• Korean Journal of Remote Sensing
• /
• v.11 no.2
• /
• pp.43-57
• /
• 1995

This paper presents reconstruction of disparity in images. To achieve this, the algorithm was made up of two different procedures - one is extraction of boundaries for man-made structures and the other is matching of the structures. In the extraction of boundaries for man-made structures, we assume that man-made structures are composed of lines and the lines make up closed polygon. The convertional algorithms of the edges extraction may not perceive man-made structures and have problems that matching algorithms were too complex. This paper proposed sub-pixel boundaries extraction algorithm that fused split-and-merge and image improvement algorithms to overcome complexity. In matching procedure, feature-based algorithm that minimize the proposed cost function are used and the cost fuction considers movement of mid-points for left and right images to match structures. Because we could not obtain disparity of inner parts for the man-made structures, interpolation method was used. The experiment showed good results.

• The Journal of Korea Robotics Society
• /
• v.14 no.4
• /
• pp.293-300
• /
• 2019

In this paper, an Embedded solution for fast navigation and precise positioning of mobile robots by floor features is introduced. Most of navigation systems tend to require high-performance computing unit and high quality sensor data. They can produce high accuracy navigation systems but have limited application due to their high cost. The introduced navigation system is designed to be a low cost solution for a wide range of applications such as toys, mobile service robots and education. The key design idea of the system is a simple localization approach using line features of the floor and delayed localization strategy using topological map. It differs from typical navigation approaches which usually use Simultaneous Localization and Mapping (SLAM) technique with high latency localization. This navigation system is implemented on single board Raspberry Pi B+ computer which has 1.4 GHz processor and Redone mobile robot which has maximum speed of 1.1 m/s.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.5
• /
• pp.179-186
• /
• 2021

For stereo matching based on deep learning, the design of network structure is crucial to the calculation of matching cost, and the time-consuming problem of convolutional neural network in image processing also needs to be solved urgently. In this paper, a method of stereo matching using sparse loss volume in parallax dimension is proposed. A sparse 3D loss volume is constructed by using a wide step length translation of the right view feature map, which reduces the video memory and computing resources required by the 3D convolution module by several times. In order to improve the accuracy of the algorithm, the nonlinear up-sampling of the matching loss in the parallax dimension is carried out by using the method of multi-category output, and the training model is combined with two kinds of loss functions. Compared with the benchmark algorithm, the proposed algorithm not only improves the accuracy but also shortens the running time by about 30%.

• Journal of the Korean Society of Systems Engineering
• /
• v.20 no.spc1
• /
• pp.108-118
• /
• 2024

As shared electric kick scooters spread to cities worldwide as a result of the proliferation of personal mobility, they have emerged as a significant social issue, impacting pedestrian and user safety, as well as urban aesthetics. In this study, we propose solutions to the unique problems associated with shared electric kick scooters, such as illegal parking, charging, and redistribution. Furthermore, we present research on supplementary services utilizing electric kick scooters in urban areas to enhance citizen safety and user satisfaction through the development of an autonomous electric kick scooter system structure and operational strategies. We suggest a low-cost autonomous electric kick scooter structure and propose AI processing, sensor fusion, and system operation methods to add autonomous capabilities to affordable electric kick scooters. Additionally, we propose operational systems and related technologies for offering various supplementary services.

• Journal of Korean Society of Environmental Engineers
• /
• v.31 no.8
• /
• pp.611-618
• /
• 2009

Road construction has been worked on by focusing on cost effectiveness such as the reduction of construction costs without understanding the natural environment and ecosystems. In addition, since ecosystems have been destroyed and the habitats of animals and plants have been isolated, wild animals have sought other habitats or have moved into isolated habitats. Thus, issues such as roadkills or the extermination of species are increasingly occurring. Based on this background, the development and application of a general assessment method need to be researched in order to verify whether or not spaces or habitats where animals can be inhabited and their species can be maintained exist. The purpose of this study is to develop an ecosystem map where a conservation value evaluation method considering the functions of an ecosystem where animals live as well as the naturalness of ecosystems is used and can be made into a drawing. The items applied to evaluate the habitat conservation values were naturalness, rarity, and functionality, and sub-items for evaluation were created. GIS as well as the evaluation items were used to create a digital map about the level of importance based on the evaluation criteria. The created digital map showed that it was not limited to the adjustment or distribution of the fauna and flora but was applicable for a general ecosystem evaluation method for the conservation of habitats. It is expected that the isolation of habitats would be able to be minimized if the digital map is used for road construction projects. The digital map is deemed to be able to be used for the construction of environmentally friendly roads, which will minimize the destruction of ecosystems and the isolation of habitats for creatures.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.35 no.2
• /
• pp.407-415
• /
• 2015

The railway route and alignment planning have been executed with a limited number of alternatives based on the site pre-survey and the topographic map. This study developed an intelligent railway alignment planning program (ei-Rail) which can derive all the considerable design alternatives and provide the data for the alternative evaluation such as constructions cost, operation cost, and etc. According to the comparisons with prevailing planned railway projects, the time and cost for planning can be reduced as well as the construction costs. This program may contribute to the development of railway industry by reducing the time and cost for planning as well as the total project cost.

• Journal of applied mathematics & informatics
• /
• v.31 no.3_4
• /
• pp.425-441
• /
• 2013

In literature, several strong designated verifier signature (SDVS) schemes have been devised using elliptic curve bilinear pairing and map-topoint (MTP) hash function. The bilinear pairing requires a super-singular elliptic curve group having large number of elements and the relative computation cost of it is approximately two to three times higher than that of elliptic curve point multiplication, which indicates that bilinear pairing is an expensive operation. Moreover, the MTP function, which maps a user identity into an elliptic curve point, is more expensive than an elliptic curve scalar point multiplication. Hence, the SDVS schemes from bilinear pairing and MTP hash function are not efficient in real environments. Thus, a cost-efficient SDVS scheme using elliptic curve cryptography with pairingfree operation is proposed in this paper that instead of MTP hash function uses a general cryptographic hash function. The security analysis shows that our scheme is secure in the random oracle model with the hardness assumption of CDH problem. In addition, the formal security validation of the proposed scheme is done using AVISPA tool (Automated Validation of Internet Security Protocols and Applications) that demonstrated that our scheme is unforgeable against passive and active attacks. Our scheme also satisfies the different properties of an SDVS scheme including strongness, source hiding, non-transferability and unforgeability. The comparison of our scheme with others are given, which shows that it outperforms in terms of security, computation cost and bandwidth requirement.

• Journal of Korea Spatial Information System Society
• /
• v.1 no.1 s.1
• /
• pp.79-88
• /
• 1999

In this paper, essential technological elements for applying GIS and GPS based AVL system to the logistics information area were reviewed. Then system alternatives were evaluated using Life-Cycle Cost Analysis. In the basic scenario, the roadside infrastructure alternative is turned out to be more efficient that the other. The sensitivity analysis shows that under the different conditions and unit costs, the wireless communication alternative can be more economical. Mixed approach based on characteristics of transportation facilities should be considered.

• International Journal of Contents
• /
• v.15 no.4
• /
• pp.8-15
• /
• 2019

This paper presents a solution of the 'Quick, Draw! Doodle Recognition Challenge' hosted by Google. Doodles are drawings comprised of concrete representational meaning or abstract lines creatively expressed by individuals. In this challenge, a doodle is presented as a sequence of sketches. From the view of at the sketch level, to learn the pattern of strokes representing a doodle, we propose a sequential model stacked with multiple convolution layers and Long Short-Term Memory (LSTM) cells following the attention mechanism [15]. From the view at the image level, we use multiple models pre-trained on ImageNet to recognize the doodle. Finally, an ensemble and a post-processing method using the minimum cost flow algorithm are introduced to combine multiple models in achieving better results. In this challenge, our solutions garnered 11th place among 1,316 teams. Our performance was 0.95037 MAP@3, only 0.4% lower than the winner. It demonstrates that our method is very competitive. The source code for this competition is published at: https://github.com/ngxbac/Kaggle-QuickDraw.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.11 no.1
• /
• pp.138-154
• /
• 2008

Geo-special technologies are being adopted in variety fields since the 3rd NGIS plan that was started at 1996. However, the required system or structure to guarantee the up-to-date validity and accuracy of the geospatial data - the most fundamental elements of the technology - was not constructed yet. All the activities related to geospatial data, including topographical map and numerical base map, are all implemented in separate way; from change of geographical objects and features, data gathering, and database construction to distribution, transfer and sharing of these data. The data model that links all the activities are required that enables consistent data-flow and effective and systematic work-flow. In this study, economic data renewal and exchange method was proposed, and benefit-cost analysis was implemented by comparing the conventional work-flow to newly proposed work-flow. The case study was implemented using the model that was adopted in Daegu metropolitan city, and the model was developed by reflecting these results.