• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.3_4
• /
• pp.138-148
• /
• 2003

Orthogonal Cross Cylinder mapping and segmentation based modeling methods have been implemented for constructing the image-based navigation system in this paper. The Orthogonal Cross Cylinder (OCC) is the object expressed by the intersection area that occurs when a cylinder is orthogonal with another. OCC mapping method eliminates the singularity effect caused in the environment maps and shows an almost even amount of area for the environment occupied by a single texel. A full-view image from a fixed point-of-view can be obtained with OCC mapping although it becomes difficult to express another image when the point-of-view has been changed. The OCC map is segmented according to the objects that form the environment and the depth value is set by the characteristics of the classified objects for the segmentation based modeling. This method can easily be implemented on an environment map and makes the environment modeling easier through extracting the depth value by the image segmentation. An environment navigation system with a full-view can be developed with these methods.

• Journal of KIISE
• /
• v.44 no.4
• /
• pp.392-398
• /
• 2017

The point-cloud representation of an object is performed by scanning a space through a laser scanner that is extracting a set of points, and the points are then integrated into the same coordinate system through a registration. The set of the completed registration-integrated point clouds is classified into meaningful regions, shapes, and noises through a mathematical analysis. In this paper, the aim is the matching of a curved area like a cylinder shape in 3D point-cloud data. The matching procedure is the attainment of the center and radius data through the extraction of the cylinder-shape candidates from the sphere that is fitted through the RANdom Sample Consensus (RANSAC) in the point cloud, and completion requires the matching of the curved region with the Catmull-Rom spline from the extracted center-point data using the Principal Component Analysis (PCA). Not only is the proposed method expected to derive a fast estimation result via linear and curved cylinder estimations after a center-axis estimation without constraint and segmentation, but it should also increase the work efficiency of reverse engineering.

• KIEAE Journal
• /
• v.16 no.1
• /
• pp.89-94
• /
• 2016

This study is part of three-dimensional(3D) heat transfer analysis program developmental process. The program is being developed without it's own built in 3D-modeller. So 3D-model must be created from another 3D-modeller such as generic CAD programs and imported to the developed program. After that, according to the 3D-geometric data form imported model, 3D-mesh created for numerical calculation. But the 3D-model created from another 3D-modeller is likely to have errors in it's geometric data such as mismatch of position between vertexes or surfaces. these errors make it difficult to create 3D-mesh for calculation. These errors are must be detected and cured in the pre-process before creating 3D-mesh. So, in this study four kinds of filters and functions are developed and tested. Firstly, 'vertex error filter' is developed for detecting and curing for position data errors between vertexes. Secondly, 'normal vector error filter' is developed for errors of surface's normal vector in 3D-model. Thirdly, 'intersection filter' is developed for extracting and creating intersection surface between adjacent objects. fourthly, 'polygon-line filter' is developed for indicating outlines of object in 3D-model. the developed filters and functions were tested on several shapes of 3D-models. and confirmed applicability. these developed filters and functions will be applied to the developed program and tested and modified continuously for less errors and more accuracy.

• The KIPS Transactions:PartD
• /
• v.17D no.3
• /
• pp.193-202
• /
• 2010

Recently, there have been several researches on automatic object identification and distributed computing technology to realize a ubiquitous computing environment. Radio Frequency IDentification (RFID) technology has been applied to many business areas to simplify complex processes and gain important benefits. To derive real benefits from RFID, the system must rapidly implement functions to process a large quantity of event data generated by the RFID operations and should be configured dynamically for changing businesses. Consequently, developers are forced to implement systems to derive meaningful high-level events from simple RFID events and bind them to various business processes. Although applications could directly consume and act on RFID events, extracting the business rules from the business logic leads to better decoupling of the system, which consequentially increases maintainability. In this paper, we describe an RFID business aware framework for business processes in the Electronic Product Code (EPC) Network. This framework is proposed for developing business applications using business services. The term "business services" refers to generated events that can be used in business applications without additional data collection and processing. The framework provides business rules related to data collection, processing, and management, and supports the rapid development and easy maintenance of business applications based on business services.

• Spatial Information Research
• /
• v.3 no.2
• /
• pp.179-189
• /
• 1995

To make vector data from a map which has no negative plates by using vectoring tool, it is necessary that we can extract objects to be vectorized from a scanned map. In this paper, we studied on extracting vectoring objects from scanned color maps. To do this, we classified vectoring objects into three types : line type, filled - area type and character/symbol type. To make the extraction method effective, we analyzed characteristics of vectoring objects and color distribution in scanned color maps. Then, we applied these characteristics to designing process of the extraction method. To extract the line type object, our line tracing method was designed by using the masks which considered connectivity and geometrical characteristics of lines. By using the local thresholding method and the similarity function for comparing the color distribution between two NxN blocks, we extracted character/symbol and the filled-area objects effectively. The method proposed in this paper can be used for constructing the small scale GIS application economically using existing color maps.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.11 no.3
• /
• pp.68-79
• /
• 2008

Ground vehicle borne system which is named RoSSAV(Road Safety Survey and Analysis Vehicle) developed in KICT(Korea Institute of Construction Technology) can collect road geometric data. This system therefore is able to evaluate the road safety and analyze road deficient sections using data collected along the roads. The purpose of this study is to extract road geometric data for 3D road modeling in dangerous road section and The system should be able to quickly provide more accurate data. Various sensors(circular laser scanner, GPS, INS, CCD camera and DMI) are installed in moving object and collect road environment data. Finally, We extract 3d road geometry(center, boundary), road facility and slope using integrated multi-sensor data.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.37 no.2
• /
• pp.50-59
• /
• 2000

Stereo vision is a technique extracting depth information from stereo images, which are two images that view an object or a scene from different locations. The most important procedure in stereo vision, which is called stereo matching, is to find the same points in stereo images. It is difficult to match stereo images in real time because stereo matching requires heavy calculation. In this Paper we design a digital VLSI to Process stereo matching in real time, which we call stereo image match processor (SIMP). For implementation of real time stereo matching, sliding memory and minimum selection tree are presented. SIMP is designed with pipeline architecture and parallel processing. SIMP takes 64 gray level 64$\times$64 stereo images and yields 8 level 64 $\times$64 disparity map by 3 bit disparity and 12 bit address outputs. SIMP can process stereo images with process speed of 240 frames/sec.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.67-75
• /
• 2011

This paper presents a scale and rotation-invariant gait recognition method using R-transform, which is computed by projecting squared coefficients of Radon transform. Since R-transform is invariant to translation, rotation, and scaling, it particularly suitable for extracting object poses without camera calibration. Coefficients of R-transform are used to compute correlation, and the maximum correlation value determines the similarity between two gait images. The proposed method requires neither camera calibration nor geometric compensation, and as a result, it makes robust gait recognition possible without additional compensation for translation, rotation, and scaling.

• Journal of information and communication convergence engineering
• /
• v.8 no.6
• /
• pp.645-650
• /
• 2010

In this paper, we present the effect of binocular cues which plays crucial role for the visualization of a stereoscopic or 3D image. This study is useful in extracting depth and disparity information by image processing technique. A linear relation between the object distance and the image distance is presented to discuss the cause of cybersickness. In the experimental results, three dimensional view of the depth map between the 2D images is shown. A median filter is used to reduce the noises available in the disparity map image. After the median filter, two filter algorithms such as 'Gabor' filter and 'Canny' filter are tested for disparity visualization between two images. The 'Gabor' filter is to estimate the disparity by texture extraction and discrimination methods of the two images, and the 'Canny' filter is used to visualize the disparity by edge detection of the two color images obtained from stereoscopic cameras. The 'Canny' filter is better choice for estimating the disparity rather than the 'Gabor' filter because the 'Canny' filter is much more efficient than 'Gabor' filter in terms of detecting the edges. 'Canny' filter changes the color images directly into color edges without converting them into the grayscale. As a result, more clear edges of the stereo images as compared to the edge detection by 'Gabor' filter can be obtained. Since the main goal of the research is to estimate the horizontal disparity of all possible regions or edges of the images, thus the 'Canny' filter is proposed for decipherable visualization of the disparity.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.9
• /
• pp.1165-1171
• /
• 2018

CNN requires a large amount of computation and memory in the process of extracting the feature of the object. Also, It is trained from the network that the user has configured, and because the structure of the network is fixed, it can not be modified during training and it is also difficult to use it in a mobile device with low computing power. To solve these problems, we apply a pruning method to the pre-trained weight file to reduce computation and memory requirements. This method consists of three steps. First, all the weights of the pre-trained network file are retrieved for each layer. Second, take an absolute value for the weight of each layer and obtain the average. After setting the average to a threshold, remove the weight below the threshold. Finally, the network file applied the pruning method is re-trained. We experimented with LeNet-5 and AlexNet, achieved 31x on LeNet-5 and 12x on AlexNet.