• Tunnel and Underground Space
• /
• v.33 no.4
• /
• pp.281-298
• /
• 2023

Continuous research efforts are being devoted to unmanned mobile platforms for lunar exploration. There is an ongoing demand for real-time information processing to accurately determine the positioning and mapping of areas of interest on the lunar surface. To apply deep learning processing and analysis techniques to practical rovers, research on software integration and optimization is imperative. In this study, a foundational investigation has been conducted on real-time analysis of virtual lunar base construction site images, aimed at automatically quantifying spatial information of key objects. This study involved transitioning from an existing region-based object recognition algorithm to a boundary box-based algorithm, thus enhancing object recognition accuracy and inference speed. To facilitate extensive data-based object matching training, the Batch Hard Triplet Mining technique was introduced, and research was conducted to optimize both training and inference processes. Furthermore, an improved software system for object recognition and identical object matching was integrated, accompanied by the development of visualization software for the automatic matching of identical objects within input images. Leveraging satellite simulative captured video data for training objects and moving object-captured video data for inference, training and inference for identical object matching were successfully executed. The outcomes of this research suggest the feasibility of implementing 3D spatial information based on continuous-capture video data of mobile platforms and utilizing it for positioning objects within regions of interest. As a result, these findings are expected to contribute to the integration of an automated on-site system for video-based construction monitoring and control of significant target objects within future lunar base construction sites.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.5 no.3
• /
• pp.49-59
• /
• 1985

Formulation of the geometric optimization for truss structures based on the elasticity theory turn out to be the nonlinear programming problem which has to deal with the Cross sectional area of the member and the coordinates of its nodes simultaneously. A few techniques have been proposed and adopted for the analysis of this nonlinear programming problem for the time being. These techniques, however, bear some limitations on truss shapes loading conditions and design criteria for the practical application to real structures. A generalized algorithm for the geometric optimization of the truss structures which can eliminate the above mentioned limitations, is developed in this study. The algorithm developed utilizes the two-phases technique. In the first phase, the cross sectional area of the truss member is optimized by transforming the nonlinear problem into SUMT, and solving SUMT utilizing the modified Newton-Raphson method. In the second phase, the geometric shape is optimized utilizing the unidirctional search technique of the Rosenbrock method which make it possible to minimize only the objective function. The algorithm developed in this study is numerically tested for several truss structures with various shapes, loading conditions and design criteria, and compared with the results of the other algorithms to examme its applicability and stability. The numerical comparisons show that the two-phases algorithm developed in this study is safely applicable to any design criteria, and the convergency rate is very fast and stable compared with other iteration methods for the geometric optimization of truss structures.

• The Journal of the Convergence on Culture Technology
• /
• v.4 no.2
• /
• pp.197-204
• /
• 2018

One of the hottest issues in our 21st century is AI. Just as the automation of manual labor has been achieved through the Industrial Revolution in the agricultural society, the intelligence information society has come through the SW Revolution in the information society. With the advent of Google 'Alpha Go', the computer has learned and predicted its own machine learning, and now the time has come for the computer to surpass the human, even to the world of Baduk, in other words, the computer. Machine learning ML (machine learning) is a field of artificial intelligence. Machine learning ML (machine learning) is a field of artificial intelligence, which means that AI technology is developed to allow the computer to learn by itself. The time has come when computers are beyond human beings. Many companies use machine learning, for example, to keep learning images on Facebook, and then telling them who they are. We also used a neural network to build an efficient energy usage model for Google's data center optimization. As another example, Microsoft's real-time interpretation model is a more sophisticated translation model as the language-related input data increases through translation learning. As machine learning has been increasingly used in many fields, we have to jump into the AI industry to move forward in our 21st century society.

• Journal of Broadcast Engineering
• /
• v.21 no.6
• /
• pp.957-964
• /
• 2016

Acquisition of reliable depth maps is a critical requirement in many applications such as 3D videos and free-viewpoint TV. Depth information can be obtained from the object directly using physical sensors, such as infrared ray (IR) sensors. Recently, Time-of-Flight (ToF) range camera including KINECT depth camera became popular alternatives for dense depth sensing. Although ToF cameras can capture depth information for object in real time, but are noisy and subject to low resolutions. Recently, filter-based depth up-sampling algorithms such as joint bilateral upsampling (JBU) and noise-aware filter for depth up-sampling (NAFDU) have been proposed to get high quality depth information. However, these methods often lead to texture copying in the upsampled depth map. To overcome this limitation, we formulate a convex optimization problem using higher order regularization for depth map upsampling. We decrease the texture copying problem of the upsampled depth map by using edge weighting term that chosen by the edge information. Experimental results have shown that our scheme produced more reliable depth maps compared with previous methods.

• Journal of the HCI Society of Korea
• /
• v.1 no.1
• /
• pp.1-8
• /
• 2006

We suggest a graphical representation of the tension flow in tonal music using a piecewise parametric curve, which is a function of time illustrating the changing degree of tension in a corresponding chord progression. The tension curve can be edited by using conventional curve editing techniques to reharmonize the original music with reflecting the user's demand to control the tension of music. We introduce three different methods to measure the tension of a chord in terms of a specific key, which can be used to represent the tension of the chord numerically. Then, by interpolating the series of numerical tension values, a tension curve is constructed. In this paper, we show the tension curve editing method can be effectively used in several interesting applications: enhancing or weakening the overall feeling of tension in a whole song, the local control of tension in a specific region of music, the progressive transition of tension flow from source to target chord progressions, and natural connection of two songs with maintaining the smoothness of the tension flow. Our work shows the possibility of controlling the perceptual factor (tension) in music by using numerical methods. Most of the computations used in this paper are not expensive so they can be calculated in real time. We think that an interesting application of our method is an interactive modification of tension in background music according to the user's emotion or current scenario in the interactive environments such as games.

• Korean Chemical Engineering Research
• /
• v.59 no.2
• /
• pp.209-218
• /
• 2021

First principle-based modeling studies have been performed to improve the heat exchange efficiency of ORV and optimize operation, but the heat transfer coefficient of ORV is an irregular system according to time and location, and it undergoes a complex modeling process. In this study, FNN, LSTM, and AutoML-based modeling were performed to confirm the effectiveness of data-based modeling for complex systems. The prediction accuracy indicated high performance in the order of LSTM > AutoML > FNN in MSE. The performance of AutoML, an automatic design method for machine learning models, was superior to developed FNN, and the total time required for model development was 1/15 compared to LSTM, showing the possibility of using AutoML. The prediction of NG and seawater discharged temperatures using LSTM and AutoML showed an error of less than 0.5K. Using the predictive model, real-time optimization of the amount of LNG vaporized that can be processed using ORV in winter is performed, confirming that up to 23.5% of LNG can be additionally processed, and an ORV optimal operation guideline based on the developed dynamic prediction model was presented.

• Journal of Digital Convergence
• /
• v.18 no.11
• /
• pp.259-266
• /
• 2020

Many developments have been steadily carried out by researchers with applying knowledge-based expert system or machine learning algorithms to the financial field. In particular, it is now common to perform knowledge based system trading in using stock prices. Recently, deep learning technologies have been applied to real fields of stock trading marketplace as GPU performance and large scaled data have been supported enough. Especially, LSTM has been tried to apply to stock price prediction because of its compatibility for time series data. In this paper, we implement stock price prediction using LSTM. In modeling of LSTM, we propose a fitness combination of model parameters and activation functions for best performance. Specifically, we propose suitable selection methods of initializers of weights and bias, regularizers to avoid over-fitting, activation functions and optimization methods. We also compare model performances according to the different selections of the above important modeling considering factors on the real-world stock price data of global major companies. Finally, our experimental work brings a fitness method of applying LSTM model to stock price prediction.

• The KIPS Transactions:PartD
• /
• v.11D no.4
• /
• pp.983-990
• /
• 2004

Multiple-count problem is occurred when rectangle objects span across several buckets. The CD histogram is a technique which selves this problem by keeping four sub-histograms corresponding to the four points of rectangle. Although It provides exact results with constant response time, there is still a considerable issue. Since it is based on a query window which aligns with a given grid, a number of errors nay be occurred when it is applied to real applications. In this paper, we propose selectivity estimation techniques using the generalized cumulative density histogram based on two probabilistic models : \circled1 probabilistic model which considers the query window area ratio, \circled2 probabilistic model which considers intersection area between a given grid and objects. Our method has the capability of eliminating an impact of the restriction on query window which the existing cumulative density histogram has. We experimented with real datasets to evaluate the proposed methods. Experimental results show that the proposed technique is superior to the existing selectivity estimation techniques. Furthermore, selectivity estimation technique based on probabilistic model considering the intersection area is very accurate(less than 5% errors) at 20% query window. The proposed techniques can be used to accurately quantify the selectivity of the spatial range query on rectangle objects.

• Journal of Korean Society for Geospatial Information Science
• /
• v.22 no.4
• /
• pp.175-181
• /
• 2014

Korean government proposed a new initiative 'government 3.0' with which the administration will open its dataset to the public before requests. City of Seoul is the front runner in disclosure of government data. If we know what kind of attributes are governing factors for any given segmentation, these outcomes can be applied to real world problems of marketing and business strategy, and administrative decision makings. However, with respect to city of Seoul, selection of optimal variables from the open dataset up to several thousands of attributes would require a humongous amount of computation time because it might require a combinatorial optimization while maximizing dissimilarity measures between clusters. In this study, we acquired 718 attribute dataset from Statistics Korea and conducted an analysis to select the most suitable variables, which differentiate Gangnam from other districts, using the Genetic algorithm and Dunn's index. Also, we utilized the Microsoft Azure cloud computing system to speed up the process time. As the result, the optimal 28 variables were finally selected, and the validation result showed that those 28 variables effectively group the Gangnam from other districts using the Ward's minimum variance and K-means algorithm.