• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.4
• /
• pp.197-203
• /
• 2015

Nuclear power plant has increased continuously for power production in all over the world and the interest about nuclear accident and the dismantling of aging nuclear power plant has been a growing. The leaked radioactive source that is generated by radiation accidents must detect and remove to minimized the damage as soon as possible. Gamma-ray detection system that have been developed until now cannot provide the precise position of radioactive sources because they detect and imaging the position of radiation sources in just two dimensions. In this paper, stereo gamma ray detection system has developed and the algorithm for calculation of the distance has implemented to be able to measure the distribution of the leakage gamma ray source for the system. Stereo camera calibration for distance detection was conducted with the correction pattern and LED light and we carried out performance test of the system for the LED light source and a gamma ray source. In both experiments the results of the performance test, it was confirmed to have a 5% error. The results of this paper is used as a material for the development of gamma-ray imaging device.

• Journal of Radiation Industry
• /
• v.5 no.2
• /
• pp.185-189
• /
• 2011

As nuclear industry has been developed, a various types of radiological contamination has occurred. After 9.11 terror in U.S.A., it has been concerned that terrorists' active area has been enlarged to use nuclear or radioactive substance. Recently, the most powerful earth-quake stroke, which triggered a massive tsunami in Japan and then Fukushima nuclear power plant reactor has suffered from a serious accident in history. The Fukushima reactor accident has occurred an anxiety of radiation leaks and about 170,000 people have been evacuated from the accidental area near the nuclear power plant. For these reasons, a social chaos can be occurred if radiological contamination occurs to the supply system for the drinking water. As such, the establishment of the radiation monitoring system for the city main water system is compelling for the national security. In this study, a feasibility test of radiation monitoring system which consists of unified hybrid-type radiation detectors was experimented for multi detection system by using gamma-ray imaging. The hybrid-type radiation sensors were fabricated with CsI(Tl) scintillators and photodiodes. A preamplifier and amplifier was also fabricated and assembled with the sensor in the shielding case. For the preliminary test of detection of radiological contamination in the river, multi CsI(Tl)-PIN photodiode radiation detectors and $^{137}Cs$ gamma-ray source were used. The DAQ was done by Linux based ROOT program and NI DAQ system with Labview program. The simulated contamination was assumed to be occurred at Gapcheon river in Daejeon city. Multi CsI(Tl)-PIN photodiode radiation detectors were positioned at the Gapcheon river side. Assuming that the radiological contaminations flows in the river the $^{137}Cs$ gamma-ray source has been moved and then, the contamination region was reconstructed.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.5
• /
• pp.112-125
• /
• 2019

An acoustic signal-based, tunnel-incident detection system was developed and evaluated. The system was comprised of three components: algorithm, acoustic signal collector, and server system. The algorithm, which was based on nonnegative tensor factorization and a hidden Markov model, processes the acoustic signals to attenuate noise and detect incident-related signals. The acoustic signal collector gathers the tunnel sounds, digitalizes them, and transmits the digitalized acoustic signals to the center server. The server system issues an alert once the algorithm identifies an incident. The performance of the system was evaluated thoroughly in two steps: first, in a controlled tunnel environment using the recorded incident sounds, and second, in an uncontrolled tunnel environment using real-world incident sounds. As a result, the detection rates ranged from 80 to 95% at distances from 50 to 10 m in the controlled environment, and 94 % in the uncontrolled environment. The superiority of the developed system to the existing video image and loop detector-based systems lies in its instantaneous detection capability with less than 2 s.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.751-770
• /
• 2019

Action recognition is an essential task in computer vision due to the variety of prospective applications, such as security surveillance, machine learning, and human-computer interaction. The availability of more video data than ever before and the lofty performance of deep convolutional neural networks also make it essential for action recognition in video. Unfortunately, limited crafted video features and the scarcity of benchmark datasets make it challenging to address the multi-person action recognition task in video data. In this work, we propose a deep convolutional neural network-based Effective Hybrid Learning (EHL) framework for two-person interaction classification in video data. Our approach exploits a pre-trained network model (the VGG16 from the University of Oxford Visual Geometry Group) and extends the Faster R-CNN (region-based convolutional neural network a state-of-the-art detector for image classification). We broaden a semi-supervised learning method combined with an active learning method to improve overall performance. Numerous types of two-person interactions exist in the real world, which makes this a challenging task. In our experiment, we consider a limited number of actions, such as hugging, fighting, linking arms, talking, and kidnapping in two environment such simple and complex. We show that our trained model with an active semi-supervised learning architecture gradually improves the performance. In a simple environment using an Intelligent Technology Laboratory (ITLab) dataset from Inha University, performance increased to 95.6% accuracy, and in a complex environment, performance reached 81% accuracy. Our method reduces data-labeling time, compared to supervised learning methods, for the ITLab dataset. We also conduct extensive experiment on Human Action Recognition benchmarks such as UT-Interaction dataset, HMDB51 dataset and obtain better performance than state-of-the-art approaches.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.12
• /
• pp.1535-1541
• /
• 2019

To carry out safe and rapid decontamination in radiological accident areas, acquisition of various information on radiation sources is needed. In particular, to figure out the location and distribution of radiation sources is essential for rapid follow-up and removal of contaminants as well as minimizing worker damage. The radiation distribution detection device is used to obtain the position and distribution information of the radiation source. In the case of a radiation distribution detection device, a detection sensor unit is generally composed of a single sensor, and the detection range is limited due to the physical characteristics of the single sensor. We applied a calibration detector for controlling the detection sensitivity of a single sensor for radiation detection and improved the limited detection range of radiation dose rate. Also, gamma irradiation test confirmed the improvement of radiation distribution detection range.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.2
• /
• pp.187-192
• /
• 2021

This study proposes a system for take-off in a forest or similar complex environment using an object detector. In the simulator, a raspberry pi is mounted on a quadcopter with a length of 550mm between motors on a diagonal line, and the experiment is conducted based on edge computing. As for the images to be used for learning, about 150 images of 640⁎480 size were obtained by selecting three points inside Kunsan University, and then converting them to black and white, and pre-processing the binarization by placing a boundary value of 127. After that, we trained the SSD_Inception model. In the simulation, as a result of the experiment of taking off the drone through the model trained with the verification image as an input, a trajectory similar to the takeoff was drawn using the label.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.26-36
• /
• 2021

In this study, a deep learning model for predicting the queue length was developed using the information collected from the image detector. Then, a multiple regression analysis model, a statistical technique, was derived and compared using two indices of mean absolute error(MAE) and root mean square error(RMSE). From the results of multiple regression analysis, time, day of the week, occupancy, and bus traffic were found to be statistically significant variables. Occupancy showed the most strong impact on the queue length among the variables. For the optimal deep learning model, 4 hidden layers and 6 lookback were determined, and MAE and RMSE were 6.34 and 8.99. As a result of evaluating the two models, the MAE of the multiple regression model and the deep learning model were 13.65 and 6.44, respectively, and the RMSE were 19.10 and 9.11, respectively. The deep learning model reduced the MAE by 52.8% and the RMSE by 52.3% compared to the multiple regression model.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_2
• /
• pp.737-746
• /
• 2022

Utilizing weather independent SAR images along with machine learning based object detector is effective in robust vessel monitoring. While conventional SAR images often applied amplitude data from Single Look Complex, exploitation of polarimetric parameters acquired from multiple polarimetric SAR images was yet to be implemented to vessel detection utilizing machine learning. Hence, this study used four polarimetric parameters (H, p₁, DoP, DPRVI) retrieved from eigen-decomposition and two backscattering coefficients (γ₀, _VV, γ₀, _VH) from radiometric calibration; six bands in total were respectively exploited from 52 Sentinel-1 SAR images, accompanied by vessel training data extracted from AIS information which corresponds to acquisition time span of the SAR image. Evaluating different cases of combination, the use of polarimetric indexes along with amplitude values derived enhanced vessel detection performances than that of utilizing amplitude values exclusively.

• Smart Media Journal
• /
• v.12 no.7
• /
• pp.9-17
• /
• 2023

Plant diseases and pests affect the growth of various plants, so it is very important to identify pests at an early stage. Although many machine learning (ML) models have already been used for the inspection and classification of plant pests, advances in deep learning (DL), a subset of machine learning, have led to many advances in this field of research. In this study, disease and pest inspection of abnormal crops and maturity classification were performed for normal crops using YOLOX detector and MobileNet classifier. Through this method, various plant pest features can be effectively extracted. For the experiment, image datasets of various resolutions related to strawberries, peppers, and tomatoes were prepared and used for plant pest classification. According to the experimental results, it was confirmed that the average test accuracy was 84% and the maturity classification accuracy was 83.91% in images with complex background conditions. This model was able to effectively detect 6 diseases of 3 plants and classify the maturity of each plant in natural conditions.

• Nuclear Engineering and Technology
• /
• v.55 no.8
• /
• pp.2797-2801
• /
• 2023

CdZnTeSe (CZTS) has attracted attention for applications in X- and gamma-ray detectors owing to its improved properties compared to those of CdZnTe (CZT). In this study, we grew and processed single crystals of CZT and CZTS using the Bridgeman method to confirm the feasibility of using a dosimeter for high-energy X-rays in radiotherapy. We evaluated their linearity and precision using the coefficient of determination (R²) and relative standard deviation (RSD). CZTS showed sufficient RSD values lower than 1.5% of the standard for X-ray dosimetry, whereas CZT's RSD values increased dramatically under some conditions. CZTS exhibited an R² value of 0.9968 at 500 V/cm, whereas CZT has an R² value of 0.9373 under the same conditions. The X-ray response of CZTS maintains its pulse shape at various dose rates, and its properties are improved by adding selenium to the CdTe matrix to lower the defect density and sub-grain boundaries. Thus, we validated that CZTS shows a better response than CZT to high-energy X-rays used for radiotherapy. Further, the applicability of an onboard imager, a high-energy X-ray (>6 MV) image, is presented. The proposed methodology and results can guide future advances in X-ray dose detection.