• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.980-997
• /
• 2024

To improve the brightness of images and reveal hidden information in dark areas is the main objective of low-light image enhancement (LLIE). LLIE methods based on deep learning show good performance. However, there are some limitations to these methods, such as the complex network model requires highly configurable environments, and deficient enhancement of edge details leads to blurring of the target content. Single-scale feature extraction results in the insufficient recovery of the hidden content of the enhanced images. This paper proposed an edge detection-based multi-scale feature enhancement network for LLIE (EDMFEN). To reduce the loss of edge details in the enhanced images, an edge extraction module consisting of a Sobel operator is introduced to obtain edge information by computing gradients of images. In addition, a multi-scale feature enhancement module (MSFEM) consisting of multi-scale feature extraction block (MSFEB) and a spatial attention mechanism is proposed to thoroughly recover the hidden content of the enhanced images and obtain richer features. Since the fused features may contain some useless information, the MSFEB is introduced so as to obtain the image features with different perceptual fields. To use the multi-scale features more effectively, a spatial attention mechanism module is used to retain the key features and improve the model performance after fusing multi-scale features. Experimental results on two datasets and five baseline datasets show that EDMFEN has good performance when compared with the stateof-the-art LLIE methods.

• Journal of Environmental Health Sciences
• /
• v.38 no.3
• /
• pp.269-276
• /
• 2012

Objectives: The purpose of this study was to provide policy directions for air pollution reduction by analyzing the variation in the characteristics of air contaminants around the Gyeonggi Province area. Methods: The data used in the study was obtained from air quality monitoring stations operated by the Gyeonggi Provincial Government. The target area was the air quality management area of the Gyeonggi Province region. Results: The concentration of $PM_{10}$ (particles measuring $10{\mu}m$ or less) in 2009 was $60{\mu}g/m^3$, which has been reduced by about 2.7% per year after improvement countermeasures were emplaced. The air pollution control policy was especially more effective for coarse particulate matter (CPM, $PM_{10-2.5}$). The improvement of $NO_2$ pollution was generally very low, especially in cities which had considerable automobile traffic. The concentration of $SO_2$ pollution was rapidly improved in industrial areas, but did not show any difference for multiple and general cities. The predicted concentration of $PM_{10}$ for 2014 based on the trend over 2001-2009 was $53.4{\mu}g/m^3$, which fails to meet the target concentration of $40{\mu}g/m^3$. The predicted concentration of $NO_2$ shows a very low probability of achieving the target concentration of 22 ppb, and thus the current improvement of air quality has proven unsatisfactory. Conclusion: Air pollution control policy should be enforced according to regional pollution characteristics in order to obtain maximum effectiveness in improvement.

• Journal of the Korean Institute of Rural Architecture
• /
• v.20 no.1
• /
• pp.11-18
• /
• 2018

The study aims to address the energy crisis and realize self-sufficiency of building as part of local energy independence, breaking away from a single concentrated energy supply system. It is intended to develop modules of the outside insulation composite panels that conform to passive certification criteria and for site-assembly systematization. The method of study first identifies trends and passive house in literature and advanced research. Second, the target performance for development is set, and the structural material is selected and designed to simulate performance. Third, a test specimen of the passive outside insulation curtain wall module designed is manufactured and constructed to test its heat transmission coefficient, condensation performance and airtightness. Finally, analyze performance test results, and explore and propose ways to improve the estimation and improvement of incomplete causes to achieve the goal. The final test results achieved the target performance of condensation and airtightness, and the heat transmission coefficient was $0.16W/(m^2{\cdot}K)$, which is $0.01W/(m^2{\cdot})K$ below the performance target. As for the lack of performance, we saw a need for a complementary design to account for simulation errors. It also provided an opportunity to recognize that insulated walls with performance can impact performance at small break. Thus, to be commercialized into a product with the need for improvement in the design of the joint parts, a management system is needed to increase the precision in the fabrication process.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.19 no.3
• /
• pp.294-303
• /
• 2008

ISAR(Inverse Synthetic Aperture Radar) images represent the 2-D(two-dimensional) spatial distribution of RCS (Radar Cross Section) of an object, and they can be applied to the problem of target identification. A traditional approach to ISAR imaging is to use a 2-D IFFT(Inverse Fast Fourier Transform). However, the 2-D IFFT results in low resolution ISAR images especially when the measured frequency bandwidth and angular region are limited. In order to improve the resolution capability of the Fourier transform, various high-resolution spectral estimation approaches have been applied to obtain ISAR images, such as AR(Auto Regressive), MUSIC(Multiple Signal Classification) or Modified MUSIC algorithms. In this study, these high-resolution spectral estimators as well as 2-D IFFT approach are combined with a recently developed ISAR image classification algorithm, and their performances are carefully analyzed and compared in the framework of radar target recognition.

• Journal of KIISE
• /
• v.45 no.3
• /
• pp.211-223
• /
• 2018

In this paper, we propose a robot-centered direction relation representation and the relevant reasoning methods for indoor service robots. Many conventional works on qualitative spatial reasoning, when deciding the relative direction relation of the target object, are based on the use of position information only. These reasoning methods may infer an incorrect direction relation of the target object relative to the robot, since they do not take into consideration the heading direction of the robot itself as the base object. In this paper, we present a robot-centered direction relation representation and the reasoning methods. When deciding the relative directional relationship of target objects based on the robot in an indoor environment, the proposed methods make use of the orientation information as well as the position information of the robot. The robot-centered reasoning methods are implemented by extending the existing cone-based, matrix-based, and hybrid methods which utilized only the position information of two objects. In various experiments with both the physical Turtlebot and the simulated one, the proposed representation and reasoning methods displayed their high performance and applicability.

• Journal of Korean Society for Geospatial Information Science
• /
• v.16 no.1
• /
• pp.13-21
• /
• 2008

This study conducted water quality projection of year 2010 in Miho stream of the Geum river basin by using GIS. Pollutant load data of corresponding tributary of the Miho stream is estimated based on the pollutant load of TMDL zone to simulate water quality of the Miho stream for BOD, TN, and TP. The pollutant load of the urban area such as Bochung and Musim stream basin is relatively high and the wastewater treatment plant of Chunju city directly affects the entire water quality of the target area. As a result, simulation result reveals that water treatment facility needs more refined treatment process for efficient water quality management. Also, to meet the target water quality of the Miho stream water quality simulation estimates the additional dilution flow by increasing irrigation water supplied from the Daechung dam through the Musim stream.

• Journal of Broadcast Engineering
• /
• v.15 no.2
• /
• pp.236-247
• /
• 2010

Recently, mean shift tracking algorithms have been proposed which use the information of color histogram together with some spatial information provided by the kernel. In spite of their fast speed, the algorithms are suffer from an inherent instability problem which is due to the use of an isotropic kernel for spatiality and the use of the Bhattacharyya coefficient as a similarity function. In this paper, we analyze how the kernel and the Bhattacharyya coefficient can arouse the instability problem. Based on the analysis, we propose a novel tracking scheme that uses a new representation of the location of the target which is constrained by the color, the area, and the spatiality information of the target in a more stable way than the mean shift algorithm. With this representation, the target localization in the next frame can be achieved by one step computation, which makes the tracking stable, even in difficult situations such as low-rate-frame environment, and partial occlusion.

• Journal of Korean Society for Geospatial Information Science
• /
• v.16 no.2
• /
• pp.87-95
• /
• 2008

Ladar (Laser Detection And Ranging, Lidar) is a sensor to acquire precise distances to the surfaces of target region using laser signals, which can be suitably applied to ATD (Automatic Target Detection) for guided missiles or aerial vehicles recently. It provides a range image in which each measured distance is expressed as the brightness of the corresponding pixel. Since the precise 3D models can be generated from the Ladar range image, more robust identification and recognition of the targets can be possible. If we simulate the data of Ladar sensor, we can efficiently use this simulator to design and develop Ladar sensors and systems and to develop the data processing algorithm. The purposes of this study are thus to simulate the signals of a Ladar sensor based on linear frequency modulation and to create range images from the simulated Ladar signals. We first simulated the laser signals of a Ladar using FM chirp modulator and then computed the distances from the sensor to a target using the FFT process of the simulated signals. Finally, we created the range image using the distances set.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.34 no.6
• /
• pp.705-712
• /
• 2001

It is of great importance to represent the directional ocean waves in a laboratory basin for hydraulic model tests. The directional ocean waves can be expressed as a linear superposition of a large number of component waves with different frequencies and propagating directions. The aim of the study is to check the wave generating characteristics by serpent-type wave generating system in PKNU (Pukyong National University) which is composed of 10 piston-type wave generators. In the experiment, spatial variation of irregular wave heights and propagating angles are measured in the multi-directional wave maker basin. Target wave directional spectrum is reproduced in the area of multi-directional wave maker basin. The directional spreading of the generated waves varied spacially in the basin. They differed from target spectrum as the measurement point becomes far from the center line normal to the generator face, The effective generation area where that target can be reproduced is limited to the triangular area attached the generator face. According to the results, it is emphasized that the effective experiment area in the basin considered wave generator characteristics should be determined in consideration of experimental conditions including structural shapes, water depth, wave directionality etc.

• Journal of Environmental Science International
• /
• v.19 no.7
• /
• pp.861-869
• /
• 2010

The present study aims to evaluate the characteristics of atmospheric polycyclic aromatic hydrocarbons (PAHs) pollution in roadside and residential areas of two Korean metropolitan cities (Seoul and Incheon) and a background area (Seokmolee). This purpose was established by analyzing temporal and spacial concentration distribution of total and 7 individual PAHs, which were extracted from ambient particulate matters, and by utilizing a multivariate statistical method (principal component analysis, PCA) for the qualitative determination of potential PAH sources. Target PAHs included benzo(a)anthracene (BaA), benzo(a)pyrene (BaP), benzo(b)fluoranthene (BbF), benzo(k)fluoranthene (BkF), chrysene (Chr), dibenzo(a,h)anthracene (DahA), and indeno(1,2,3-cd)pyrene (IcdP). For all surveyed sites, the concentrations of total PAHs were higher in winter season than in other seasons. However, the concentrations of individual PAHs varied with surveyed sites. In both residential and roadside sites of Seoul and Incheon, BbF revealed the highest atmospheric levels. For all 7 target PAHs, the ambient concentrations were higher in Seoul and Incheon than in a background area (Seokmolee). In both residential and roadside areas, the concentrations of 4 target PAHs (BaA, BbF, BkF, DahA) were higher in Incheon than in Seoul. However, both the residential and roadside Chr concentrations were comparable in Seoul and Incheon. In addition, the residential IcdP concentrations were higher in Incheon than in Seoul, whereas the roadside concentrations were higher in Seoul. The roadside and residential BaP concentrations exhibited the reverse result to the IcdP concentrations. An PCA analysis suggested that atmospheric PAHs in both residential and roadside areas would be due to combined effects of several potential sources such as gasoline- and diesel-fueled vehicles, coal/oil combustion, and waste incineration.