 increases the average precision by 1.3% compared with other algorithms. The improved tracking model, MOTA reaches 54.3% on the MOT17 pedestrian tracking data, and the tracking accuracy is 3.7% higher than the related algorithms and The model presented in this paper improves the FPS by nearly 5 on the fps indicator.

• Journal of the Korean Society for Precision Engineering
• /
• v.27 no.1
• /
• pp.58-63
• /
• 2010

A new contact force estimation technique is proposed. Keeping the contact force at a certain level between finishing tool and the object is essential since the quality of the finished surface is very sensitive to the contact force during the finishing process. However, the contact force measurement cannot be obtained by simply installing load cells under machine table or in the middle of tool linkage. The reason is that the weight of the machine table and the tool linkage are much heavier than the force to be measured. To that end, a method for estimating disturbance is proposed for a system that is similar to the mechanism of the finishing machine, and the same method is applied to estimate the contact force of the brush-type finishing machine. To verify the effectiveness of the proposed method, a small scale test set-up has been built and the method has been tested.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2000.11a
• /
• pp.862-865
• /
• 2000

The object of this paper is to evaluate the surface roughness using the experimental equation of surface roughness, which is developed in turning by an orthogonal array method. $L_9{3^4}$ orthogonal array method, one of fractional factorial design has been used to study effects of main cutting parameters such as cutting speed, feed rate and depth of cut, on the surface roughness. And the analysis of variance (ANOVA)-test has been used to check the significance of cutting parameters. Using the result of ANOVA-test, the experimental equation of surface roughness, which consists of only significant cutting parameter - feed rate, has been developed. The coefficient of determination of this equation is 0.962.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1994.10a
• /
• pp.778-783
• /
• 1994

In operating automated manufacturing system, the long term stability and reliability of NC machine tools become most critical issues. Especially the machining accuracy is dominated by the thermal deformation of machine tools which remains still unsolved and causes troubles in manufacturing operations. Although researches have been carried out on the thermal behavior of a machine tools to minimize or control the thermal deformation of machine tools, the computer models for an analysis of the thermal behacior in machine tools has yet to appear in the open literature. The object of the paper is to present a method of modeling the thermal behavior of a machine tool. The method will make use of finite elements ad be capable of modeling whole machine structures as well as of heat generation processes in the kinematic system components. And temperature distributions and thermal deformations of a CNC lathe are analyzed using the finite element method and are compared with those measured in practice.

• Journal of the Korean Society for Precision Engineering
• /
• v.11 no.6
• /
• pp.136-142
• /
• 1994

This study presents an algorithm and related techniques which could satisfy the important properties of check weighers and conveyor scales. The algorithm of Recursive Least Squares Regression is described for te weighing system simulated as a dynamic model of the second order. Using the model and the algorithm, model parameters and then the mass being weighed can be determined from the step input. The performance of the algorithm is illustrated in digital simulation. Discussions are extended to the development of fast converging algorithm. It turns out that the algorithm shows several desirable features suitable for microcomputer assisted real-time signal processing, which are high precision and stability in noisy environment.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.5
• /
• pp.137-151
• /
• 2014

This paper proposes a method of detecting object of interest(OOI) in general natural images. OOI is subjectively estimated by human in images. The vision of human, in general, might focus on OOI. As the first step for automatic detection of OOI, candidate regions of OOI are detected by using a saliency map based on the human visual perception. A saliency map locates an approximate OOI, but there is a problem that they are not accurately segmented. In order to address this problem, in the second step, an exact object region is automatically detected by combining graph-based image segmentation and skeletonization. In this paper, we calculate the precision, recall and accuracy to compare the performance of the proposed method to existing methods. In experimental results, the proposed method has achieved better performance than existing methods by reducing the problems such as under detection and over detection.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.3 no.2
• /
• pp.18-31
• /
• 1985

The object of this study is to analize the trilateration adjustment by FEM. FEM is a numerical method for analysis dealing with problems of displacement and variation about the object. Since a plane trilateration net can be likend to a plan structural frame work in stress analysis, the technic of FEM can be used for trilateration adjustment Thus, this study applied FEM and Condition Equation Method to a trilateration adjustment, and investigated precision and characteristics of them.

• Journal of the Korean Society for Precision Engineering
• /
• v.17 no.2
• /
• pp.227-234
• /
• 2000

The human sensibility caused by the motion of an object grasped by a human operator is defined as kinesthetic sense of arm. Due to nonlinearity and ambiguity of human sense, there is no absolute standard for quantification of kinesthetic sense. In this research, a so-called 2-dimensional arm motion generator is developed to present various mechanical impedance (i.e., stiffness or damping) characteristics to a human arm. The kinesthetic words representing arm kinesthetic sense are selected and then the subject's satisfaction levels on these words for given impedance values are measured and processed by the SD method and factor analysis. In addition, the quantification method using neural network is proposed to take into account the individual difference between the mean sensibility and each subject's sensibility. Through this proposed algorithm, the sensibility of human motion described qualitatively can be converted into engineering data ensuring objectivity, reproducibility, and universality.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.397-401
• /
• 1995

ESPI(Electronic Speckle Pattern Interfermetry) is an optical technique to measure surface deforamtion of engineering components and materials in industrial ares. This optical method is capable of providing full-field results with high spatial resolution, high speed and is the non-contact technique. One of important application aspects using electronic speckle pattern interferometry is to generate contours of a diffuse object in order to provide data for 3-D shape analysis and topography measurement. The contouring method by modified dual-beam speckle pattern interferometry is proposed. We introduce a shift of the illumination beams through optical fiber in order to obtain the contour fringe patterns. The speckle pattern correlation technique is suitable for providing measurement range from millimeters to several centimeters. The complete geometric analysis of the contoretical and experimental results are obtained.