• Geophysics and Geophysical Exploration
• /
• v.23 no.2
• /
• pp.97-114
• /
• 2020

Recently, many studies have been actively conducted on the application of machine learning in all branches of science and engineering. Studies applying machine learning are also rapidly increasing in all sectors of seismic exploration, including interpretation, processing, and acquisition. Among them, fault detection is a critical technology in seismic interpretation and also the most suitable area for applying machine learning. In this study, we introduced various machine learning techniques, described techniques suitable for fault detection, and discussed the reasons for their suitability. We collected papers published in renowned international journals and abstracts presented at international conferences, summarized the current status of the research by year and field, and intensively analyzed studies on fault detection using machine learning. Based on the type of input data and machine learning model, fault detection techniques were divided into seismic attribute-, image-, and raw data-based technologies; their pros and cons were also discussed.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.5
• /
• pp.83-93
• /
• 2013

Recently, the SURF algorithm, which is conjugated for object tracking system as part of many computer vision applications, is a well-known scale- and rotation-invariant feature detection algorithm. The SURF, due to its high computational complexity, there is essential to develop a hardware accelerator in order to be used on an IP in embedded environment. However, the SURF requires a huge local memory, causing many problems that increase the chip size and decrease the value of IP in ASIC and SoC system design. In this paper, we proposed a way to design a SURF algorithm in hardware with greatly reduced local memory by partitioning the algorithms into several Sub-IPs using external memory and a DMA. To justify validity of the proposed method, we developed an example of simplified object tracking algorithm. The execution speed of the hardware IP was about 31 frame/sec, the logic size was about 74Kgate in the 30nm technology with 81Kbytes local memory in the embedded system platform consisting of ARM Cortex-M0 processor, AMBA bus(AHB-lite and APB), DMA and a SDRAM controller. Hence, it can be used to the hardware IP of SoC Chip. If the image processing algorithm akin to SURF is applied to the method proposed in this paper, it is expected that it can implement an efficient hardware design for target application.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.10 no.6
• /
• pp.108-117
• /
• 2011

Seoul metropolitan government has been operating traffic signal control system with the name of COSMOS since 2001. COSMOS uses the degrees of saturation and congestion which are calculated by installing loop detectors. At present, inductive loop detector is generally used for detecting vehicles but it is inconvenient and costly for maintenance since it is buried on the road. In addition, the estimated queue length might be influenced in case of error occurred in measuring speed, because it only uses the speed of vehicles passing by the detector. A traffic signal control algorithm which enables smooth traffic flow at intersection is proposed. The proposed algorithm assigns vehicles to the group of each lane and calculates traffic volume and congestion degree using traffic information of each group using VANETs(Vehicular Ad-hoc Networks) inter-vehicle communication. It does not demand additional devices installation such as cameras, sensors or image processing units. In this paper, the algorithm we suggest is verified for AJWT(Average Junction Waiting Time) and TQL(Total Queue Length) under single intersection model based on GLD(Green Light District) Simulator. And the result is better than Random control method and Best first control method. In case real-time control method with VANETs is generalized, this research that suggests the technology of traffic control in signalized intersections using wireless communication will be highly useful.

• Journal of the Korean Society for Computer Game
• /
• v.31 no.4
• /
• pp.61-70
• /
• 2018

In this paper, we propose a synchronized playback method of 3D reference model and video by extracting golf swing information from learner's golf video to precisely compare and analyze each motion in each position and time in the golf swing, and present the implementation result. In order to synchronize the 3D model with the learner's swing video, the learner's golf swing movie is first photographed and relative time information is extracted from the photographed video according to the position of the golf club from the address posture to the finishing posture. Through applying time information from learners' swing video to a 3D reference model that rigs the motion information of a pro-golfer's captured swing motion at 120 frames per second through high-quality motion capture equipment into a 3D model and by synchronizing the 3D reference model with the learner's swing video, the learner can correct or learn his / her posture by precisely comparing his or her posture with the reference model at each position of the golf swing. Synchronized playback can be used to improve the functionality of manually adjusting system for comparing and analyzing the reference model and learner's golf swing. Except for the part where the image processing technology that detects each position of the golf posture is applied, It is expected that the method of automatically extracting the time information of each location from the video and of synchronized playback can be extended to general life sports field.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.409-418
• /
• 2021

Conformal coating is a technology that protects PCB(Printed Circuit Board) and minimizes PCB failures. Since the defects in the coating are linked to failure of the PCB, the coating surface is examined for air bubbles to satisfy the successful conditions of the conformal coating. In this paper, we propose an algorithm for detecting problematic bubbles in high-risk groups by applying image signal processing. The algorithm consists of finding candidates for problematic bubbles and verifying candidates. Bubbles do not appear in visible light images, but can be visually distinguished from UV(Ultra Violet) light sources. In particular the center of the problematic bubble is dark in brightness and the border is high in brightness. In the paper, these brightness characteristics are called valley and mountain features, and the areas where both characteristics appear at the same time are candidates for problematic bubbles. However, it is necessary to verify candidates because there may be candidates who are not bubbles. In the candidate verification phase, we used convolutional neural network models, and ResNet performed best compared to other models. The algorithms presented in this paper showed the performance of precision 0.805, recall 0.763, and f1-score 0.767, and these results show sufficient potential for bubble test automation.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.5
• /
• pp.34-41
• /
• 2021

Sidewalks are facilities used for the safe and comfortable passage of pedestrians and are paved with blocks of various materials. Currently, Korea does not have a quantitative survey method for the pavement condition of sidewalks, so it is necessary to develop an efficient survey method. Drones are being used as an efficient survey tool in various fields, but there are limited studies in which sidewalks have been investigated. This study investigates the possibility of detection by limiting the missing sidewalk blocks using a drone. This study is an initial study on the development of a method for detecting damage in sidewalk blocks. For this, sidewalk blocks were artificially removed to simulate a dropout situation, and images were acquired with 0.7-cm resolution using a drone. As a characteristic of the point cloud data acquired through image pre-processing, there was high variance of the elevation of the points in the missing area of the sidewalk block. Using these characteristics, an experiment was conducted to detect the missing parts of the sidewalk block by applying four thresholds to the variance of the elevation of points included in the grid corresponding to the sidewalk area. As a result, the detection accuracy was shown with a positive detection ratio of 70-80%, omission errors of 20-30%, and commission errors lower than 2%. It is judged that the possibility of detecting missing sidewalk blocks is high. This study focused on detecting a simulated missing sidewalk block in a limited environment. Therefore, it is expected that an efficient and quantitative method of detecting damaged sidewalk blocks can be developed in the future through additional research with considerations of the actual environment.

• Korean Journal of Remote Sensing
• /
• v.37 no.2
• /
• pp.233-243
• /
• 2021

Photovoltaic panels are hazardous electronic waste that has heavy metal as one of the hazardous components. Each year, hazardous electronic waste is increasing worldwide and every heavy rainfall exposes the photovoltaic panel to become the source of heavy metal soil contamination. the development needs a monitoring technology for this hazardous exposure. this research use relationships between SAR temporal baseline and coherence of Sentinel-1 satellite to detected photovoltaic panel. Also, the photovoltaic plant detection tested using the difference between that photovoltaic panel and the other difference surface of coherence. The author tested the photovoltaic panel and its environment to calculate differences in coherence relationships. As a result of the experiment, the coherence of the photovoltaic panel, which is assumed to be a permanent scatterer, shows a bias that is biased toward a median value of 0.53 with a distribution of 0.50 to 0.65. Therefore, further research is needed to improve errors that may occur during processing. Additionally, the author found that the change detection using a temporal baseline is possible as the rate of reduction of coherence of photovoltaic panels differs from those of artificial objects such as buildings. This result could be an efficient way to continuously monitor regardless of weather conditions, which was a limitation of the existing optical satellite image-based photovoltaic panel detection research and to understand the spatial distribution in situations such as photovoltaic panel loss.

• 재활복지
• /
• v.21 no.3
• /
• pp.129-146
• /
• 2017

In an event of an emergency, such as fire in a building, visually impaired and blind people are prone to exposed to a level of danger that is greater than that of normal people, for they cannot be aware of it quickly. Current fire detection methods such as smoke detector is very slow and unreliable because it usually uses chemical sensor based technology to detect fire particles. But by using vision sensor instead, fire can be proven to be detected much faster as we show in our experiments. Previous studies have applied various image processing and machine learning techniques to detect fire, but they usually don't work very well because these techniques require hand-crafted features that do not generalize well to various scenarios. But with the help of recent advancement in the field of deep learning, this research can be conducted to help solve this problem by using deep learning-based object detector that can detect fire using images from security camera. Deep learning based approach can learn features automatically so they can usually generalize well to various scenes. In order to ensure maximum capacity, we applied the latest technologies in the field of computer vision such as YOLO detector in order to solve this task. Considering the trade-off between recall vs. complexity, we introduced two convolutional neural networks with slightly different model's complexity to detect fire at different recall rate. Both models can detect fire at 99% average precision, but one model has 76% recall at 30 FPS while another has 61% recall at 50 FPS. We also compare our model memory consumption with each other and show our models robustness by testing on various real-world scenarios.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.6
• /
• pp.565-572
• /
• 2018

Recently, UAVs (Unmanned Aerial Vehicles) or drones have gained popularity for the engineering surveying and mapping because they enable the rapid data acquisition and processing as well as their operation cost is low. The applicable fields become much wider including the topographic monitoring, agriculture, and forestry. It is reported that the high geospatial accuracy is achievable with the drone photogrammetry for many applications. However most studies reported the best achievable mapping results using well-distributed ground control points though some studies investigated the impact of control points on the accuracy. In this study, we focused on the drone mapping of corridors such as roads and pipelines. The distribution and the number of control points along the corridor were diversified for the accuracy assessment. In addition, the effects of the camera self-calibration and the number of the image strips were also studied. The experimental results showed that the biased distribution of ground control points has more negative impact on the accuracy compared to the density of points. The prior camera calibration was favored than the on-the-fly self-calibration that may produce poor positional accuracy for the case of less or biased control points. In addition, increasing the number of strips along the corridor was not helpful to increase the positional accuracy.

• Journal of Biomedical Engineering Research
• /
• v.40 no.3
• /
• pp.105-115
• /
• 2019

Brain tumor surgery may be difficult, but it is also incredibly important. The technological improvements for traditional brain tumor surgeries have always been a focus to improve the precision of surgery and release the potential of the technology in this important area of the body. The need for precision during brain tumor surgery has led to an increase in Robotic-assisted surgeries (RAS). One of the challenges to the widespread acceptance of RAS in the neurosurgery is to recognize invisible tumor accurately. Therefore, it is important to detect brain tumor size and location because surgeon tries to remove as much tumor as possible. In this paper, we proposed brain tumor detection procedures for MRI (Magnetic Resonance Imaging) system. A method of automatic brain tumor detection is needed to accurately target the location of the lesion during brain tumor surgery and to report the location and size of the lesion. In the qualitative assessment, the proposed method showed better results than those obtained with other brain tumor detection methods. Comparisons among all assessment criteria indicated that the proposed method was significantly superior to the threshold method with respect to all assessment criteria. The proposed method was effective for detecting brain tumor.