• Journal of the Korean Society for Precision Engineering
• /
• v.10 no.4
• /
• pp.170-179
• /
• 1993

In this study, self-organized neural network is used to solve the vorrespondence problem of the axial stereo image. Edge points are extracted from a pair of stereo images and then the edge points of rear image are assined to the output nodes of neural network. In the matching process, the two input nodes of neural networks are supplied with the coordi- nates of the edge point selected randomly from the front image. This input data activate optimal output node and its neighbor nodes whose coordinates are thought to be correspondence point for the present input data, and then their weights are allowed to updated. After several iterations of updating, the weights whose coordinates represent rear edge point are converged to the coordinates of the correspondence points in the front image. Because of the feature map properties of self-organized neural network, noise-free and smoothed depth data can be achieved.

• Geophysics and Geophysical Exploration
• /
• v.7 no.1
• /
• pp.93-98
• /
• 2004

The sand-covered Muweilah archaeological site in the United Arab Emirates (UAE) is a unique Iron Age site, and has been subject to intensive investigations. However, excavations are time consuming and may require twenty years to complete. Thus geophysical surveys were undertaken with the objective of characterising the site more expeditiously. This paper presents preliminary results of these surveys. Ground penetrating radar (GPR) was tested as a primary imaging tool, with an ancillary shallow time domain EM (MetalMapper) system. Dense 3D GPR datasets were migrated to produce horizontal (plan view) depth slices at 10 cm intervals, which is conceptually similar to the archaeologists' excavation methodology. The objective was to map all features associated with anthropogenic activity. This required delineating extensive linear and planar features, which could represent infrastructure. The correlation between these and isolated point reflectors, which could indicate anthropogenic activity, was then assessed. Finally, MetalMapper images were used to discriminate between metallic and non-metallic scatterers. The moderately resistive sand cover allowed GPR depth penetration of up to 5 m with a 500 MHz system. GPR successfully mapped floor levels, walls, and isolated anthropogenic activity, but crumbling walls were difficult to track in some cases. From this study, two possible courtyard areas were recognised. The MetalMapper was less successful because of its limited depth penetration of 50 cm. Despite this, the system was still useful in detecting modem-day ferruginous waste and bronze artefacts. The results (subject to ongoing ground-truthing) indicated that GPR was optimal for sites like Muweilah, which are buried under a few metres of sand. The 3D survey methodology proved essential to achieve line-to-line correlation for tracking walls. In performing the surveys, a significant improvement in data quality ensued when survey areas were flattened and de-vegetated. Although MetalMapper surveys were not as useful, they certainly indicated the value of including other geophysical data to constrain interpretation of complex GPR features.

• Journal of KIISE:Databases
• /
• v.28 no.3
• /
• pp.430-448
• /
• 2001

In navigation system, a primary task is to compute the minimum cost route from the current location to the destination. One of major problems for navigation systems is that a significant amount of computation time is required when the digital road map is large. Since navigation systems are real time systems, it is critical that the path be computed while satisfying a time constraint. In this paper, we have developed a HiTi(Hierarchical MulTi) graph model for hierarchically structuring large digital road maps to speedup the minimum cost path computation. We propose a new shortest path algorithm named SPAH, which utilizes HiTi graph model of a digital road map for its computation. We prove that the shortest path computed by SPAH is the optimal. Our performance analysis of SPAH also showed that it significantly reduces the computation time over exiting methods. We present an in-depth experimental analysis of HiTi graph method by comparing it with other similar works.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.4
• /
• pp.570-579
• /
• 2021

The environments in current farming and fishing communities have been exacerbated by the shortage of personnel caused by aging, the deficiency of equipment, and the decrease in produce prices. To help solve these issues, this study examined the history, such as inspections, failures, and repairs, by constructing a database for underground water wells, pumping stations, and irrigation, which are critical for management among agriculture production infrastructures. In particular, in the case of underground water wells, their optimal locations were determined using spatial information, such as a geological map of water resources, a water vein map, and underwater depth, because indiscreet installations and an absence of spatial information resulted in economic losses and environmental pollution. Therefore, this study could efficiently manage many facilities scattered in rural areas by developing a system. An analysis of the status of 14 underground water wells using spatial information showed that the location information at six points was specified incorrectly. On the other hand, a site investigation showed that the water vein map analysis at one point was inaccurate.

• Journal of Drive and Control
• /
• v.20 no.4
• /
• pp.1-8
• /
• 2023

In recent years, robots have been utilized in various industries to reduce workload and enhance work efficiency. The following mobility offers users convenience by autonomously tracking specific locations and targets without the need for additional equipment such as forklifts or carts. In this paper, deep learning techniques were employed to recognize individuals and assign each of them a unique identifier to enable the recognition of a specific person even among multiple individuals. To achieve this, the distance and angle between the robot and the targeted individual are transmitted to respective controllers. Furthermore, this study explored the control methodology for mobility that tracks a specific person, utilizing Simultaneous Localization and Mapping (SLAM) and Proportional-Integral-Derivative (PID) control techniques. In the PID control method, a genetic algorithm is employed to extract the optimal gain value, subsequently evaluating PID performance through simulation. The SLAM method involves generating a map by synchronizing data from a 2D LiDAR and a depth camera using Real-Time Appearance-Based Mapping (RTAB-MAP). Experiments are conducted to compare and analyze the performance of the two control methods, visualizing the paths of both the human and the following mobility.

• IEIE Transactions on Smart Processing and Computing
• /
• v.1 no.3
• /
• pp.161-170
• /
• 2012

This paper presents an efficient and robust approach for determining the correspondence between unbalanced stereo images. The disparity vectors were used instead of feature points, such as corners, to calculate a correspondence relationship. For a faster and optimal estimation, the vectors were classified into several regions, and the homography of each region was calculated using the RANSAC algorithm. The correspondence image was calculated from the images transformed by each homography. Although it provided good results under normal conditions, it was difficult to obtain reliable results in an unbalanced stereo pair. Therefore, a balancing method is also proposed to minimize the unbalance effects using the histogram specification and structural similarity index. The experimental results showed that the proposed approach outperformed the baseline algorithms with respect to the speed and peak-signal-to-noise ratio. This work can be applied to practical fields including 3D depth map acquisition, fast stereo coding, 2D-to-3D conversion, etc.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.49 no.3
• /
• pp.63-68
• /
• 2007

The LRA(Logistic Regression Analysis) conducts a quantitative analysis by collecting a lot of samples and the AHP(Analytic Hierarchy Program) makes use of expert decision influenced by subjective judgment to a certain degree. This study is to suggest a combination method in mapping landslide hazard by giving equal weight for the result of LRA and AHP. Topographic factors(slope, aspect, elevation), soil dram, soil depth and land use were adopted to classify landslide hazard areas. The three methods(LRA, AHP, the combined approach) was applied to a $520km^2$ region located in the middle of South Korea which have occurred 39 landslides during 1999 and 2003. The suggested method showed 58.9% matching rate for the real landslide sites comparing with the classified areas of high-risk landslide While LRA and AHP Showed 46.1% and 48.7% matching rates respectively. Further studies are recommended to find the optimal combining weight of LRA and AHP with more landslide data.

• Korean Institute of Interior Design Journal
• /
• v.26 no.6
• /
• pp.172-179
• /
• 2017

The regional trauma center should be a trauma treatment center equipped with facilities, equipments, and manpower capable of providing optimal treatment from emergency surgery to a severely traumatized patient upon arrival at the hospital. In order to establish a medical system for effective severe diseases, it is necessary to prepare architectural planning guidelines for the regional trauma centers. This study analyzes the connectivity, control, integration, and mean depth of current trauma centers using the convex map of space syntax, And to provide basic data for building for more efficient regional trauma center. The major areas that must be included in the regional trauma center are trauma resuscitation room, trauma operating room, trauma intensive care unit, and trauma general ward. It is necessary to carry out the architectural planning to increase the interconnection of the four areas. Also, the elevator plan for trauma patients should be emphasized. In addition, a regional trauma center should be separated from the existing facility for independent operation. According to the case analysis of the space configuration of the regional trauma center, the location of the operating room is most important considering the connection with each department of the hospital and the treatment flow of the severe trauma patients.

• Journal of Navigation and Port Research
• /
• v.32 no.5
• /
• pp.355-361
• /
• 2008

Stereo matching is one of the most active research areas in computer vision. In this paper, we propose a stereo matching scheme using genetic algorithm for object depth recognition. The proposed approach considers the matching environment as an optimization problem and finds the optimal solution by using an evolutionary strategy. Accordingly, genetic operators are adapted for the circumstances of stereo matching. An individual is a disparity set. Horizontal pixel line of image is considered as a chromosome. A cost function is composed of certain constraints which are commonly used in stereo matching. Since the cost function consists of intensity, similarity and disparity smoothness, the matching process is considered at the same time in each generation. The LoG(Laplacian of Gaussian) edge is extracted and used in the determination of the chromosome. We validate our approach with experimental results on stereo images.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.1
• /
• pp.23-28
• /
• 2017

Shape from focus (SFF) is a technique used to reconstruct 3D shape of objects from a sequence of images obtained at different focus settings of the lens. In this paper, a new shape from focus method for 3D reconstruction of microscopic objects is described, which is based on gradient operator in Mathematical Morphology. Conventionally, in SFF methods, a single focus measure is used for measuring the focus quality. Due to the complex shape and texture of microscopic objects, single measure based operators are not sufficient, so we propose morphological operators with multi-structuring elements for computing the focus values. Finally, an optimal focus measure is obtained by combining the response of all focus measures. The experimental results showed that the proposed algorithm has provided more accurate depth maps than the existing methods in terms of three-dimensional shape recovery.