• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.7
• /
• pp.1117-1122
• /
• 2017

Pedestrian detection is a very important and valuable part of artificial intelligence and computer vision. It can be used in various areas for example automatic drive, video analysis and others. Many works have been done for the pedestrian detection. The accuracy of pedestrian detection on multiple pedestrian image has reached high level. It is not easily get more progress now. This paper proposes a new structure based on the idea of HOG and convolutional filters to do the pedestrian detection in single pedestrian image. It can be a method to increase the accuracy depend on the high accuracy in single pedestrian detection. In this paper, we use Multiblock HOG and magnitude of the pixel as the feature and use convolutional filter to do the to extract the feature. And then use NEWFM to be the classifier for training and testing. We use single pedestrian image of the INRIA data set as the data set. The result shows that the Convolutional Multiblock HOG we proposed get better performance which is 0.015 miss rate at 10-4 false positive than the other detection methods for example HOGLBP which is 0.03 miss rate and ChnFtrs which is 0.075 miss rate.

• Journal of the Institute of Convergence Signal Processing
• /
• v.1 no.1
• /
• pp.23-31
• /
• 2000

Iterative curve evolution techniques are powerful methods for image segmentation. Classical methods proposed curve evolutions which guarantee close contours at convergence and, combined with the level set method, they easily handled curve topology changes. In this paper, we present a new geometric active contour model based on level set methods introduced by Osher & Sethian for detection of object boundaries or shape and we adopt anisotropic diffusion filtering method for removing noise from original image. Classical methods allow only one-way curve evolutions : shrinking or expanding of the curve. Thus, the initial curve must encircle all the objects to be segmented or several curves must be used, each one totally inside one object. But our method allows a two-way curve evolution : parts of the curve evolve in the outward direction while others evolve in the inward direction. It offers much more freedom in the initial curve position than with a classical geodesic search method. Our algorithm performs accurate and precise segmentations from noisy images with complex objects(jncluding sharp angles, deep concavities or holes), Besides it easily handled curve topology changes. In order to minimize the processing time, we use the narrow band method which allows us to perform calculations in the neighborhood of the contour and not in the whole image.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.6
• /
• pp.490-496
• /
• 2014

The thickness of knee joint cartilage causes most diseases of knee. Therefore, an articular cartilage segmentation of knee magnetic resonance imaging (MRI) is required to diagnose a knee diagnosis correctly. In particular, fully automatic segmentation method of knee joint cartilage enables an effective diagnosis of knee disease. In this paper, we analyze a well-known level-set based segmentation method in brain MRI, and apply that method to knee MRI with solving some problems from different image characteristics. The proposed method, a fully automatic segmentation in whole process, enables to process faster than previous semi-automatic segmentation methods. Also it can make a three-dimension visualization which provides a specialist with an assistance for the diagnosis of knee disease. In addition, the proposed method provides more accurate results than the existing methods of articular cartilage segmentation in knee MRI through experiments.

• The Journal of Society for e-Business Studies
• /
• v.19 no.4
• /
• pp.45-60
• /
• 2014

Dentist can obtain 3D anatomical information without distortion and information loss by using dental Computed Tomography scan images on line, and also can make the preoperative plan of implant placement or orthodontics. It is essential to segment individual tooth for making an accurate diagnosis. However, it is very difficult to distinguish the difference in the brightness between the dental and adjacent area. Especially, the root of a tooth is very elusive to automatically identify in dental CT images because jawbone normally adjoins the tooth. In the paper, we propose a method of automatically tooth region segmentation, which can identify the root of a tooth clearly. This algorithm separate the tooth from dental CT scan images by using Seeded Region Growing method on dental crown and by using Level-set method on dental root respectively. By using the proposed method, the results can be acquired average 19.2% better accuracy, compared to the result of the previous methods.

• The Transactions of the Korea Information Processing Society
• /
• v.1 no.4
• /
• pp.490-501
• /
• 1994

In this study the problems of cell marking method used in the field of ATM network traffic control are presented. Also an extended cell marking method considering the user level priority is proposed. The conventional traffic monitoring schemes set the CLP bit of a cell to 1 only under the circumstance of the violation of traffic contract. It causes that the number of low level cells increases and the levels of cells are lowered regardless of the user level priority. The three level priority control method combining FCI bit with CLP bit has also been proposed. It divides CLP=0 cells into two levels. Consequently, the proposed method preserves more cells in high level than the conventional one and the real loss of high level cells can be reduced. The performance of the proposed scheme has also been analyzed by the PBS(partial buffer sharing) with two thresholds for the proposed three levels. The result shows that the PBS with two thresholds can give more efficient control than the scheme with no priority, or the PBS with one threshold.

• Journal of the Ergonomics Society of Korea
• /
• v.32 no.1
• /
• pp.37-45
• /
• 2013

Objective: This study describes the change of operator performance in drastic change of illumination level, and proposes an alternative method to cope with it. Background: The control standard of illumination for nuclear power plants(NPPs) is based on the set of limit criteria for maintaining a specific illumination level. However, there is a possibility to cause human errors according to the psychological and physiological influences to operators in the situation of drastic change of illumination such as SBO(Station Black Out), so a basic study is necessary to review the current approach. Method: We assessed the visual fatigue, subjective work load and task performance according to the three illumination situations(Normal Illumination, Emergency Illumination, and Drastic Change of Illumination). Result: Research finding shows that there are not significant differences in task performance between normal illumination (1,000lx level) and emergency illumination (100lx level), only if beyond the dark adaptation limit. However, subjective work load on mental demand and visual fatigue show a potential challenge to visual performance in drastic change of illumination. Conclusion/Application: Several trials can complement this challenge in NPPs by applying 3-way communication, enhancing readability of procedures, and managing the visual factors affecting the operators' performance through a Visual Environment Management Program including visual health aspects, etc.

• Journal of the Korean Society of Safety
• /
• v.35 no.1
• /
• pp.107-115
• /
• 2020

This paper introduces the first vital area identification (VAI) process for the physical protection of nuclear power plants (NPPs) during low power and shutdown (LPSD) operation. This LPSD VAI is based on the 3rd generation VAI method which very efficiently utilizes probabilistic safety assessment (PSA) event trees (ETs). This LPSD VAI process was implemented to the virtual NPP during LPSD operation in this study. Korea Atomic Energy Research Institute (KAERI) had developed the 2nd generation full power VAI method that utilizes whole internal and external (fire and flooding) PSA results of NPPs during full power operation. In order to minimize the huge burden of the 2nd generation full power VAI method, the 3rd generation full power VAI method was developed, which utilizes ETs and minimal PSA fault trees instead of using the whole PSA fault tree. In the 3rd generation full power VAI method, (1) PSA ETs are analyzed, (2) minimal mitigation systems for avoiding core damage are selected from ETs by calculating system-level target sets and prevention sets, (3) relatively small sabotage fault tree that has the systems in the shortest system-level prevention set is composed, (4) room-level target sets and prevention sets are calculated from this small sabotage fault tree, and (5) the rooms in the shortest prevention set are defined as vital areas that should be protected. Currently, the 3rd generation full power VAI method is being employed for the VAI of Korean NPPs. This study is the first development and application of the 3rd generation VAI method to the LPSD VAI of NPP. For the LPSD VAI, (1) many LPSD ETs are classified into a few representative LPSD ETs based on the functional similarity of accident scenarios, (2) a few representative LPSD ETs are simplified with some VAI rules, and then (3) the 3rd generation VAI is performed as mentioned in the previous paragraph. It is well known that the shortest room-level prevention sets that are calculated by the 2nd and 3rd generation VAI methods are identical.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.1
• /
• pp.45-56
• /
• 2015

In this paper, we present a method that can detect context-sensitive word errors and generate correction candidates. Spelling error detection is one of the most widespread research topics, however, the approach proposed in this paper is adjusted for an automated English scoring system. A common strategy in context-sensitive word error detection is using a pre-defined confusion set to generate correction candidates. We automatically generate a confusion set in order to consider the characteristics of sentences written by second-language learners. We define a word error that cannot be detected by a conventional grammar checker because of part-of-speech ambiguity, and propose how to detect the error and generate correction candidates for this kind of error. An experiment is performed on the English writings composed by junior-high school students whose mother tongue is Korean. The f1 value of the proposed method is 70.48%, which shows that our method is promising comparing to the current-state-of-the art.

• Proceedings of the KIPE Conference
• /
• 2015.07a
• /
• pp.177-178
• /
• 2015

This paper presents a neutral point deviation compensating control algorithm applied to a 3-level NPC converter. The neutral point deviation is analyzed with a focus on the current flowing out of or into the neutral point of the dc link. Based on the zero sequence components of the reference voltages, this paper analyzes the neutral point deviation and balancing control for 3-level NPC converter. An analytical method is proposed to calculate the injected zero sequence voltage for NP balancing based on average neutral current. This paper also proposes a control scheme compensating for the neutral point deviation under generalized unbalanced grid operating conditions. The positive and negative sequence components of the pole voltages and ac input currents are employed to accurately explain the behavior of 3-level NPC converter. Simulation and experimental results for a test set up of 30kW are shown to verify the validity of the proposed algorithm.

• Journal of Korean Society of Rural Planning
• /
• v.11 no.1 s.26
• /
• pp.9-15
• /
• 2005

Preservation of geometrical context of terrains in a digitized format is useful in handling and making modification to the data. Digitization of three-dimensional terrain still proves a great challenge due to heavy load of context required to retain details of topological and geometrical information. Methods of simplification, restoration and multi-level terrain generation are often employed to transform the original data into a compressed digital format. However, reduction of the stored data size comes at an expense of loss of details in the original data set. This article reports on an alternative scheme for simplification and restoration of terrain data. The algorithm utilizes the fact that the terrain formation and patterns can be predicted and modeled through the fractal algorithm. This method was used to generate multi-level terrain model based on NGIS digital maps with preserving geometrical context of terrains.