• Journal of the Korea Computer Graphics Society
• /
• v.28 no.3
• /
• pp.125-134
• /
• 2022

This paper implements an AR manual for a vehicle that can be used even in the vehicle interior space where it is difficult to apply the augmentation method of AR content, which is mainly used, and applies a deep learning model to improve the augmentation matching between real space and virtual objects. Through deep learning, the logo of the steering wheel is recognized regardless of the position, angle, and inclination, and 3D interior space coordinates are generated based on this, and the virtual button is precisely augmented on the actual vehicle parts. Based on the same learning model, the function to recognize the main warning light symbols of the vehicle is also implemented to increase the functionality and usability as an AR manual for vehicles.

• Journal of the Society of Disaster Information
• /
• v.16 no.1
• /
• pp.96-110
• /
• 2020

Recently, due to global warming, it is easily exposed to various disasters such as fire, flood, and earthquake. In particular, large-scale disasters have continuously been occurring in crowded areas such as traditional markets, facilities for the elderly and children, and public facilities where various people stay. Purpose: This study aims to detect a fire occurred in crowded facilities early in the event to analyze and provide an optimal evacuation route using big data and advanced technology. Method: The researchers propose a new algorithm through context-aware 3D object model technology and A* algorithm optimization and propose a scenario-based optimal evacuation route selection technique. Result: Using the HPA* E algorithm, the evacuation simulation in the event of a fire was reproduced as a 3D model and the optimal evacuation route and evacuation time were calculated for each scenario. Conclusion: It is expected to reduce fatalities and injuries through the evacuation induction technique that enables evacuation of the building in the shortest path by analyzing in real-time via fire detection sensors that detects the temperature, flame, and smoke.

• Korean Journal of Applied Biomechanics
• /
• v.25 no.2
• /
• pp.157-165
• /
• 2015

Object : The goals of this research were to make Performance Enhanced Model(PE) taken the largest performance index (PI) through artificial variation of principle components calculated by principle component analysis for trial data, and to verify the effect through comparing kinematic factors between trial data (Raw) and PE. Method : Ten subjects (5 men, 5 women) were recruited and 80% of their maximal record was considered. The PI is a regression equation. In order to develop PE, we extracted Principle components from trial position data (by Principle Components Analysis (PCA)). Before PCA, we made 17 position data to 3 row matrix according to components. We calculated 3 eigen value (principle components) through PCA. And except Y (medial-lateral direction) component (because motion of Y component is small), principle components of X (anterior-posterior direction) and Z (vertical direction) components were changed as following. Changed principle components = principle components + principle components ${\times}$ k. After changing the each principle component, we reconstructed position data using the changed principle components and calculated performance index (PI). A Paired t-test was used to compare Raw data and Performance Enhanced Model data. The level of statistical significance was set at $p{\leq}0.05$. Result : The PI was significantly increased about 12.9kg at PE ($101.92{\pm}6.25$) when compared to the Raw data ($91.29{\pm}7.10$). It means that performance can be increased by optimizing 3D positions. The difference of kinematic factors as follows : the movement distance of the bar from start to lock out was significantly larger (about 1cm) for PE, the width of anterior-posterior bar position in full phase was significantly wider (about 1.3cm) for PE and the horizontal displacement toward the weightlifter after beginning of descent from maximal height was significantly greater (about 0.4cm) for PE. Additionally, the minimum knee angle in the 2-pull phase was significantly smaller (approximately 2.7cm) for the PE compared to that of the Raw. PE was decided at proximal position from the Raw (origin point (0,0)) of PC variation). Conclusion : PI was decided at proximal position from the Raw (origin point (0,0)) of PC variation). This means that Performance Enhanced Model was decided by similar motion to the Raw without a great change. Therefore, weightlifters could be accept Performance Enhanced Model easily, comfortably and without large stress. The Performance Enhance Model can provide training direction for athletes to improve their weightlifting records.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.6D
• /
• pp.1025-1032
• /
• 2006

Sensor modeling of high-resolution satellites is a prerequisite procedure for mapping and GIS applications. Sensor models, describing the geometric relationship between scene and object, are divided into two main categories, which are rigorous and approximate sensor models. A rigorous model is based on the actual geometry of the image formation process, involving internal and external characteristics of the implemented sensor. However, approximate models require neither a comprehensive understanding of imaging geometry nor the internal and external characteristics of the imaging sensor, which has gathered a great interest within photogrammetric communities. This paper described a comparison between rigorous and various approximate sensor models that have been used to determine three-dimensional positions, and proposed the appropriate sensor model in terms of the satellite imagery usage. Through the case study of using IKONOS satellite scenes, rigorous and approximate sensor models have been compared and evaluated for the positional accuracy in terms of acquirable number of ground controls. Bias compensated RFM(Rational Function Model) turned out to be the best among compared approximate sensor models, both modified parallel projection and parallel-perspective model were able to be modelled with a small number of controls. Also affine transformation, one of the approximate sensor models, can be used to determine the planimetric position of high-resolution satellites and perform image registration between scenes.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.344-346
• /
• 2004

IKONOS 1m satellite imagery is particularly well suited for 3-D feature extraction and 1 :5,000 scale topographic mapping. Because the image line and sample calculated by given RPCs have the error of more than 11m, in order to be able to perform feature extraction and topographic mapping, rational polynomial coefficients(RPCs) camera model that are derived from the very complex IKONOS sensor model to describe the object-image geometry must be refined by several Ground Control Points(GCPs). This paper presents a quantitative evaluation of the geometric accuracy that can be achieved with IKONOS imagery by refining the offset and scaling factors of RPCs using several GCPs. If only two GCPs are available, the offsets and scale factors of image line and sample are updated. If we have more than three GCPs, four parameters of the offsets and scale factors of image line and sample are refined first, and then six parameters of the offsets and scale factors of latitude, longitude and height are updated. The stereo images acquired by IKONOS satellite are tested using six ground points. First, the RPCs model was refined using 2 GCPs and 4 check points acquired by GPS. The results from IKONOS stereo images are reported and these show that the RMSE of check point acquired from left images and right are 1.021m and 1.447m. And then we update the RPCs model using 4 GCPs and 2 check points. The RMSE of geometric accuracy is 0.621 m in left image and 0.816m in right image.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.9 no.4
• /
• pp.125-133
• /
• 1989

For convergent photos, which are now widely adopted for terrestrial facility survey, a number of experimental studies and theoretical studies on the developments of accuracy predictional model according to the convergent angle change have been accomplished. And such studies are basically depend on the symmetrical geometric configuration at the normal direction to the center of the object. However, in may cases of facility survey such as building facades, bridges, dam surfaces, relatively flat topography, etc., the object features are almost like planar, and frequently the surroundings do not allow the photo station at normal direction, and the sufficient convergent angle can be hardly achieved. Considering those points, in this study, the accuracy analysis on three dimensional coordinates according to the variations of photo direction and of convergent angle to the planar object were attempted, and the optimum geometric configurations at the normal, side-looking, and the most side-looking direction were investigated. The result through this study show that from normal direction to the side-looking direction angle ${\tau}=30^{\circ}$, the larger the convergent angle, the higher the accuracy, and in case that right photo is at the most side-looking direction, the better accuracy can be achieved according to the convergent angle increase up to $60^{\circ}$.

• Journal of Korean Society of Transportation
• /
• v.21 no.1
• /
• pp.127-136
• /
• 2003

Road safety is defined under the minimum design standard and design examination process is consisted of the standard according to current road design. However, road safety in practical way is correlative to not only all element of roads but also road shape, such as, between straight line and curved line and between curved lines. Also. it is related to alignments such as horizontal alignment and vertical alignment, and cross section. That is, the practical road design should be examined in both sides of 3 dimension and consecutiveness (consistency) as the actual road is a 3 - dimensional successive object. The paper presents a concept for acceleration to evaluate consistency of road considering actual road shape on 3-dimension. Acceleration of vehicle is influential to road consistency based on running state of vehicles and state of drivers. The magnitude of acceleration. especially, is a quite influential element to drivers. Based on above, the acceleration on each point on 3-D road can be calculated and then displacement can be done. Computation of acceleration means total calculation on each axis. Speed profile refers to “Development of a safety evaluation model for highway horizontal alignment based on running speed(Jeong, Jun-Hwa, 2001)” and then acceleration can be calculated by using the speed pronto. According to literature review, definition of acceleration on 3-D and g-g-g diagram are established. For example, as a result of the evaluation, if the acceleration is out of range, the road is out of consistency. The paper shows calculation for change of acceleration on imaginary road under minimum design standard and the change tried to be applied to consistency. However accurate acceleration is not shown because the speed forecasting model is limited and the paper did not consider state of vehicles (suspension, tires and model of vehicles). If speed pronto is defined exactly, acceleration is calculated on all road shapes, such as. compound curve and clothoid curve. and then it is appled to consistency evaluation. Unfortunately, speed forecasting model on 3 -D road and on compound curves have rarely presented. Speed forecasting model and speed profile model need to be established and standard of consistency evaluation need to developed and verified by experimental vehicles.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_1
• /
• pp.973-985
• /
• 2019

In this paper, we propose a method to separate the ground and building areas and generate building models automatically through planarity analysis using UAV (Unmanned Aerial Vehicle) based point cloud. In this study, proposed method includes five steps. In the first step, the planes of the point cloud were extracted by analyzing the planarity of the input point cloud. In the second step, the extracted planes were analyzed to find a plane corresponding to the ground surface. Then, the points corresponding to the plane were removed from the point cloud. In the third step, we generate ortho-projected image from the point cloud ground surface removed. In the fourth step, the outline of each object was extracted from the ortho-projected image. Then, the non-building area was removed using the area, area / length ratio. Finally, the building's outer points were constructed using the building's ground height and the building's height. Then, 3D building models were created. In order to verify the proposed method, we used point clouds made using the UAV images. Through experiments, we confirmed that the 3D models of the building were generated automatically.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.7
• /
• pp.1923-1932
• /
• 1998

This paper deals with a 2-D objects recognition algorithm. And in this paper, we present an algorithm which can reduce the computation time in model retrieval by means of hashing technique instead of using the binary~tree method. In this paper, we treat an object boundary as a string of structural units and use an attributed string matching algorithm to compute similarity measure between two strings. We select from the privileged strings a privileged string wIth mmimal eccentricity. This privileged string is treated as the reference string. And thell we wllstructed hash table using the distance between privileged string and the reference string as a key value. Once the database of all model strings is built, the recognition proceeds by segmenting the scene into a polygonal approximation. The distance between privileged string extracted from the scene and the reference string is used for model hypothesis rerieval from the table. As a result of the computer simulation, the proposed method can recognize objects only computing, the distance 2-3tiems, while previous method should compute the distance 8-10 times for model retrieval.

• Korean Journal of Construction Engineering and Management
• /
• v.16 no.4
• /
• pp.118-128
• /
• 2015

Recently BIM technology has been expanded for using in construction project. Due to the high-cost of BIM infrastructure development, lack of regulations, lack of process and so forth, usage of BIM has been delayed than initial expectations. In design phase, especially, collaboration based on BIM system has been a key factor for successful next generation building project. Through the analysis of current research trends about IT technologies, virtualization and BIM service, data exchange such as drawings, 3D model, object data, properties using cloud computing and virtual server system is defined as a most successful solution. The purpose of this study is to enable the cloud computing BIM server to provide several main functions such as editing models, 3D model viewing and checking, mark-up and snapshot in high-performance quality by proper design of VDI system. Concurrent client connection performance is a main technical index of VDI. Through testing of test-bed server client, developed VDI system's multi-connect control is evaluated. Performance-test result of BIM server VDI effect to development direction of cloud computing BIM service for commercialization.