• Smart Media Journal
• /
• v.10 no.3
• /
• pp.31-38
• /
• 2021

It is hard to predict when and where a fall accident will happen. Also, if rapid follow-up measures on it are not performed, a fall accident leads to a threat of life, so studies that can automatically detect a fall accident have become necessary. Among automatic fall-accident detection techniques, a fall detection scheme using an IMU (inertial measurement unit) sensor attached to a wrist is difficult to detect a fall accident due to its movement, but it is recognized as a technique that is easy to wear and has excellent accessibility. To overcome the difficulty in obtaining fall data, this study proposes an algorithm that efficiently learns less data through machine learning such as KNN (k-nearest neighbors) and SVM (support vector machine). In addition, to improve the performance of these mathematical classifiers, this study utilized feature data aquired in the frequency space. The proposed algorithm analyzed the effect by diversifying the parameters of the model and the parameters of the frequency feature extractor through experiments using standard datasets. The proposed algorithm could adequately cope with a realistic problem that fall data are difficult to obtain. Because it is lighter than other classifiers, this algorithm was also easy to implement in small embedded systems where SIMD (single instruction multiple data) processing devices were difficult to mount.

• Journal of Broadcast Engineering
• /
• v.24 no.3
• /
• pp.495-505
• /
• 2019

Typical algorithms of deep learning include CNN(Convolutional Neural Networks), which are mainly used for image recognition, and RNN(Recurrent Neural Networks), which are used mainly for speech recognition and natural language processing. Among them, CNN is able to learn from filters that generate feature maps with algorithms that automatically learn features from data, making it mainstream with excellent performance in image recognition. Since then, various algorithms such as R-CNN and others have appeared in object detection to improve performance of CNN, and algorithms such as YOLO(You Only Look Once) and SSD(Single Shot Multi-box Detector) have been proposed recently. However, since these deep learning-based detection algorithms determine the success of the detection in the still images, stable object tracking and detection in the video requires separate tracking capabilities. Therefore, this paper proposes a method of combining Kalman filters into deep learning-based detection networks for improved object tracking and detection performance in the video. The detection network used YOLO v2, which is capable of real-time processing, and the proposed method resulted in 7.7% IoU performance improvement over the existing YOLO v2 network and 20 fps processing speed in FHD images.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.6
• /
• pp.85-91
• /
• 2020

Recently, video-taping equipment such as CCTV have been seeing more use for crime prevention and general safety concerns. Since these video-taping equipment operates all throughout the day, the need for security personnel is lessened, and naturally costs incurred from managing such manpower should also decrease. However, technology currently used predominantly lacks self-sufficiency when given the task of searching for a specific object in the recorded video such as a person, and has to be done manually; current security-based video equipment is insufficient in an environment where real-time information retrieval is required. In this paper, we propose a technology that uses the latest deep-learning technology and OpenCV library to quickly search for a specific person in a video; the search is based on the clothing information that is inputted by the user and transmits the result in real time. We implemented our system to automatically recognize specific human objects in real time by using the YOLO library, whilst deep learning technology is used to classify human clothes into top/bottom clothes. Colors are also detected through the OpenCV library which are then all combined to identify the requested object. The system presented in this paper not only accurately and quickly recognizes a person object with a specific clothing, but also has a potential extensibility that can be used for other types of object recognition in a video surveillance system for various purposes.

• Journal of Korean Society of Forest Science
• /
• v.109 no.4
• /
• pp.484-491
• /
• 2020

In this study, to solve the existing inefficient stem analysis process and expensive equipment cost problems, a method for detecting and analyzing tree rings using smartphone images was proposed and a semi-automated computer program (TRIO, Tree Ring Information) was developed. TRIO can measure the annual ring radius and save the results to Excel. Since TRIO uses smartphone images, the results may vary depending on the quality of the smartphone camera. Therefore, using the Samsung Galaxy S10 and Tap 2, 30 dics images of Pinus rigida were acquired and analyzed, and these were compared with WinDENDROTM. As a result of the study, both Samsung Galaxy S10 and S2 showed significant results with WinDENDROTM, and the R2 value of S10 had a high correlation as 0.976, and RMSE was analyzed as 0.4199, and very similar results were output. The R2 value of S2 was 0.975 and the RMSE was 0.4232, showing no significant difference from S10. Accordingly, the TRIO developed in this study analyzed the annual radius value very similar to WinDENDROTM.

• Journal of the Korean Geosynthetics Society
• /
• v.19 no.4
• /
• pp.41-50
• /
• 2020

Since cracks in concrete structures expedite corrosion of reinforced concrete over a long period of time, regular on-site inspections are essential to ensure structural usability and prevent degradation. Most of the safety inspections of facilities rely on visual inspection with naked eye, so cost and time consuming are severe, and the reliability of results differs depending on the inspector. In this study, a portable measuring device that can be used for safety diagnosis and maintenance was developed as a device that measures the width and length of concrete cracks through image analysis of cracks photographed with a camera. This device captures the cracks found within a close distance (3 m), and accurately calculates the unit pixel size by laser distance measurement, and automatically calculates the crack length and width with the image processing algorithm developed in this study. In measurement results using the crack image applied to the experiment, the measurement of the length of a 0.3 mm crack within a distance of 3 m was possible with a range of about 10% error. The crack width showed a tendency to be overestimated by detecting surrounding pixels due to vibration and blurring effect during the binarization process, but it could be effectively corrected by applying the crack width reduction function.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.24 no.6
• /
• pp.77-84
• /
• 2020

In this paper, we developed a damage evaluation technique that can determine the damage location of a long-sized structure such as a cable-stayed bridge, and verified the performance of the developed technique through experiments. The damage assessment method aims to extract data that can evaluate the damage of the structure without the undamage data and can determine the damage location only by analyzing the response data of the structure. To complete this goal, we developed a damage assessment technique that considers variability based on the IMD theory, which is a statistical pattern recognition technique, to identify the damage location. To complete this goal, we developed a damage assessment technique that considers variability based on the IMD theory, which is a statistical pattern recognition technique, to identify the damage location. To evaluate the performance of the developed technique experimentally, cable damage experiments were conducted on model cable-stayed bridges. As a result, the damage assessment method considering variability automatically outputs the damageless data according to external force, and it is confirmed that the performance of extracting information that can determine the damage location of the cable through the analysis of the outputted damageless data and the measured damage data is shown.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.166-172
• /
• 2022

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

• Analytical Science and Technology
• /
• v.22 no.3
• /
• pp.210-218
• /
• 2009

A gas chromatography-tandem mass spectrometry (GC-MS/MS) method was developed and validated for simultaneous determination of amphetamine derivatives and norketamine in human hair. Preparation of hair involves external decontamination, mechanical pulverization, incubation and extraction prior to instrumental analysis. The samples were derivatized using heptafluorobutyric anhydride, and analyzed by GC-MS/MS. The linear ranges were 0.05-20.0 ng/mg for the analytes except for 3,4-methylenedioxyamphetamine, with good coefficients of determination ($r^2$ >0.998). The intra-day and inter-day precisions were within 10.7% and 8.5%, respectively. The intra-day and inter-day accuracies were between -1.6 and 17.0% and -2.6 and 10.5%, respectively. The limits of detections for each analyte were lower than 0.007 ng/mg, while recoveries were 75.9-100.9%. When the method was applied to hair samples obtained from suspected drug abusers, the concentrations in hair samples were 0.97-19.30 ng/mg for methamphetamine and 0.14-2.56 ng/mg for amphetamine.

• Analytical Science and Technology
• /
• v.21 no.1
• /
• pp.41-47
• /
• 2008

Although liquid-liquid extraction (LLE) method has been used routinely for the analysis of amphetamine-like drugs (amphetamine; AP, methamphetamine; MA, 3,4-methylenedioxyamphetamine; MDA, 3,4-methylenedioxymethamphetamine; MDMA, 3,4-methylenedioxyethylamphetamine; MDEA), a solid-phase extraction (SPE) method, which can be automated, was applied for the simultaneous determination by GC/MS in human urine. Urine samples (3 mL) and 0.1 M phosphate buffer (1 mL, pH 7.0) were extracted by an automated SPE system. The eluent was evaporated, derivatized with trifluoroacetic anhydride (TFAA), and analyzed by GC/MS. The calibration curves was linear with correlation coefficient ($r^2$) above 0.994 in the ranges of 34.0 (AP), 28.0 (MDA)~1000.0 ng/mL for AP, MDA, and 50.0~2000.0 ng/mL for MA, MDMA, and MDEA. The limits of detection ranged from 4.0 to 10.0 ng/mL, and the limits of quantitation ranged from 12.0 to 34.0 ng/mL. The relative recoveries were 93.5~107.7 %. The precisions and accuracies were 1.9~14.8 % and -8.7~14.8 %, respectively. The present method was successfully applied to identify the MA or Ecstasy (MDMA) abusers in exact as well as rapid.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.4D
• /
• pp.687-693
• /
• 2006

Image co-registration is the process of overlaying two images of the same scene, one of which represents a reference image, while the other is geometrically transformed to the one. In order to improve efficiency and effectiveness of the co-registration approach, the author proposed a pre-qualified area matching algorithm which is composed of feature extraction with canny operator and area matching algorithm with cross correlation coefficient. For refining matching points, outlier detection using studentized residual was used and iteratively removes outliers at the level of three standard deviation. Throughout the pre-qualification and the refining processes, the computation time was significantly improved and the registration accuracy is enhanced. A prototype of the proposed algorithm was implemented and the performance test of 3 Landsat images of Korea. showed: (1) average RMSE error of the approach was 0.435 pixel; (2) the average number of matching points was over 25,573; (3) the average processing time was 4.2 min per image with a regular workstation equipped with a 3 GHz Intel Pentium 4 CPU and 1 Gbytes Ram. The proposed approach achieved robustness, full automation, and time efficiency.