• Journal of Radiation Protection and Research
• /
• v.47 no.3
• /
• pp.111-133
• /
• 2022

The exciting advancement related to the "modeling of digital human" in terms of a computational phantom for radiation dose calculations has to do with the latest hype related to deep learning. The advent of deep learning or artificial intelligence (AI) technology involving convolutional neural networks has brought an unprecedented level of innovation to the field of organ segmentation. In addition, graphics processing units (GPUs) are utilized as boosters for both real-time Monte Carlo simulations and AI-based image segmentation applications. These advancements provide the feasibility of creating three-dimensional (3D) geometric details of the human anatomy from tomographic imaging and performing Monte Carlo radiation transport simulations using increasingly fast and inexpensive computers. This review first introduces the history of three types of computational human phantoms: stylized medical internal radiation dosimetry (MIRD) phantoms, voxelized tomographic phantoms, and boundary representation (BREP) deformable phantoms. Then, the development of a person-specific phantom is demonstrated by introducing AI-based organ autosegmentation technology. Next, a new development in GPU-based Monte Carlo radiation dose calculations is introduced. Examples of applying computational phantoms and a new Monte Carlo code named ARCHER (Accelerated Radiation-transport Computations in Heterogeneous EnviRonments) to problems in radiation protection, imaging, and radiotherapy are presented from research projects performed by students at the Rensselaer Polytechnic Institute (RPI) and University of Science and Technology of China (USTC). Finally, this review discusses challenges and future research opportunities. We found that, owing to the latest computer hardware and AI technology, computational human body models are moving closer to real human anatomy structures for accurate radiation dose calculations.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.7
• /
• pp.312-318
• /
• 2006

The conventional lip-synch system has a two-step process, speech segmentation and recognition. However, the difficulty of speech segmentation procedure and the inaccuracy of training data set due to the segmentation lead to a significant Performance degradation in the system. To cope with that, the connected vowel recognition method using Head-Body-Tail (HBT) model is proposed. The HBT model which is appropriate for handling relatively small sized vocabulary tasks reflects co-articulation effect efficiently. Moreover the 7 vowels are merged into 3 classes having similar lip shape while the system is optimized by employing a class dependent SCHMM structure. Additionally in both end sides of each word which has large variations, 8 components Gaussian mixture model is directly used to improve the ability of representation. Though the proposed method reveals similar performance with respect to the CHMM based on the HBT structure. the number of parameters is reduced by 33.92%. This reduction makes it a computationally efficient method enabling real time operation.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.3
• /
• pp.88-97
• /
• 2000

This paper presents motion estimation method using region segmentation information Motion estimation which is very difficult to be implemented only by software because of intensive computation cost, is implemented by special-purpose hardware in real-time applications In this paper, we propose region based motion estimation algorithm which can reduce the computation cost by using region segmentation information and setting the variable search window compared with FSMA algorithm Secondly, another proposed algorithm is to segment semantic region like face for selective coding and transfer of semantic region using segmented region information This work alms to improving the subjective quality of skin color region or face region m the picture that has slow motion and IS mainly composed of one or two speakers of video conference and video telephony applications.

• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.67-76
• /
• 2019

In this paper, we propose an efficient object classification method based on semantic segmentation for multi-labeled image data. In addition to various pixel unit information and processing techniques such as color information, contour, contrast, and saturation included in image data, a detailed region in which each object is located is extracted as a meaningful unit and the experiment is conducted to reflect the result in the inference. We use a neural network that has been proven to perform well in image classification to understand which object is located where image data containing various class objects are located. Based on these researches, we aim to provide artificial intelligence services that can classify real-time detailed areas of complex images containing various objects in the future.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.3138-3151
• /
• 2022

Traffic safety and congestion are becoming more and more serious, especially the frequent occurrence of traffic accidents, which have caused great casualties and economic losses. Cellular Vehicle to Everything (C-V2X) can assist in safe driving and improve traffic efficiency through real-time information sharing and communication between vehicles. All vehicles communicate directly with Base Stations (BS), which will increase the base station load. And when the communicating vehicles are too far apart, too fast or there are obstacles in the communication path, the communication link can be unstable or even interrupted. Therefore, choosing an effective and reliable multi-hop relay-assisted Vehicle to Vehicle (V2V) communication can not only reduce the base station load and improve the system throughput but also expand the base station coverage and improve the communication quality of edge vehicles. Therefore, a communication area division scheme based on regular hexagon segmentation technology is proposed, a relay-assisted V2V communication mechanism is designed for the divided communication areas, and an efficient communication link is constructed by selecting the best relay node. Simulation results show that the scheme can improve the throughput of the system by nearly 55% and enhance the robustness of the V2V communication link.

• Nuclear Engineering and Technology
• /
• v.49 no.7
• /
• pp.1442-1450
• /
• 2017

In liquid metal fast breeder reactors, postulated failures of the plant protection system may lead to serious unprotected accidental consequences. Unprotected transients are generically categorized as transient overpower accidents and transient under cooling accidents. In both cases, core meltdown may occur and this can lead to a molten fuel coolant interaction (MFCI). The understanding of MFCI phenomena is essential for study of debris coolability and characteristics during post-accident heat removal. Sodium is used as coolant in liquid metal fast breeder reactors. Viewing inside sodium at elevated temperature is impossible because of its opaqueness. In the present study, a methodology to depict MFCI phenomena using a flat panel detector based imaging system (i.e., real time radiography) is brought out using a woods metal-water experimental facility which simulates the $UO_2-Na$ interaction. The developed imaging system can capture attributes of the MFCI process like jet breakup length, jet front velocity, fragmented particle size, and a profile of the debris bed using digital image processing methods like image filtering, segmentation, and edge detection. This paper describes the MFCI process and developed imaging methodology to capture MFCI attributes which are directly related to the safe aspects of a sodium fast reactor.

• Journal of the Korean Society for Precision Engineering
• /
• v.18 no.3
• /
• pp.68-74
• /
• 2001

A lane detection based on a road model or feature all needs correct acquirement of information on the lane in an image. It is inefficient to implement a lane detection algorithm through the full range of an image when it is applied to a real road in real time because of the calculating time. This paper defines two (other proper terms including"modes") for detecting lanes on a road. First is searching mode that is searching the lane without any prior information of a road. Second is recognition mode, which is able to reduce the size and change the position of a searching range by predicting the position of a lane through the acquired information in a previous frame. It allows to extract accurately and efficiently the edge candidate points of a lane without any unnecessary searching. By means of inverse perspective transform which removes the perspective effect on the edge candidate points, we transform the edge candidate information in the Image Coordinate System(ICS) into the plan-view image in the World Coordinate System(WCS). We define a linear approximation filter and remove faulty edge candidate points by using it. This paper aims at approximating more correctly the lane of an actual road by applying the least-mean square method with the fault-removed edge information for curve fitting.e fitting.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1398-1400
• /
• 1996

In this paper, a method of the decision of the road direction for ALV(Autonomous Land Vehicle) road following by region-based segmentation is presented. The decision of the road direction requires extracting road regions from images in real-time to guide the navigation of ALV on the roadway. Two thresholds to discriminate between road and non-road region in the image are easily decided, using knowledge of problem region and polygonal approximation that searches multiple peaks and valleys in histogram of a road image. The most likely road region of the binary image is selected from original image by these steps. The location of a vanishing point to indicate the direction of the road can be obtained applying it to X-Y profile of the binary road region again. It can successfully steer a ALV along a road reliably, even in the presence of fluctuation of illumination condition, bad road surface condition such as hidden boundaries, shadows, road patches, dirt and water stains, and unusual road condition. Pyramid structure also saves time in processing road images and a real-time image processing for achieving navigation of ALV is implemented. The efficacy of this approach is demonstrated using several real-world road images.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.5
• /
• pp.323-330
• /
• 2023

The development of an analysis model that reflects the microstructure characteristics of polyvinyl alcohol (PVA) fiber-reinforced cementitious composites, which have a highly complex microstructure, enables synergy between efficient material design and real experiments. PVA fiber orientations are an important factor that influences the mechanical behavior of PVA fiber-reinforced cementitious composites. Owing to the difficulty in distinguishing the gray level value obtained from micro-CT images of PVA fibers from adjacent phases, fiber segmentation is time-consuming work. In this study, a micro-CT test with a voxel size of 0.65 ㎛³ was performed to investigate the three-dimensional distribution of fibers. To segment the fibers and generate training data, histogram, morphology, and gradient-based phase-segmentation methods were used. A U-net model was proposed to segment fibers from micro-CT images of PVA fiber-reinforced cementitious composites. Data augmentation was applied to increase the accuracy of the training, using a total of 1024 images as training data. The performance of the model was evaluated using accuracy, precision, recall, and F1 score. The trained model achieved a high fiber segmentation performance and efficiency, and the approach can be applied to other specimens as well.

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.1
• /
• pp.1-11
• /
• 2001

This paper presents a learning-based approach for the construction of license Plate recognition system. The system consist of three modules. They are respectively, car detection module, license plate recognition module and recognition module. Car detection module detects a car in the given image sequence obtained from the camera with simple color-based approach. Segmentation module extracts the license plate in detect car image using neural network as filters for analyzing the color and texture properties of license plate. Recognition module then reads characters in detected license plate with support vector machine (SVM)-based characters recognizer. The system has been tested from parking lot and tollgate, etc. and have show the following performances on average: Car detect rate 100%, segmentation rate 97.5%, and character recognition rate about 97.2%. Overall system performances is 94.7% and processing time is one sec. Then our propose system does well using real world.