• Journal of Internet Computing and Services
• /
• v.21 no.3
• /
• pp.113-121
• /
• 2020

Human Pose Estimation (HPE) which localizes the human body joints becomes a high potential for high-level applications in the field of computer vision. The main challenges of HPE in real-time are occlusion, illumination change and diversity of pose appearance. The single RGB image is fed into HPE framework in order to reduce the computation cost by using depth-independent device such as a common camera, webcam, or phone cam. However, HPE based on the single RGB is not able to solve the above challenges due to inherent characteristics of color or texture. On the other hand, depth information which is fed into HPE framework and detects the human body parts in 3D coordinates can be usefully used to solve the above challenges. However, the depth information-based HPE requires the depth-dependent device which has space constraint and is cost consuming. Especially, the result of depth information-based HPE is less reliable due to the requirement of pose initialization and less stabilization of frame tracking. Therefore, this paper proposes a new method of HPE which is robust in estimating self-occlusion. There are many human parts which can be occluded by other body parts. However, this paper focuses only on head self-occlusion. The new method is a combination of the RGB image-based HPE framework and the depth information-based HPE framework. We evaluated the performance of the proposed method by COCO Object Keypoint Similarity library. By taking an advantage of RGB image-based HPE method and depth information-based HPE method, our HPE method based on RGB-D achieved the mAP of 0.903 and mAR of 0.938. It proved that our method outperforms the RGB-based HPE and the depth-based HPE.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.22 no.6
• /
• pp.1-8
• /
• 2014

Safety performance of a new car is evaluated through USNCAP and their results in the star rating are provided to the consumers. It is very important to obtain high score of USNCAP to appeal their performance to consumers. Therefore the car companies have made the effort to improve their car safety performance. These efforts should satisfy the demand not only to get high score but also to pass the FMVSS, NHTSA regulations on safety. Huge numbers of car crash tests have been conducted on these bases by car companies. However physical tests spend too much cost and time, as an alternative way, the simulation on the car crash could be a solution to reduce the cost and time. Therefore the simulations have been widely conducted in car industry and various researches on this have been reported. In this study, restraint system had been optimized to minimize the injury of female passenger. Belted $5^{th}%ile$ female frontal crash test was selected from various test methods of USNCAP for the study. Initial velocity of the test was 56km/h. The combination injury probability of USNCAP was selected as an objective function and the injury limit value, which was defined in FMVSS, was set to an optimization constraint. Many researches that were similar to this study had been conducted, however most of them had limitation that interaction between airbag and safety belt had not been considered. Contrary to these researches, the interaction was considered in this study.

• International Journal of Industrial Entomology and Biomaterials
• /
• v.33 no.1
• /
• pp.15-23
• /
• 2016

One major constraint in the development and implementation of a successful and cost-effective area-wide integrated pest management (AW-IPM) programme with a SIT component for Bactrocera oleae (Diptera: Tephritidae) is the ability to produce a large number of high quality mass-reared individuals. The aim of this study was to develop a more efficient and practical egg collection system in an attempt to improve the mass-rearing of this species. The following basic parameters were examined: egg production per female, egg hatch, pupal recovery, pupal weight, adult emergence and percentage of fliers. Three different strains (Israel wild-type, France wild-type, and Greece laboratory) were tested and each strain was evaluated for six generations. Female flies of the Israel strain produced significantly more eggs per female than the other two strains, but egg hatch was significantly lower. Egg hatch of the France wild type and the Greece laboratory strain was similar. For all other parameters, there was no significant difference between strains; however, there was a significant generational effect for all parameters observed. As a result of this study, a protocol was developed for the mass-rearing of this species that included the use of large adult holding cages that could house up to 96,000 flies per cage. The newly developed method of egg collection using a flat wax panel as one of the sides of an adult holding cage proved to be cost-effective, efficient, making colony growth easier for industrial mass-rearing.

• Korean Journal of Construction Engineering and Management
• /
• v.11 no.2
• /
• pp.74-82
• /
• 2010

A government agency has been announced to increase 23,663 hundred million wons by cost of design change which occurred in the pre-construction and construction phase. As design change is a phenomenon to occur by means of a characteristic of the building design that standardization is difficult, even if it is said that a perfect design is done in design phase, design change is prevented, and it is going to decrease, and there is a limit. Because there are some causes in all of the construction project, it is change order of client, relative system, unfit design and field condition, etc. In this study, we are suggested logic and basic model of the decision making support process model that it should selecting the optimal alternative through complex and quantitative analyzed: that is cost, performance and constructability as respect Owner or CMr is executing project under the CM delivery system construction project which it occurred design change.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.2B
• /
• pp.183-191
• /
• 2004

Single shortest path routing is known to perform poorly for Internet traffic engineering (TE) where the typical optimization objective is to minimize the maximum link load. Splitting traffic uniformly over equal cost multiple shortest paths in OSPF and IS-IS does not always minimize the maximum link load when multiple paths are not carefully selected for the global traffic demand matrix. However, among all the equal cost multiple shortest paths in the network, a set of TE-aware shortest paths, which reduces the maximum link load significantly, can be found and used by IP routers without any change of existing routing protocols and serious configuration overhead. While calculating TE-aware shortest paths. the destination-based forwarding constraint at a node should be satisfied, because an IP router will forward a packet to the next-hop toward the destination by looking up the destination prefix. In this paper, we present a problem formulation of finding a set of TE-aware shortest paths in ILP, and propose a simple heuristic for the problem. From the simulation results, it is shown that TE-aware shortest path routing performs better than default shortest path routing and ECMP in terms of the maximum link load with the marginal configuration overhead of changing the next-hops.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.11B
• /
• pp.758-771
• /
• 2005

Information systems in current corporations are managing and storing large data officially happened on individual and various databases. Corporations for migrating the stored data from these individual databases are adopting with technologies of EAI, MDR, DW etc.. However these technologies are not only required to expenses introduction charge and maintenance cost but also have problems of heterogeneous environment required per each vender In this paper, to solve problems of these current existing technologies, we propose to design our data migration system to migrate source data and semantic constraint condition between heterogeneous relation databases based on web service. As corporations use web services, they can reduce introduction expense and maintenance cost because of using current existent web environment. Each system can independently migrate XML based data against any platform, system environment, and Implementation language.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.10
• /
• pp.123-131
• /
• 1999

In this paper, we proposed stereo matching algorithm by dynamic programming with edges emphasized. Existing algorithms show blur generally at depth discontinuities owing to smoothness constraint and non-existence of matching pixel in occlusion regions. Also it accompanies matching error by lackness of matching information in the untextured regions. This paper defines new cost function to make up for the problems occurred to existing algorithms. It is possible through deriving matching of edges in left and right images to be carried out between edge regions anf deriving that in the other regions to be peformed between the other regions. In case of the possibility that edges can be Produced in a large amount, matching between edge information adds weight to cost function in proportion to Path distance. Proposed algorithm was applied to various images obtained by convergent camera model as well as parallel camera model. As the result, proposed algorithm showed improved performance in the aspect of matching error and processing in the occlusion regions compared to existing algorithms. Also it could improve blur especially in discontinuity regions.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.40 no.4
• /
• pp.253-259
• /
• 2017

Recent development in science and technology has modernized the weapon system of ROKN (Republic Of Korea Navy). Although the cost of purchasing, operating and maintaining the cutting-edge weapon systems has been increased significantly, the national defense expenditure is under a tight budget constraint. In order to maintain the availability of ships with low cost, we need accurate demand forecasts for spare parts. We attempted to find consumption pattern using data mining techniques. First we gathered a large amount of component consumption data through the DELIIS (Defense Logistics Intergrated Information System). Through data collection, we obtained 42 variables such as annual consumption quantity, ASL selection quantity, order-relase ratio. The objective variable is the quantity of spare parts purchased in f-year and MSE (Mean squared error) is used as the predictive power measure. To construct an optimal demand forecasting model, regression tree model, randomforest model, neural network model, and linear regression model were used as data mining techniques. The open software R was used for model construction. The results show that randomforest model is the best value of MSE. The important variables utilized in all models are consumption quantity, ASL selection quantity and order-release rate. The data related to the demand forecast of spare parts in the DELIIS was collected and the demand for the spare parts was estimated by using the data mining technique. Our approach shows improved performance in demand forecasting with higher accuracy then previous work. Also data mining can be used to identify variables that are related to demand forecasting.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.2
• /
• pp.315-324
• /
• 2017

The smart grid with distributed power supply introduces a number of problems including not only the problems of the existing power grid but also the problem of protection co-operation due to new electric phenomenon because it has a mixed operation structure combining the existing radial operation structure and the new loop operation structure. The EMTP based power system analysis method has flexibility and convenience from the view of system configuration but it requires another experimental verification because of uncertainty of design and analysis results. On the other hand, the real demonstration system has difficulties in observing accurate fault on large scale system due to considerable economical and spatial construction cost, system configuration constraint, and it is difficult to demonstrate the distributed, autonomous and adaptive control strategy of smart grid. In this paper, a basic theory for a micro smart grid simulator design using MEMS(Micro Electro-Mechanical Systems) miniaturization technology is studied which can safely and freely experiment and observe electrical phenomena, and distribution, autonomous adaptive control strategy for disturbances on 22.9kV smart grid under minimum economic and spatial cost.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2008.04a
• /
• pp.1001-1004
• /
• 2008

This study reviewed the results of utilization of insulation heat curing method using double layer bubble sheet in slab concrete and mass concrete in cold weather environment. First of all, when double layer bubble sheets are applied, it was shown that slab concrete was protected from early freezing by remaining between 6 and $10^{\circ}C$ even in case outside temperature drops $10^{\circ}C$ below zero until the 2nd day from piling, and in the case of mass concrete, with the maximum temperature difference between the center and surface less than $6^{\circ}C$, crack occurrence index was close to 2 and no hydration heat crack occurred by internal constraint. The insulation heat preservation curing method using the double bubble sheet applied in this field prevented early freezing owing to stable curing temperature management, deterring concrete strength development delay at low temperature, and obtained the needed strength. Also, it was proven that the method is highly effective and economic for cold weather concrete quality maintenance through curing cost reduction like construction period shortening and labor cost reduction, etc by reducing the process of temporary equipment installation and disassembling.