• Journal of the Korean Society of Safety
• /
• v.36 no.1
• /
• pp.18-25
• /
• 2021

In many developed countries, such as South Korea, efficiently maintaining the aging infrastructures is an important issue. Currently, inspectors visually inspect the infrastructure for maintenance needs, but this method is inefficient due to its high costs, long logistic times, and hazards to the inspectors. Thus, in this paper, a novel crack inspection approach for concrete bridges is proposed using integrated image processing techniques. The proposed approach consists of four steps: (1) training a deep learning model to automatically detect cracks on concrete bridges, (2) acquiring in-situ images using a drone, (3) generating orthomosaic images based on 3D modeling, and (4) detecting cracks on the orthmosaic image using the trained deep learning model. Cascade Mask R-CNN, a state-of-the-art instance segmentation deep learning model, was trained with 3235 crack images that included 2415 hard negative images. We selected the Tancheon overpass, located in Seoul, South Korea, as a testbed for the proposed approach, and we captured images of pier 34-37 and slab 34-36 using a commercial drone. Agisoft Metashape was utilized as a 3D model generation program to generate an orthomosaic of the captured images. We applied the proposed approach to four orthomosaic images that displayed the front, back, left, and right sides of pier 37. Using pixel-level precision referencing visual inspection of the captured images, we evaluated the trained Cascade Mask R-CNN's crack detection performance. At the coping of the front side of pier 37, the model obtained its best precision: 94.34%. It achieved an average precision of 72.93% for the orthomosaics of the four sides of the pier. The test results show that this proposed approach for crack detection can be a suitable alternative to the conventional visual inspection method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.11
• /
• pp.1507-1518
• /
• 2020

High-quality images have a lot of information, so sensitive data is stored by encryption for private company, military etc. Encrypted images can only be decrypted with a secret key, but the original data cannot be retained when attacked by the Shear attack and Noise pollution attack techniques that overwrite some pixel data with arbitrary values. Important data is the more necessary a countermeasure for the recovery method against attack. In this paper, we propose a random number generator PingPong256 and a shuffling method that rearranges pixels to resist Shear attack and Noise pollution attack techniques so that image and video encryption can be performed more quickly. Next, the proposed PingPong256 was examined with SP800-22, tested for immunity to various noises, and verified whether the image to which the shuffling method was applied satisfies the Anti-shear attack and the Anti-noise pollution attack.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.4
• /
• pp.591-597
• /
• 2022

Recently, many studies have been done on the data augmentation technique as a way to efficiently build datasets. Among them, a representative data augmentation technique is a method of utilizing Generative Adversarial Network (GAN), which generates data similar to real data by competitively learning generators and discriminators. However, when learning GAN, there are cases where a broken pixel image occurs among similar data generated according to the environment and progress, which cannot be used as a dataset and causes an increase in learning time. In this paper, an algorithm was developed to select these damaged images by analyzing the histogram of image data generated during the GAN learning process, and as a result of comparing them with the images generated in the existing GAN, the ratio of the damaged images was reduced by 33.3 times(3,330%).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.2
• /
• pp.542-558
• /
• 2023

A digital focus index (DFI) is a value used to determine image focus in scientific apparatus and smart devices. Automatic focus (AF) is an iterative and time-consuming procedure; however, its processing time can be reduced using a general processing unit (GPU) and a multi-core processor (MCP). In this study, parallel architectures of a minimax search algorithm (MSA) are applied to two DFIs: range algorithm (RA) and image contrast (CT). The DFIs are based on a histogram; however, the parallel computation of the histogram is conventionally inefficient because of the bank conflict in shared memory. The parallel architectures of RA and CT are constructed using parallel reduction for MSA, which is performed through parallel relative rating of the image pixel pairs and halved the rating in every step. The array size is then decreased to one, and the minimax is determined at the final reduction. Kernels for the architectures are constructed using open source software to make it relatively platform independent. The kernels are tested in a hexa-core PC and an embedded device using Lenna images of various sizes based on the resolutions of industrial cameras. The performance of the kernels for the DFIs was investigated in terms of processing speed and computational acceleration; the maximum acceleration was 32.6× in the best case and the MCP exhibited a higher performance.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.12
• /
• pp.63-73
• /
• 2009

This paper presents a vehicle detection method that uses convolution matching method based on a simple color information. An input image is expressed as 8 oriented color expression(Red, Green, Blue, White, Black, Cyan, Yellow, Magenta) considering an orientation of a pixel color vector. It makes the image very reliable and strong against changes of illumination condition or environment. This paper divides the vehicle detection into a hypothesis generation step and a hypothesis verification step. In the hypothesis generation step, the vehicle candidate region is found by vertical edge and shadow. In the hypothesis verification step, the convolution matching and the complexity of image edge are used to detect real vehicles. It is proved that the proposed method has the fast and high detection rate on various experiments where the illumination source and environment are changed.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.136-136
• /
• 2021

In this study, a deep convolutional neural network (DCNN) model is proposed for short-term precipitation forecasting using weather radar-based images. The DCNN model is a combination of convolutional neural networks, autoencoder neural networks, and U-net architecture. The weather radar-based image data used here are retrieved from competition for rainfall forecasting in Korea (AI Contest for Rainfall Prediction of Hydroelectric Dam Using Public Data), organized by Dacon under the sponsorship of the Korean Water Resources Association in October 2020. This data is collected from rainy events during the rainy season (April - October) from 2010 to 2017. These images have undergone a preprocessing step to convert from weather radar data to grayscale image data before they are exploited for the competition. Accordingly, each of these gray images covers a spatial dimension of 120×120 pixels and has a corresponding temporal resolution of 10 minutes. Here, each pixel corresponds to a grid of size 4km×4km. The DCNN model is designed in this study to provide 10-minute predictive images in advance. Then, precipitation information can be obtained from these forecast images through empirical conversion formulas. Model performance is assessed by comparing the Score index, which is defined based on the ratio of MAE (mean absolute error) to CSI (critical success index) values. The competition results have demonstrated the impressive performance of the DCNN model, where the Score value is 0.530 compared to the best value from the competition of 0.500, ranking 16^th out of 463 participating teams. This study's findings exhibit the potential of applying the DCNN model to short-term rainfall prediction using weather radar-based images. As a result, this model can be applied to other areas with different spatiotemporal resolutions.

• Journal of Radiation Protection and Research
• /
• v.47 no.4
• /
• pp.214-225
• /
• 2022

Background: The conventional cerium-doped Gd₂Al₂Ga₃O₁₂ (GAGG(Ce)) scintillator-based gamma-ray imager has a bulky detector, which can lead to incorrect positioning of the gammaray source if the shielding against background radiation is not appropriately designed. In addition, portability is important in complex environments such as inside nuclear power plants, yet existing gamma-ray imager based on a tungsten mask tends to be weighty and therefore difficult to handle. Motivated by the need to develop a system that is not sensitive to background radiation and is portable, we changed the material of the scintillator and the coded aperture. Materials and Methods: The existing GAGG(Ce) was replaced with Bi₄Ge₃O₁₂ (BGO), a scintillator with high gamma-ray detection efficiency but low energy resolution, and replaced the tungsten (W) used in the existing coded aperture with lead (Pb). Each BGO scintillator is pixelated with 144 elements (12 × 12), and each pixel has an area of 4 mm × 4 mm and the scintillator thickness ranges from 5 to 20 mm (5, 10, and 20 mm). A coded aperture consisting of Pb with a thickness of 20 mm was applied to the BGO scintillators of all thicknesses. Results and Discussion: Spectroscopic characterization, imaging performance, and image quality evaluation revealed the 10 mm-thick BGO scintillators enabled the portable gamma-ray imager to deliver optimal performance. Although its performance is slightly inferior to that of existing GAGG(Ce)-based gamma-ray imager, the results confirmed that the manufacturing cost and the system's overall weight can be reduced. Conclusion: Despite the spectral characteristics, imaging system performance, and image quality is slightly lower than that of GAGG(Ce), the results show that BGO scintillators are preferable for gamma-ray imaging systems in terms of cost and ease of deployment, and the proposed design is well worth applying to systems intended for use in areas that do not require high precision.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.139-141
• /
• 2022

As interest in digital video media and intelligent systems increases rapidly, technologies using video information are being combined and used in various fields such as security and artificial intelligence. Impulse noise generated during digital image processing degrades the image quality of the image and reduces the reliability of information, so it is necessary to remove it through a filter. There are SMF, AWMF, and MDBUTMF as well-known antecedent methods, but they all have limitations in achieving seamless filtering in environments with large loss of information on valid pixels due to problems with the algorithm itself. Therefore, this paper designs a median filter algorithm that applies weights reflecting the reliability of the information by searching for the nearest effective pixels present within the mask. For performance evaluation, this algorithm and the preceding algorithm were compared and analyzed using PSNR and enlarged images.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1763-1770
• /
• 2023

The availability of high-resolution satellite image time series data has led to an increase in change detection research. Various methods are being studied, such as satellite image pixel and object-level change detection algorithms, as well as algorithms that apply deep learning technology. In this paper, we propose a QGIS plugin-based system to enhance the utilization of these useful results and present an actual implementation case. The proposed system is a system for intensive change detection and monitoring of areas of interest, and we propose a convenient system expansion method for algorithms to be developed in the future. Furthermore, it is expected to contribute to the construction of satellite image utilization systems by presenting the basic structure of commercialization of change detection research.

• Journal of Astronomy and Space Sciences
• /
• v.40 no.4
• /
• pp.173-197
• /
• 2023

ShadowCam is a high-sensitivity, high-resolution imager provided by NASA for the Danuri (KPLO) lunar mission. ShadowCam calibration shows that it is well suited for its purpose, to image permanently shadowed regions (PSRs) that occur near the lunar poles. It is 205 times as sensitive as the Lunar Reconnaissance Orbiter Camera (LROC) Narrow Angle Camera (NAC). The signal to noise ratio (SNR) is greater than 100 over a large part of the dynamic range, and the top of the dynamic range is high enough to accommodate most brighter PSR pixels. The optical performance is good enough to take full advantage of the 1.7 meter/pixel image scale, and calibrated images have uniform response. We describe some instrument artifacts that are amenable to future corrections, making it possible to improve performance further. Stray light control is very challenging for this mission. In many cases, ShadowCam can image shadowed areas with directly illuminated terrain in or near the field of view (FOV). We include thorough qualitative descriptions of circumstances under which lunar brightness levels far higher than the top of the dynamic range cause detector or stray light artifacts and the size and extent of the artifact signal under those circumstances.