• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.1
• /
• pp.30-37
• /
• 2021

Accurate 3D object tracking with camera images is a key enabling technology for augmented reality applications. Motivated by the impressive success of convolutional neural networks (CNNs) in computer vision tasks such as image classification, object detection, image segmentation, recent studies for 3D object tracking have focused on leveraging deep learning. In this paper, we review deep learning approaches for 3D object tracking. We describe key methods in this field and discuss potential future research directions.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.3
• /
• pp.513-520
• /
• 2020

Recently, the development of a vision inspection system using machine learning has become more active. This study seeks to develop a defect inspection model using machine learning. Defect detection problems for images correspond to classification problems, which are the method of supervised learning in machine learning. In this study, defect detection models are developed based on algorithms that automatically extract features and algorithms that do not extract features. One-dimensional CNN and two-dimensional CNN are used as algorithms for automatic extraction of features, and MLP and SVM are used as algorithms for non-extracting features. A defect detection model is developed based on four models and their accuracy and AUC compare based on AUC. Although image classification is common in the development of models using CNN, high accuracy and AUC is achieved when developing SVM models by converting pixels from images into RGB values in this study.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.4
• /
• pp.234-240
• /
• 2022

This paper proposes a customized AI exercise recommendation service for balancing the relative amount of exercise according to the working environment by each occupation. WISDM database is collected by using acceleration and gyro sensors, and is a dataset that classifies physical activities into 18 categories. Our system recommends a adaptive exercise using the analyzed activity type after classifying 18 physical activities into 3 physical activities types such as whole body, upper body and lower body. 1 Dimensional convolutional neural network is used for classifying a physical activity in this paper. Proposed model is composed of a convolution blocks in which 1D convolution layers with a various sized kernel are connected in parallel. Convolution blocks can extract a detailed local features of input pattern effectively that can be extracted from deep neural network models, as applying multi 1D convolution layers to input pattern. To evaluate performance of the proposed neural network model, as a result of comparing the previous recurrent neural network, our method showed a remarkable 98.4% accuracy.

• The Journal of Bigdata
• /
• v.5 no.1
• /
• pp.209-225
• /
• 2020

This study tried to establish a base level for the form of ginseng in order to prevent fraud in which novice consumers, who have no information on ginseng and mountain ginseng, regard ginseng as mountain ginseng. To that end, researchers designed a service design in which when a consumer takes a picture of ginseng with an APP dedicated to a smartphone, the photo is sent remotely and the determined results are sent to the consumer based on machine learning data. In order to minimize the difference between the data set in the research process and the background color, location, size, illumination, and color temperature of the mountain ginseng when consumers took pictures through their smartphones, the filming box exclusively for consumers was designed. Accordingly, the collection of mountain ginseng samples was made under the same controlled environment and setting as the designed box. This resulted in a 100% predicted probability from the CNN(VGG16) model using a sample that was about one-tenth less than widley required in machine learning.

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.2
• /
• pp.11-19
• /
• 2020

When a character's pose changes, its center of mass(COM) also changes. The change of COM has distinctive patterns corresponding to various motion types like walking, running or sitting. Thus the motion type can be predicted by using COM movement. We propose a motion generator that uses character's center of mass information. This generator can generate various motions without annotated action type labels. Thus dataset for training and running can be generated full-automatically. Our neural network model takes the motion history of the character and its center of mass information as inputs and generates a full-body pose for the current frame, and is trained using simple Convolutional Neural Network(CNN) that performs 1D convolution to deal with time-series motion data.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.664-671
• /
• 2021

This paper proposes a GPGPU structure that can reduce the number of operations and memory access by effectively applying a data reuse method to a convolutional neural network(CNN). Convolution is a two-dimensional operation using kernel and input data, and the operation is performed by sliding the kernel. In this case, a reuse method using an internal register is proposed instead of loading kernel from a cache memory until the convolution operation is completed. The serial operation method was applied to the convolution to increase the effect of data reuse by using the principle of GPGPU in which instructions are executed by the SIMT method. In this paper, for register-based data reuse, the kernel was fixed at 4×4 and GPGPU was designed considering the warp size and register bank to effectively support it. To verify the performance of the designed GPGPU on the CNN, we implemented it as an FPGA and then ran LeNet and measured the performance on AlexNet by comparison using TensorFlow. As a result of the measurement, 1-iteration learning speed based on AlexNet is 0.468sec and the inference speed is 0.135sec.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.33 no.3
• /
• pp.101-109
• /
• 2021

Wave observations using a marine X-band radar are conducted by analyzing the backscattered radar signal from sea surfaces. Wave parameters are extracted using Modulation Transfer Function obtained from 3D wave number and frequency spectra which are calculated by 3D FFT of time series of sea surface images (42 images per minute). The accuracy of estimation of the significant wave height is, therefore, critically dependent on the quality of radar images. Wave observations during Typhoon Maysak and Haishen in the summer of 2020 show large errors in the estimation of the significant wave heights. It is because of the deteriorated radar images due to raindrops falling on the sea surface. This paper presents the algorithm developed to increase the accuracy of wave heights estimation from radar images by adopting convolution neural network(CNN) which automatically classify radar images into rain and non-rain cases. Then, an algorithm for deriving the Hs is proposed by creating different ANN models and selectively applying them according to the rain or non-rain cases. The developed algorithm applied to heavy rain cases during typhoons and showed critically improved results.

• Journal of Advanced Navigation Technology
• /
• v.27 no.1
• /
• pp.111-118
• /
• 2023

For the implementation of a smart factory, it is necessary to collect data by connecting various sensors and devices in the manufacturing environment and to diagnose or predict failures in production facilities through data analysis. In this paper, to predict the residual useful lifetime of milling insert used for machining products in CNC machine, weight k-NN algorithm, Decision Tree, SVR, XGBoost, Random forest, 1D-CNN, and frequency spectrum based on vibration signal are investigated. As the results of the paper, the frequency spectrum does not provide a reliable criterion for an accurate prediction of the residual useful lifetime of an insert. And the weighted k-nearest neighbor algorithm performed best with an MAE of 0.0013, MSE of 0.004, and RMSE of 0.0192. This is an error of 0.001 seconds of the remaining useful lifetime of the insert predicted by the weighted-nearest neighbor algorithm, and it is considered to be a level that can be applied to actual industrial sites.

• Archives of design research
• /
• v.11 no.1
• /
• pp.291-302
• /
• 1998

This paper covers the development process of multimedia evaluation system, especially focused on customer satisfactory factors while customers navigating net-based Interactive multimedia system. Customers usually experience new level of interaction cased by newly developed web-based technology In ordinary multimedia system. However, if it gives customers satisfactory experience is a matter of question. To find out the relationship between customer satisfaction and interactivity factors exposed by multimedia system, a model has been developed which describes the structure of web-based multimedia system and its relation to customer satisfactory factors. Five different experiments, including 'semantic differential', 'focus group interview', and 'expert review', has been conducted and four customer satisfactory factors were identified. Those are 'customery value', 'structural perfectness', 'visual perfectness', and 'contemporaneity'. With these factors and newly delveoped evaluation system, 7 different web-site has been evaluated and analyzed at the end of this report.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.3
• /
• pp.140-147
• /
• 2024

In the Republic of Korea, people with hearing impairments are the second-largest demographic within the registered disability community, following those with physical disabilities. Despite this demographic significance, research on sign language translation technology is limited due to several reasons including the limited market size and the lack of adequately annotated datasets. Despite the difficulties, a few researchers continue to improve the performacne of sign language translation technologies by employing the recent advance of deep learning, for example, the transformer architecture, as the transformer-based models have demonstrated noteworthy performance in tasks such as action recognition and video classification. This study focuses on enhancing the recognition performance of sign language translation by combining transformers with 3D-CNN. Through experimental evaluations using the PHOENIX-Wether-2014T dataset [1], we show that the proposed model exhibits comparable performance to existing models in terms of Floating Point Operations Per Second (FLOPs).