• Nuclear Engineering and Technology
• /
• v.55 no.2
• /
• pp.493-505
• /
• 2023

Comprehensive condition monitoring of large industry systems such as nuclear power plants (NPPs) is essential for safety and maintenance. In this study, we developed novel system-scale diagnostic technology based on deep-learning and IR thermography that can efficiently and cost-effectively classify system conditions using compact Raspberry Pi and IR sensors. This diagnostic technology can identify the presence of an abnormality or accident in whole system, and when an accident occurs, the type of accident and the location of the abnormality can be identified in real-time. For technology development, the experiment for the thermal image measurement and performance validation of major components at each accident condition of NPPs was conducted using a thermal-hydraulic integral effect test facility with compact infrared sensor modules. These thermal images were used for training of deep-learning model, convolutional neural networks (CNN), which is effective for image processing. As a result, a proposed novel diagnostic was developed that can perform diagnosis of components, whole system and accident classification using thermal images. The optimal model was derived based on the modern CNN model and performed prompt and accurate condition monitoring of component and whole system diagnosis, and accident classification. This diagnostic technology is expected to be applied to comprehensive condition monitoring of nuclear power plants for safety.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.700-703
• /
• 2021

Infrared cameras are widely used in recent research for automatic monitoring the abnormal behaviors of the pig. However, when deployed in real pig farms, infrared cameras always get polluted due to the harsh environment of pig farms which negatively affects the performance of pig monitoring. In this paper, we propose a real-time noise-robust infrared camera-based pig automatic monitoring system to improve the robustness of pigs' automatic monitoring in real pig farms. The proposed system first uses a preprocessor with a U-Net architecture that was trained as a GAN generator to transform the noisy images into clean images, then uses a YOLOv5-based detector to detect pigs. The experimental results show that with adding the preprocessing step, the average pig detection precision improved greatly from 0.639 to 0.759.

• Journal of The Korean Astronomical Society
• /
• v.43 no.1
• /
• pp.1-8
• /
• 2010

JHK near-infrared photometry of star clusters in the dwarf irregular/dwarf starburst galaxy NGC 1569 are presented. After adopting several criteria to exclude other sources (foreground stars, background galaxies, etc.), 154 candidates of star clusters are identified in the near-infrared images of NGC 1569, which include very young star clusters. Especially, from analysis based on theoretical background, we found ten very young star clusters near the center of NGC 1569. The total reddening values toward these clusters are estimated to be $A_V$=1-9 mag from comparison with the theoretical estimates given by the Leitherer et al. (1999)'s star cluster model.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.4
• /
• pp.291-300
• /
• 2015

In the steel manufacturing process heat-endurance deterioration of a ladle used to cause a big accident. In this paper, an infrared imaging system and image analyzing procedure are proposed for inspecting refractory bricks of a ladle. The proposed algorithm contains following three parts: two-stage image selection procedure, reference point detection, and analysis of heat-endurance deterioration. Experiments were conducted with real data from a steel plant and detailed configuration of infrared imaging system was presented.

• Journal of Korea Multimedia Society
• /
• v.6 no.6
• /
• pp.977-984
• /
• 2003

In this paper, we propose an image enhancement algorithm for panoramic infrared image. This method divides a panoramic infrared image into disjoint subimages and performs the contrast stretch for subimages using statistical characteristics of each subimage. But these cause blocking artifact in boundary regions of neighboring subimages which different to the statistical characteristic. To remove blocking artifact, we perform the contrast stretch for subimage's boundary regions using statistical characteristics of horizontally neighboring subimages. Experimental results show that the proposed method effectively improves their appearance to human viewers.

• Journal of The Korean Astronomical Society
• /
• v.39 no.4
• /
• pp.89-94
• /
• 2006

We present JHK-band near-infrared photometry of the star clusters in the dwarf irregular galaxy IC 5152. After excluding possible foreground stars, a number of candidate star clusters are identified in the near-infrared images of IC 5152, which include young populations. Especially, five young star clusters are identified in the(J-H, H-K) two color diagram and the total extinction values toward these clusters are estimated to be $A_v=2-6$ from the comparison with the theoretical values given by the Leitherer et al.(1999)'s theoretical star cluster model.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.7
• /
• pp.39-45
• /
• 2017

In this paper, we propose three compensation methods to solve problems in high-resolution airborne infrared camera and to improve long-range target information acquisition performance. First, image motion and temporal noise reduction technique which is caused by atmospheric turbulence. Second, thermal blurring image correction technique by imperfect performance of NUC(Non Uniformity Correction) or raising the internal temperature of the camera. Finally, DRC(Dynamic Range Compression) and flicker removing technique of 14bits HDR(High Dynamic Range) infrared image. Through this study, we designed techniques to improve the acquisition performance of long-range target information of high-resolution airborne infrared camera, and compared and analyzed the performance improvement result with implemented images.

• Korean Journal of Remote Sensing
• /
• v.30 no.6
• /
• pp.797-807
• /
• 2014

The Sea Surface Temperature (SST) is one of the most important oceanic environmental factors in determining the change of marine environments and ecological activities. Satellite thermal infrared images can be effective for understanding the global trend of sea surface temperature due to large scale. However, their low spatial resolution caused some limitations in some areas where complicated and refined coastal shapes due to many islands are present as in the Korean Peninsula. The coastal ocean is also very important because human activities interact with the environmental change of coastal area and most aqua farming is distributed in the coastal ocean. Thus, low-cost airborne thermal infrared remote sensing with high resolution capability is considered for verifying its possibility to extract SST and to monitor the changes of coastal environment. In this study, an airborne thermal infrared system was implemented using a low-cost and ground-based thermal infrared camera (FLIR), and more than 8 airborne acquisitions were carried out in the western coast of the Korean Peninsula during the periods between May 23, 2012 and December 7, 2013. The acquired thermal infrared images were radiometrically calibrated using an atmospheric radiative transfer model with a support from a temperature-humidity sensor, and geometrically calibrated using GPS and IMU sensors. In particular, the airborne sea surface temperature acquired in June 25, 2013 was compared and verified with satellite SST as well as ship-borne thermal infrared and in-situ SST data. As a result, the airborne thermal infrared sensor extracted SST with an accuracy of $1^{\circ}C$.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.664-669
• /
• 2002

Intertidal zone (tidal flat) is a place which is sometimes dry and sometimes wet depending on the tidal rhythm. Direct measurement of topography in the intertidal zone is very difficult to be achieved. The interface between wet and dry parts in the tidal flat, which can be identified from near infrared band of satellite image, is a 'depth contour' which corresponds to the sea level at the time of satellite pass. Aquisition of topography data in tidal flat is possible by combining various techniques such as (1) identification of the interface between wet and dry parts, (2) GCP correction of satellite image, and (3) realtime prediction of sea level elevation at the time of satellite pass. The algorithm was successfully applied in obtaining topography (bathymetry) data in the intertidal zone of Asan Bay in the west coast of Korea from 26 satellite images. The method is expected to be very efficient in making bathymetry data base in the western and southern parts of Korea where tidal flats are well developed in wide regions.

• International Journal of Contents
• /
• v.6 no.4
• /
• pp.49-56
• /
• 2010

In this paper we present a system that enables the user to interact with large display system even without touching the screen. With two infrared sensitive cameras mounted on the bottom left and bottom right of the display system pointing upwards, the user fingertip position on the selected region of interest of each camera view is found using vertical intensity profile of the background subtracted image. The position of the finger in two images of left and right camera is mapped to the display screen coordinate by using pre-determined matrices, which are calculated by interpolating samples of user finger position on the images taken by pointing finger over some known coordinate position of the display system. The screen is then manipulated according to the calculated position and depth of the fingertip with respect to the display system. Experimental results demonstrate an efficient, robust and stable human computer interaction.