• The Journal of the Convergence on Culture Technology
• /
• v.7 no.3
• /
• pp.577-582
• /
• 2021

Recently, with the development of AR, VR, and smart device technologies, the demand for services based on non-face-to-face environments is also increasing in the fitness industry. The non-face-to-face online home training service has the advantage of not being limited by time and place compared to the existing offline service. However, there are disadvantages including the absence of exercise equipment, difficulty in measuring the amount of exercise and chekcing whether the user maintains an accurate exercise posture or not. In this study, we develop a standard exercise program that can compensate for these shortcomings and propose a new non-face-to-face home training application by using a deep learning-based body posture estimation image processing algorithm. This application allows the user to directly watch and follow the trainer of the standard exercise program video, correct the user's own posture, and perform an accurate exercise. Furthermore, if the results of this study are customized according to their purpose, it will be possible to apply them to performances, films, club activities, and conferences

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.4
• /
• pp.184-193
• /
• 2021

The system for managing spatial data updates the existing information by extracting only the information that is different from the existing information for the newly obtained spatial information file to update the stored information. In order to extract only objects that have changed from existing information, it is necessary to compare whether there is any difference from existing information for all objects included in the newly obtained spatial information file. This study was conducted to improve this total inspection method in a situation where the amount of spatial information that is frequently updated increases and data update is required at the national level. In this study, before inspecting individual objects in a new acquisition space information file, a method of determining whether individual space objects have been changed only by the information in the file was considered. Spatial data files have structured data characteristics different from general image or text document files, so it is possible to determine whether to change the file unit in a simpler way compared to the existing method of creating and managing file hash. By reducing the number of target files that require full inspection, it is expected to improve the use of resources in the system by saving the overall data quality inspection time and saving data extraction time.

• Korean Journal of Remote Sensing
• /
• v.38 no.3
• /
• pp.237-250
• /
• 2022

In this study, we propose a method to estimate the biomass of invertebrate grazers from the videos with underwater drones by using a multi-object tracking model based on deep learning. In order to detect invertebrate grazers by classes, we used YOLOv5 (You Only Look Once version 5). For biomass estimation we used DeepSORT (Deep Simple Online and real-time tracking). The performance of each model was evaluated on a workstation with a GPU accelerator. YOLOv5 averaged 0.9 or more mean Average Precision (mAP), and we confirmed it shows about 59 fps at 4 k resolution when using YOLOv5s model and DeepSORT algorithm. Applying the proposed method in the field, there was a tendency to be overestimated by about 28%, but it was confirmed that the level of error was low compared to the biomass estimation using object detection model only. A follow-up study is needed to improve the accuracy for the cases where frame images go out of focus continuously or underwater drones turn rapidly. However,should these issues be improved, it can be utilized in the production of decision support data in the field of invertebrate grazers control and monitoring in the future.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1527-1539
• /
• 2022

As coastal erosion of the east coast is accelerating, the need for scientific and quantitative coastal erosion monitoring technology for a wide area increases. The traditional method for observing changes in the coast was precision monitoring based on field surveys, but it can only be applied to a small area. The airborne bathymetric Light Detection And Ranging (LiDAR) system is a technology that enables economical surveying of coastal and seabed topography in a wide area. In particular, it has the advantage of constructing topographical data for the intertidal zone, which is a major area of interest for coastal erosion monitoring. In this study, time series analysis of coastal seabed topography acquired in Aug, 2021 and Mar. 2022 on the littoral cell GW36 in Gangwon was performed using the Seahawk Airborne Bathymetric LiDAR (ABL) system. We quantitatively monitored the topographical changes by measuring the baseline length, shoreline and Digital Terrain Model (DTM) changes. Through this, the effectiveness of the ABL surveying technique was confirmed in coastal erosion monitoring.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.10
• /
• pp.409-418
• /
• 2022

In this paper, we propose SAAnnot-C3Pap, a semi-automatic annotation method for obtaining ground truth of a player's posture. In order to obtain ground truth about the two-dimensional joint position in the existing music domain, openpose, a two-dimensional posture estimation method, was used or manually labeled. However, automatic annotation methods such as the existing openpose have the disadvantages of showing inaccurate results even though they are fast. Therefore, this paper proposes SAAnnot-C3Pap, a semi-automated annotation method that is a compromise between the two. The proposed approach consists of three main steps: extracting postures using openpose, correcting the parts with errors among the extracted parts using supervisely, and then analyzing the results of openpose and supervisely. Perform the synchronization process. Through the proposed method, it was possible to correct the incorrect 2D joint position detection result that occurred in the openpose, solve the problem of detecting two or more people, and obtain the ground truth in the playing posture. In the experiment, we compare and analyze the results of the semi-automated annotation method openpose and the SAAnnot-C3Pap proposed in this paper. As a result of comparison, the proposed method showed improvement of posture information incorrectly collected through openpose.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.1
• /
• pp.9-16
• /
• 2023

Robots are expected to expand their scope of application to the military field and take on important missions such as surveillance and enemy detection in the coming future warfare. Swarm robots can perform tasks that are difficult or time-consuming for a single robot to be performed more efficiently due to the advantage of having multiple robots. Swarm robots require mutual recognition and collaboration. So they send and receive vast amounts of data, making it increasingly difficult to verify SW. Hardware-in-the-loop simulation used to increase the reliability of mission verification enables SW verification of complex swarm robots, but the amount of verification data exchanged between the HILS device and the simulator increases exponentially according to the number of systems to be verified. So communication overload may occur. In this paper, we propose a digital twin-based communication optimization technique to solve the communication overload problem that occurs in mission verification of swarm robots. Under the proposed Digital Twin based Multi HILS Framework, Network DT can efficiently allocate network resources to each robot according to the mission scenario through the Network Controller algorithm, and can satisfy all sensor generation rates required by individual robots participating in the group. In addition, as a result of an experiment on packet loss rate, it was possible to reduce the packet loss rate from 15.7% to 0.2%.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.4
• /
• pp.49-57
• /
• 2022

The government is making great efforts to prevent crimes such as missing children by using public CCTVs. However, there is a shortage of operating manpower, weakening of concentration due to long-term concentration, and difficulty in tracking. In addition, applying real-time object search, re-identification, and tracking through a deep learning algorithm showed a phenomenon of increased parameters and insufficient memory for speed reduction due to complex network analysis. In this paper, we designed the network to improve speed and save memory through the application of Yolo v4, which can recognize real-time objects, and the application of Batch and TensorRT technology. In this thesis, based on the research on these advanced algorithms, OSNet re-ranking and K-reciprocal nearest neighbor for re-identification, Jaccard distance dissimilarity measurement algorithm for correlation, etc. are developed and used in the solution of CCTV national safety identification and tracking system. As a result, we propose a solution that can track objects by recognizing and re-identification objects in real-time within situation of a Korean public multi-CCTV environment through a set of algorithm combinations.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.64 no.3
• /
• pp.9-24
• /
• 2022

Currently, a vast amount of hydrologic data is accumulated in real-time through automatic water level measuring instruments in agricultural reservoirs. At the same time, false and missing data points are also increasing. The applicability and reliability of quality control of hydrological data must be secured for efficient agricultural water management through calculation of water supply and disaster management. Considering the characteristics of irregularities in hydrological data caused by irrigation water usage and rainfall pattern, the Korea Rural Community Corporation is currently applying the Hampel filter as a water level data quality management method. This method uses window size as a key parameter, and if window size is large, distortion of data may occur and if window size is small, many outliers are not removed which reduces the reliability of the corrected data. Thus, selection of the optimal window size for individual reservoir is required. To ensure reliability, we compared and analyzed the RMSE (Root Mean Square Error) and NSE (Nash-Sutcliffe model efficiency coefficient) of the corrected data and the daily water level of the RIMS (Rural Infrastructure Management System) data, and the automatic outlier detection standards used by the Ministry of Environment. To select the optimal window size, we used the classification performance evaluation index of the error matrix and the rainfall data of the irrigation period, showing the optimal values at 3 h. The efficient reservoir automatic calibration technique can reduce manpower and time required for manual calibration, and is expected to improve the reliability of water level data and the value of water resources.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.6
• /
• pp.175-181
• /
• 2022

The condition of infrastructure deteriorates as the service life increases. Since most infrastructure in South Korea were intensively built during the period of economic growth, the proportion of outdated infrastructure is rapidly increasing now. Aging of such infrastructure can lead to safety accidents and even human casualties. To prevent these issues in advance, periodic and accurate inspection is essential. For this reason, the need for research to detect various types of damage using computer vision and deep learning is increasingly required in the field of remotely controlled or autonomous inspection. To this end, this study proposed a neural network structure that can detect concrete damage by classifying it into three types. In particular, the proposed neural network can detect them more accurately through a hierarchical learning technique. This neural network was trained with 2,026 damage images and tested with 508 damage images. As a result, we completed an algorithm with average mean intersection over union of 67.04% and F1 score of 52.65%. It is expected that the proposed damage detection algorithm could apply to accurate facility condition diagnosis in the near future.

• Journal of Internet Computing and Services
• /
• v.23 no.6
• /
• pp.1-13
• /
• 2022

As the information and communication environment develops, the environment of military facilities is also development remarkably. In proportion to this, cyber threats are also increasing, and in particular, APT attacks, which are difficult to prevent with existing signature-based cyber defense systems, are frequently targeting military and national infrastructure. It is important to identify attack groups for appropriate response, but it is very difficult to identify them due to the nature of cyber attacks conducted in secret using methods such as anti-forensics. In the past, after an attack was detected, a security expert had to perform high-level analysis for a long time based on the large amount of evidence collected to get a clue about the attack group. To solve this problem, in this paper, we proposed an automation technique that can classify an attack group within a short time after detection. In case of APT attacks, compared to general cyber attacks, the number of attacks is small, there is not much known data, and it is designed to bypass signature-based cyber defense techniques. As an attack model, we used MITRE ATT&CK® which modeled many parts of cyber attacks. We design an impact score considering the versatility of the attack techniques and proposed a group similarity score based on this. Experimental results show that the proposed method classified the attack group with a 72.62% probability based on Top-5 accuracy.