• Journal of Korea Multimedia Society
• /
• v.20 no.12
• /
• pp.1901-1912
• /
• 2017

Traffic lights at night are usually framed in the image as bright regions bigger than the real size due to glow effect. Moreover, the colors of lighting region saturate to white. So it is difficult to distinguish between different traffic lights at night. Many related studies have tried to decrease the glow effect in the process of capturing images. Some studies drastically decreased the shutter time of the camera to reduce the adverse effect by the glow. However, this makes the video too dark. This study proposes a new idea which utilizes the glow effect. It examines the outer radial region of traffic light. It presents an algorithm to discriminate the color of traffic light by the analysis of the outer radial region. The advantage of the proposed method is that it can recognize traffic lights in the image captured by an ordinary black box camera. Experimental results using seven short videos show the performance of traffic light recognition reporting the precision of 96.4% and the recall of 98.2%. These results show that the proposed method is valid and effective.

• Korean Institute of Interior Design Journal
• /
• v.25 no.4
• /
• pp.135-146
• /
• 2016

The purpose of this study is to analyze the correlation between fashion brand image and store space image. To investigate this study further, one of the luxury fashion brands was selected for a case study and surveys were conducted to 200 participants. This study evaluates the factors of fashion brand images that customers associate with a brand before stepping inside the flagship store. Also it analyzes the factors of store space image after the experience of the flagship store. As a result of the correlation analysis based on quantitative statistic measures, the fashion brand image and store space image coincided highest with extraordinary, young and strong characteristics. According to the space elements of the flagship store, the relationship of the brand image with the store image was investigated. As a result of analysis, customers felt the high correlation with the facade among the architectural elements of flagship store. This resulted in that customers consider that the black box of the facade represents originality of this fashion brand as a concept of spatial elements. As a practical implication, companies should understand that the architectural design is a very crucial component in designing the flagship store, as it gives customers their first impression about a brand. The brand image is required to be integrated through the exterior design of the store. The final conclusion of this study shows that the flagship store provides a space where you can experience the corporate value and brand through the space of brand experience and share an emotional image created by the brand as well.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.1
• /
• pp.142-152
• /
• 2016

GPS is not able to be used for indoor positioning and currently most of techniques emerging to overcome the limit of GPS utilize private wireless networks. However, these methods require high costs for installation and maintenance, and they are inappropriate to be used in the place where precise positioning is needed as in indoor parking lots. This paper proposes a vehicular indoor positioning method based on QR-code recognition. The method gets an absolute coordinate through QR-code scanning, and obtain the location (an relative coordinate) of a black-box camera using the tilt and roll angle correction through affine transformation, scale transformation, and trigonometric function. Using these information of an absolute coordinate and an relative one, the precise position of a car is estimated. As a result, average error of 13.79cm is achieved and it corresponds to just 27.6% error rate in contrast to 50cm error of the recent technique based on wireless networks.

• The Journal of Engineering Geology
• /
• v.32 no.1
• /
• pp.101-111
• /
• 2022

This study analyzed the relationship between water turbidity and its reflectance, as measured using hyperspectral imaging. First, samples of turbid water were generated in boxes. This was followed by drone-based hyperspectral imaging and analysis of the correlation between the samples' measured turbidity and hyperspectral reflectance. The nine boxes for turbidity measurement were made of black acrylic that absorbed all light turbidity was induced using soil collected near Changhacheon, which causes turbidity in Imha Lake. The results indicate that the reflectance of wavelengths in the near-infrared region followed a pattern of increase with increasing soil content for each box. Analysis of this correlation between the turbidity and average reflectance measured in each box yielded a very high R² value of 0.8702, indicating that reflectance is a suitable proxy for turbidity.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.2
• /
• pp.256-264
• /
• 2024

In the last 10 years, AI has made rapid progress, and image classification, in particular, are showing excellent performance based on deep learning. Nevertheless, due to the nature of deep learning represented by a black box, it is difficult to actually use it in critical decision-making situations such as national defense, autonomous driving, medical care, and finance due to the lack of explainability of judgement results. In order to overcome these limitations, in this study, a model description algorithm capable of local interpretation was applied to the inception network-derived AI to analyze what grounds they made when classifying national defense data. Specifically, we conduct a comparative analysis of explainability based on confidence values by performing LIME analysis from the Inception v2_resnet model and verify the similarity between human interpretations and LIME explanations. Furthermore, by comparing the LIME explanation results through the Top1 output results for Inception v3, Inception v2_resnet, and Xception models, we confirm the feasibility of comparing the efficiency and availability of deep learning networks using XAI.

• Journal of radiological science and technology
• /
• v.45 no.2
• /
• pp.145-150
• /
• 2022

The main purpose of this work was to restore the blurry chest CT images by applying a blind deconvolution algorithm. In general, image restoration is the procedure of improving the degraded image to get the true or original image. In this regard, we focused on a blind deblurring approach with chest CT imaging by using digital image processing in MATLAB, which the blind deconvolution technique performed without any whole knowledge or information as to the fundamental point spread function (PSF). For our approach, we acquired 30 chest CT images from the public source and applied three type's PSFs for finding the true image and the original PSF. The observed image might be convolved with an isotropic gaussian PSF or motion blurring PSF and the original image. The PSFs are assumed as a black box, hence restoring the image is called blind deconvolution. For the 30 iteration times, we analyzed diverse sizes of the PSF and tried to approximate the true PSF and the original image. For improving the ringing effect, we employed the weighted function by using the sobel filter. The results was compared with the three criteria including mean squared error (MSE), root mean squared error (RMSE) and peak signal-to-noise ratio (PSNR), which all values of the optimal-sized image outperformed those that the other reconstructed two-sized images. Therefore, we improved the blurring chest CT image by using the blind deconvolutin algorithm for optimal approach.

• Journal of information and communication convergence engineering
• /
• v.15 no.3
• /
• pp.187-192
• /
• 2017

Autonomous driving vehicle research demands complex road and lane understanding such as lane departure warning, adaptive cruise control, lane keeping and centering, lane change and turn assist, and driving under complex road conditions. A fast and robust road lane detection subsystem is a basic but important building block for this type of research. In this paper, we propose a method that performs road lane detection from black box input. The proposed system applies Random Sample Consensus to find the best model of road lanes passing through divided regions of the input image under HSV color model. HSV color model is chosen since it explicitly separates chromaticity and luminosity and the narrower hue distribution greatly assists in later segmentation of the frames by limiting color saturation. The implemented method was successful in lane detection on real world on-board testing, exhibiting 86.21% accuracy with 4.3% standard deviation in real time.

• Korean Journal of Crystallography
• /
• v.11 no.4
• /
• pp.231-237
• /
• 2000

CMR Materials RE/sub 1-x/Ca/sub x/MnO₃(RE=La, Nd, A=Ca, Sr) were grown using the floating zone image furnace with halogen lamps as heat source. The growth condition was at 2∼10 mm/hr growth rate in air atmosphere, were 445∼50 rpm and 20∼25 rpm of rotation rate of feedrod and growing crystal, respectively. The grown crystals showed shiny black color and annealed at 1500℃ in a box furnace to release the residual stress during cooling. Characterization analyses of the crystal were carried out using XRD and SEM. The crystal structure of Nd/sub 0.7/Ca/sub 0.3/MnO₃ was analyzed with smart CCD XRD was lattice parameter of a=5.425(4)Å, b=5.434(4)Å, and c=7.712(5)Å, an orthorombic system with space group of pbnm.

• Journal of Korea Multimedia Society
• /
• v.18 no.3
• /
• pp.339-348
• /
• 2015

In this paper, we propose improved night visibility enhancement algorithm based on haze removal method. The proposed method uses new haze removal method in place of the conventional methods. Our night visibility enhancement method is very good and faster than traditional methods. This method also uses additionally local histogram equalization for sharpening the enhanced image. Our method can be applied to any application that uses a visible light camera, and it is appropriate to apply a black box, vehicle camera, and cell phone camera, since it is possible that real-time processing.

• Journal of the Optical Society of Korea
• /
• v.19 no.5
• /
• pp.531-536
• /
• 2015

This paper presents a new graphical method for selecting a pair of optical glass and housing materials to simultaneously achromatize and athermalize a multilens system composed of many elements. To take into account the lens spacing and housing, we quantify the lens power, chromatic power, and thermal power by weighting the ratio of the paraxial ray height at each lens to them. In addition, we introduce the equivalent single lens and the expanded athermal glass map including a housing material. Even though a lens system is composed of many elements, we can simply identify a pair of glass and housing materials that satisfies the athermal and achromatic conditions. Applying this method to design a black box camera lens equipped with a 1/4-inch image sensor having a pixel width of $2{\mu}m$, the chromatic and thermal defocusings are reduced to less than the depth of focus, over the specified ranges in temperature and frequency.