• Journal of Korea Society of Industrial Information Systems
• /
• v.19 no.1
• /
• pp.77-85
• /
• 2014

Medicine-bottle classification algorithm to avoid medicine accidents must be robust to a geometric change such as rotation, size variation, location movement of the medicine bottles. In this paper, we propose an algorithm to classify the medicine bottles exactly in real-time by using SIFT(Scale Invariant Feature Transform) which is robust to the geometric change. In first, we classify medicine bottles by size using minimum boundary rectangle(MBR) of medicine bottles as a striking feature in order to classify the medicine bottles. We extract label region in the MBR and the region of interest(ROI) considering rotation. Then, we classify medicine bottles using SIFT for the extracted ROI. We also simplify the number of octave of SIFT in order to improve a process speed of SIFT. We confirm to classify all the medicine bottles exactly as a result of performance evaluation of the proposed algorithm about images of 250 medicine bottles. We also confirm to improve the process time more than twice the processing time by simplifying the number of octave of SIFT.

• Journal of Broadcast Engineering
• /
• v.21 no.2
• /
• pp.252-260
• /
• 2016

The performance of human detection system is affected by camera location and view angle. In 2D image acquired from such camera settings, humans are displayed in different sizes. Detecting all the humans with diverse sizes poses a difficulty in realizing a real-time system. However, if the size of a human in an image can be predicted, the processing time of human detection would be greatly reduced. In this paper, we propose a method that estimates human size by constructing an indoor scene in 3D space. Since the human has constant size everywhere in 3D space, it is possible to estimate accurate human size in 2D image by projecting 3D human into the image space. Experimental results validate that a human size can be predicted from the proposed method and that machine-learning based detection methods can yield the reduction of the processing time.

• Korean Journal of Construction Engineering and Management
• /
• v.2 no.1 s.5
• /
• pp.88-97
• /
• 2001

The Internet, the main issue of a new millennium, is being researched vitally for the progress of the construction industry, and the construction industry is considered to be led into a high-value added state-of-arts technology industry through CALS. Even if many construction companies gradually widen the use of the Internet for various purposes such as an electronic bidding system and an e-commerce system, the companies are still demanded to use the Internet more broadly and practically. Hence, the need for a tool for fast decision making and an effective construction management has risen. The PRIMA system has been developed specifically focused on meeting with those recent changes of the construction industry. This system is composed of three parts. Those are Just In Time(JIT) management, integrated application of man power${\cdot}$safety${\cdot}$work management and decision making process based on real-time information in the Internet. The usefulness of the PRIMA system has already been proved in a super-scale construction project. As the Internet environment get improved the use of the tool will be spread out gradually for many construction projects, regardless their size and location.

• Journal of Information Processing Systems
• /
• v.15 no.6
• /
• pp.1277-1295
• /
• 2019

With its technical development, digital printing is being universally introduced to the mass production of clothing factories. At the same time, many fashion platforms have been made for customers' participation using digital printing, and a tool is provided in platforms for customers to make designs. However, there is no sufficient solution in the production stage for automatically converting a customer's design into a file before printing other than designating a square area for the pattern designed by the customer. That is, if 30 different designs come in from customers for one shirt, designers have to do the work of reproducing the design on the clothing pattern in the same location and in the same angle, and this work requires a great deal of manpower. Therefore, it is necessary to develop a technology which can let the customer make the design and, at the same time, reflect it in the clothing pattern. This is defined in relation to the existing clothing pattern with digital printing. This study yields a clothing pattern for digital printing which reflects a customer's design in real time by matching the diagram area where a customer designs on a given clothing model and the area where a standard pattern reflects the customer's actual design information. Designers can substitute the complex mapping operation of programmers with a simple area-matching operation. As there is no limit to clothing designs, the variousfashion design creations of designers and the diverse customizing demands of customers can be satisfied at low cost with high efficiency. This is not restricted to T-shirts or eco-bags but can be applied to all woven wear, including men's, women's, and children's clothing, except knitwear.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.8
• /
• pp.1885-1894
• /
• 2014

There are various high-performance algorithms in the area of the existing VDSs (vehicle detection systems). However, they requires a large amount of computational time-complexity and their systems generally are very expensive and consumes high-power. This paper proposes real-time traffic information detection algorithm that can be applied to low-cost, low-power, and open development platform such as Android. This algorithm uses a vehicle's sub-shadow to set ROI(region of interest) and to count vehicles using a location of the sub-shadow and the vehicle. The proposed algorithm is able to count the vehicles per each roads and each directions separately. The experiment result show that the detection rate for going-up vehicles is 94.1% and that for going-down vehicles is 97.1%. These results are close to or surpasses 95%, the detection rate of commercial loop detectors.

• Journal of the Korean Institute of Gas
• /
• v.7 no.2 s.19
• /
• pp.48-53
• /
• 2003

This study is to look at the effect for deformation of carbon steel for high-presure pipe, on the AE signals produced by tensile test. Acoustic emission(AE) has been widely used in various fields because of its extreme sensitivity, dynamic detection ability and location of growing defects. We investigated a relationship failure mode and AE signals by tensile test, From the tensile test, we could divide into four ranges of the failure modes of elastic range, yield range, plastic range before $\sigma$u, plastic range after $\sigma$u. And failure behaviors of elastic range, yield range, plastic range before $\sigma$u, plastic range after $\sigma$u could be evaluated in tensile test by AE counts, accumulation counts and time frequency analysis. It is expected to be basic data that can protect a risk according to tensile test and bending of pipe material for pressure vessel, as a real time test of AE.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.6
• /
• pp.637-644
• /
• 2019

In recent years, many public safety systems in the smart city are developed. These systems are taking responsibility to make a safe and comfortable city. In this paper, we propose vehicle tracking systems include a public safety system that enables the policeman to track the stolen vehicles more efficiently by providing the vehicle information in real time. When a vehicle is stolen, the vehicle owner can send a user emergency request. Then, the public safety server which supported by a geospatial query technique will give information such as time, distance, and routes to a policeman who is closest to the location of the vehicle to catch the thief. 300 simulations were performed to evaluate the performance of the system. We found that the average of times required when vehicle owner send a user emergency message on user application until policeman obtain a vehicle tracking request on police application below 1.2 seconds.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.1
• /
• pp.85-93
• /
• 2022

This paper contains the design and implementation results of a package tour management application using a Geofence technology as well as the performance evaluation. This application ables the tour guide to monitor the tourist movement in real-time whether the tourists are inside the virtual polygonal Geofence set by the tour guide. Even when the tour is moving between travel destinations, a virtual circular Geofence can be set by the tour guide to monitoring the tourist movement while on the move. The application includes tour guide's and tourist's locations, schedule and participant management. To evaluate the performance, average response time and accuracy is measured, resulting in satisfactory performance. The average response time ranged from 0.0047 seconds to 7.3 seconds in various cases and for accuracy, it scored 100% in various cases. It is expected that implementing Geofence technology to package tour management applications will help tour guides to perform more productive package tours by reducing the burden of managing tourists.

• Journal of Web Engineering
• /
• v.21 no.3
• /
• pp.729-750
• /
• 2022

In general, the importance of 6DoF (degree of freedom) 3D (dimension) volumetric contents technology is emerging in 5G (generation) telepresence service, Web-based (WebGL) graphics, computer vision, robotics, and next-generation augmented reality. Since it is possible to acquire RGB images and depth images in real-time through depth sensors that use various depth acquisition methods such as time of flight (ToF) and lidar, many changes have been made in object detection, tracking, and recognition research. In this paper, we propose a method to improve the quality of 3D models for 5G telepresence by processing images acquired through depth and RGB cameras on a multi-view camera system. In this paper, the quality is improved in two major ways. The first concerns the shape of the 3D model. A method of removing noise outside the object by applying a mask obtained from a color image and a combined filtering operation to obtain the difference in depth information between pixels inside the object were proposed. Second, we propose an illumination compensation method for images acquired through a multi-view camera system for photo-realistic 3D model generation. It is assumed that the three-dimensional volumetric shooting is done indoors, and the location and intensity of illumination according to time are constant. Since the multi-view camera uses a total of 8 pairs and converges toward the center of space, the intensity and angle of light incident on each camera are different even if the illumination is constant. Therefore, all cameras take a color correction chart and use a color optimization function to obtain a color conversion matrix that defines the relationship between the eight acquired images. Using this, the image input from all cameras is corrected based on the color correction chart. It was confirmed that the quality of the 3D model could be improved by effectively removing noise due to the proposed method when acquiring images of a 3D volumetric object using eight cameras. It has been experimentally proven that the color difference between images is reduced.

• Journal of Ship and Ocean Technology
• /
• v.6 no.4
• /
• pp.1-12
• /
• 2002

A control system for an automated line heating process is developed by use of object-oriented methodology. The main function of the control system is to provide real-time heating information to technicians or automated machines. The information includes heating location, torch speed, heating order, and others. The system development is achieved by following the five steps in the object-oriented procedure. First, requirements are specified and corresponding objects are determined. Then, the analysis, design, and implementation of the proposed system are sequentially carried out. The system consists of six subsystems, or modules. These are (1) the inference module with an artificial neural network algorithm, (2) the analysis module with the Finite Element Method and kinematics analysis, (3) the data access module to store and retrieve the forming information, (4) the communication module, (5) the display module, and (6) the measurement module. The system is useful, irrespective of the heating sources, i.e. flame/gas, laser, or high frequency induction heating. A newly developed automated line heating machine is connected to the proposed system. Experiments and discussions follow.