• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.1
• /
• pp.22-28
• /
• 2021

This is a basic study on the development of deep learning-based algorithms to detect smoke before the smoke detector operates in the event of a ship fire, analyze and utilize the detected data, and support fire suppression and evacuation activities by predicting the spread of smoke before it spreads to remote areas. Proposed algorithms were reviewed in accordance with the following procedures. As a first step, smoke images obtained through fire simulation were applied to the YOLO (You Only Look Once) model, which is a deep learning-based object detection algorithm. The mean average precision (mAP) of the trained YOLO model was measured to be 98.71%, and smoke was detected at a processing speed of 9 frames per second (FPS). The second step was to estimate the spread of smoke using the coordinates of the boundary box, from which was utilized to extract the smoke geometry from YOLO. This smoke geometry was then applied to the time series prediction algorithm, long short-term memory (LSTM). As a result, smoke spread data obtained from the coordinates of the boundary box between the estimated fire occurrence and 30 s were entered into the LSTM learning model to predict smoke spread data from 31 s to 90 s in the smoke image of a fast fire obtained from fire simulation. The average square root error between the estimated spread of smoke and its predicted value was 2.74.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.1009-1029
• /
• 2023

Urban trees play a vital role in urban ecosystems,significantly reducing impervious surfaces and impacting carbon cycling within the city. Although previous research has demonstrated the efficacy of employing artificial intelligence in conjunction with airborne light detection and ranging (LiDAR) data to generate urban tree information, the availability and cost constraints associated with LiDAR data pose limitations. Consequently, this study employed freely accessible, high-resolution multispectral satellite imagery (i.e., Sentinel-2 data) to estimate fractional tree canopy cover (FTC) within the urban confines of Suwon, South Korea, employing machine learning techniques. This study leveraged a median composite image derived from a time series of Sentinel-2 images. In order to account for the diverse land cover found in urban areas, the model incorporated three types of input variables: average (mean) and standard deviation (std) values within a 30-meter grid from 10 m resolution of optical indices from Sentinel-2, and fractional coverage for distinct land cover classes within 30 m grids from the existing level 3 land cover map. Four schemes with different combinations of input variables were compared. Notably, when all three factors (i.e., mean, std, and fractional cover) were used to consider the variation of landcover in urban areas(Scheme 4, S4), the machine learning model exhibited improved performance compared to using only the mean of optical indices (Scheme 1). Of the various models proposed, the random forest (RF) model with S4 demonstrated the most remarkable performance, achieving R² of 0.8196, and mean absolute error (MAE) of 0.0749, and a root mean squared error (RMSE) of 0.1022. The std variable exhibited the highest impact on model outputs within the heterogeneous land covers based on the variable importance analysis. This trained RF model with S4 was then applied to the entire Suwon region, consistently delivering robust results with an R² of 0.8702, MAE of 0.0873, and RMSE of 0.1335. The FTC estimation method developed in this study is expected to offer advantages for application in various regions, providing fundamental data for a better understanding of carbon dynamics in urban ecosystems in the future.

• Journal of the Korean earth science society
• /
• v.39 no.1
• /
• pp.53-66
• /
• 2018

The information of surface reflectance ($R_{sfc}$) is important for the heat balance and the environmental/climate monitoring. The $R_{sfc}$ sensitivity to error-induced variables for the Geostationary Environment Monitoring Spectrometer (GEMS) retrieval from geostationary-orbit satellite observations at 300-500 nm was investigated, utilizing polar-orbit satellite data of the MODerate resolution Imaging Spectroradiometer (MODIS) and Ozone Mapping Instrument (OMI), and the radiative transfer model (RTM) experiment. The variables in this study can be cloud, Rayleigh-scattering, aerosol, ozone and surface type. The cloud detection in high-resolution MODIS pixels ($1km{\times}1km$) was compared with that in GEMS-scale pixels ($8km{\times}7km$). The GEMS detection was consistent (~79%) with the MODIS result. However, the detection probability in partially-cloudy (${\leq}40%$) GEMS pixels decreased due to other effects (i.e., aerosol and surface type). The Rayleigh-scattering effect in RGB images was noticeable over ocean, based on the RTM calculation. The reflectance at top of atmosphere ($R_{toa}$) increased with aerosol amounts in case of $R_{sfc}$<0.2, but decreased in $R_{sfc}{\geq}0.2$. The $R_{sfc}$ errors due to the aerosol increased with wavelength in the UV, but were constant or slightly decreased in the visible. The ozone absorption was most sensitive at 328 nm in the UV region (328-354 nm). The $R_{sfc}$ error was +0.1 because of negative total ozone anomaly (-100 DU) under the condition of $R_{sfc}=0.15$. This study can be useful to estimate $R_{sfc}$ uncertainties in the GEMS retrieval.

• Korean Journal of Cognitive Science
• /
• v.28 no.1
• /
• pp.65-90
• /
• 2017

Rewards or penalties become informative only when contingent on an immediately preceding response. Our goal was to determine if the brain responds differently to motivational events depending on whether they provide feedback with the contingencies effective for learning. Event-related fMRI data were obtained from 22 volunteers performing a visuomotor categorical task. In learning-condition trials, participants learned by trial and error to make left or right responses to letter cues (16 consonants). Monetary rewards (+500) or penalties (-500) were given as feedback (learning feedback). In random-condition trials, cues (4 vowels) appeared right or left of the display center, and participants were instructed to respond with the appropriate hand. However, rewards or penalties (random feedback) were given randomly (50/50%) regardless of the correctness of response. Feedback-associated BOLD responses were analyzed with ANOVA [trial type (learning vs. random) x feedback type (reward vs. penalty)] using SPM8 (voxel-wise FWE p < .001). The right caudate nucleus and right cerebellum showed activation, whereas the left parahippocampus and other regions as the default mode network showed deactivation, both greater for learning trials than random trials. Activations associated with reward feedback did not differ between the two trial types for any brain region. For penalty, both learning-penalty and random-penalty enhanced activity in the left insular cortex, but not the right. The left insula, however, as well as the left dorsolateral prefrontal cortex and dorsomedial prefrontal cortex/dorsal anterior cingulate cortex, showed much greater responses for learning-penalty than for random-penalty. These findings suggest that learning-penalty plays a critical role in learning, unlike rewards or random-penalty, probably not only due to its evoking of aversive emotional responses, but also because of error-detection processing, either of which might lead to changes in planning or strategy.

• Korean Journal of Remote Sensing
• /
• v.26 no.2
• /
• pp.123-131
• /
• 2010

In this paper we applied Ground-Based Synthetic Aperture Radar(GB-SAR) interferometry to detect artificial displacement of a reflector and performed an atmospheric humidity correction to improve the accuracy. A series of GB-SAR images were obtained using a center frequency of 5.3 GHz with a range resolution of 25 cm and a azimuth resolution of $0.324^{\circ}$, all in full-polarization (HH, VV, VH, HV) modes. A triangular trihedral corner reflector was located 160 m away from the system, and the artificial displacements of 0-40 mm was implemented during the GB-SAR image acquisition. The result showed that the RMS error between the actual and measured displacements, averaged in all polarization data, was 1.22 mm, while the maximum error in case of the 40 mm displacement was 2.72 mm at HH-polarization. After the atmospheric correction with respect to the humidity, the RMS error was reduced to 0.52 mm. We conclude that a GB-SAR system can be used to monitor the possible displacement of artificial/natural scatterers and the stability assessment with sub-millimeter accuracy.

• Korean Journal of Remote Sensing
• /
• v.37 no.3
• /
• pp.475-491
• /
• 2021

With the recent increase in available high-resolution (< ~1 m) satellite SAR images, the demand for precise registration of SAR images is increasing in various fields including change detection. The registration between high-resolution SAR images acquired in different look angle is difficult due to speckle noise and geometric distortion caused by the characteristics of SAR images. In this study, registration is performed in two stages, coarse and fine, using the x-band SAR data imaged at staring spotlight mode of TerraSAR-X. For the coarse registration, a method combining the adaptive sampling method and SAR-SIFT (Scale Invariant Feature Transform) is applied, and three rigid methods (NCC: Normalized Cross Correlation, Phase Congruency-NCC, MI: Mutual Information) and one non-rigid (Gefolki: Geoscience extended Flow Optical Flow Lucas-Kanade Iterative), for the fine registration stage, was performed for performance comparison. The results were compared by using RMSE (Root Mean Square Error) and FSIM (Feature Similarity) index, and all rigid models showed poor results in all image combinations. It is confirmed that the rigid models have a large registration error in the rugged terrain area. As a result of applying the Gefolki algorithm, it was confirmed that the RMSE of Gefolki showed the best result as a 1~3 pixels, and the FSIM index also obtained a higher value than 0.02~0.03 compared to other rigid methods. It was confirmed that the mis-registration due to terrain effect could be sufficiently reduced by the Gefolki algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.11
• /
• pp.2094-2105
• /
• 1994

This paper contains a Hough transform based projection method derived from Radon transform for tracking dim unresolved(sub-pixel) moving targets that move along straight line parths across a time sequential image data. In contrast to several recently presented Hough transform methods using a compressed image referred to as the track map our proposed technique utilizing a set of projections taken along arbitrary orientations effectively increases the changes of target detection, and creates a robust track estimation environment by incorporating all the available knowledge obtained from the projections. Moreover, in order to quantitatively assess the estimation capability of the projection-based Hough transform algorithm, the analytical bounds on the Hough space parameter errors introduced by image space noise contamination are derived. The simulation yielded promising results of estimating the track parameters even under low signal to noise rations when our technique was tested against the time sequential sets of real infrared image data referred to as the HiCamps.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.22 no.3
• /
• pp.644-653
• /
• 1998

In resistance spot weld, the assurance of weld quality has been a long-standing problem. Since the weld nuggets if resustance spot welding form between the workpieces, visual detection of defects in usually impossible. Welding quality of resistance spot welding can be verified by non destructive and destructive inspections such as X-Ray inspection and testing of weld strength. But these tests, in addition to being time-consuming and costly, can entail risks due to sampling basis. The purpose of this study is the development of the monitoring system based on fuzzy inference, aimed at diagonosis of quality in resistance spot welding. The fuzzy inference system consists of fuzzy input variables, fuzzy membership functions and fuzzy rules. For inferring the welding quality(strength), the experimental data of the spot welding were acquired in various welding conditions with the monitoring system designed. Some fuzzy input variables-maximum, slop and difference values of electrode movement signals-were extracted from the experimental data. It was confirmed that the fuzzy inference values of strength have a .${\pm}$5% error in comparison with actual values for the selected welding conditions(9-10.5KA, 10-14 cycle, 250-300 $kg_f$). This monitoring system can be useful in improving the quality assurance and reliability of the resistance spot welding process.

• Journal of Biomedical Engineering Research
• /
• v.36 no.5
• /
• pp.183-190
• /
• 2015

Invasive blood pressure (IBP) is measured for the patient's real time arterial pressure (ABP) to monitor the critical abrupt disorders of the cardiovascular system. It can be used for the estimation of cardiac output and the opening and closing time detection of the aortic valve. Although the unexplained inflections on ABP make it difficult to find the mathematical relations with other cardiovascular parameters, the estimations based on ABP for other data have been accepted as useful methods as they had been verified with the statistical results among vast patient data. Previous windkessel models were composed with systemic resistance and vascular compliance and they were successful at explaining the average systolic and diastolic values of ABP simply. Although it is well-known that the blood pressure reflection from peripheral arteries causes complex inflection on ABP, previous models do not contain any elements of the reflections because of the complexity of peripheral arteries' shapes. In this study, to simulate a reflection wave of blood pressure, a new mathematical model was designed with four elements that were the impedance of aorta, the compliance of aortic arch, the peripheral resistance, and the compliance of peripheral arteries. The parameters of the new model were adjusted to have three types of arterial blood pressure waveform that were measured from a patient. It was used to find the relations between the inflections and other cardiovascular parameters such as the opening-closing time of aortic valve and the cardiac output. It showed that the blood pressure reflection can bring wide range errors to the closing time of aortic valve and cardiac output with the conventional estimation based on ABP and that the changes of one-stroke volumes can be easily detected with previous estimation while the changes of heart rate can bring some error caused by unexpected reflections.

• Journal of Positioning, Navigation, and Timing
• /
• v.6 no.4
• /
• pp.159-166
• /
• 2017

The position of autonomous driving vehicle is basically acquired through the global positioning system (GPS). However, GPS signals cannot be received in tunnels. Due to this limitation, localization of autonomous driving vehicles can be made through sensors mounted on them. In particular, a 3D Light Detection and Ranging (LIDAR) system is used for longitudinal position error correction. Few feature points and structures that can be used for localization of vehicles are available in tunnels. Since lanes in the road are normally marked by solid line, it cannot be used to recognize a longitudinal position. In addition, only a small number of structures that are separated from the tunnel walls such as sign boards or jet fans are available. Thus, it is necessary to extract usable information from tunnels to recognize a longitudinal position. In this paper, fire hydrants and evacuation guide lights attached at both sides of tunnel walls were used to recognize a longitudinal position. These structures have highly distinctive reflectivity from the surrounding walls, which can be distinguished using LIDAR reflectivity data. Furthermore, reflectivity information of tunnel walls was fused with the road surface reflectivity map to generate a synthetic reflectivity map. When the synthetic reflectivity map was used, localization of vehicles was able through correlation matching with the local maps generated from the current LIDAR data. The experiments were conducted at an expressway including Maseong Tunnel (approximately 1.5 km long). The experiment results showed that the root mean square (RMS) position errors in lateral and longitudinal directions were 0.19 m and 0.35 m, respectively, exhibiting precise localization accuracy.