• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.755-764
• /
• 2019

Currently commercially available light field cameras are difficult to acquire 5D light field video since it can only acquire the still images or high price of the device. In order to solve these problems, we propose a deep learning based method for synthesizing the light field video from monocular video. To solve the problem of obtaining the light field video training data, we use UnrealCV to acquire synthetic light field data by realistic rendering of 3D graphic scene and use it for training. The proposed deep running framework synthesizes the light field video with each sub-aperture image (SAI) of $9{\times}9$ from the input monocular video. The proposed network consists of a network for predicting the appearance flow from the input image converted to the luminance image, and a network for predicting the optical flow between the adjacent light field video frames obtained from the appearance flow.

• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.914-924
• /
• 2018

In this paper, we implement an Android application for infant language education using marker-based augmented reality. Combining animal word markers (noun), size/color word markers (adjective), and action word markers (verb) in puzzle form to make a simple sentence, the application shows virtual contents related to the content of the sentence. For example, when an animal marker is showed up on a camera, the corresponding animal appears. Additionally, when the motion markers are combined, the animal's appearance changes into an animation in which it acts. When a user touched a marker, user can hear the sound of the word, which gives an auditory effect, and by adding the rotation function, user can see the animation in any direction. Our goal is to increase infants' interest in learning language and also increase the effectiveness of education on the meaning of words and the structure of simple sentences, by encouraging them to actively participate in language learning through visual and auditory stimuli.

• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.780-789
• /
• 2018

Nowadays, gun crimes occur very frequently not only in public places but in alleyways around the world. In particular, it is essential to detect a person armed by a pistol to prevent those crimes since small guns, such as pistols, are often used for those crimes. Because conventional works for armed person detection have treated an armed person as a single object in an input image, their accuracy is very low. The reason for the low accuracy comes from the fact that the gunman is treated as a single object although the pistol is a relatively much smaller object than the person. To solve this problem, we propose a novel algorithm called APDA(Armed Person Detection Algorithm). APDA detects the armed person using in a post-processing the positions of both wrists and the pistol achieved by the CNN-based human body feature detection model and the pistol detection model, respectively. We show that APDA can provide both 46.3% better recall and 14.04% better precision than SSD-MobileNet.

• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.77-86
• /
• 2019

This paper proposes using machine-learning technology to analyze and classify historical collected documents based on them. Data is collected based on keywords associated with a specific domain and the non-conceptuals such as special characters are removed. Then, tag each word of the document collected using a Korean-language morpheme analyzer with its nouns, verbs, and sentences. Embedded documents using Doc2Vec model that converts documents into vectors. Measure the similarity between documents through the embedded model and learn the document classifier using the machine running algorithm. The highest performance support vector machine measured 0.83 of F1-score as a result of comparing the classification model learned.

• Journal of Broadcast Engineering
• /
• v.24 no.2
• /
• pp.234-242
• /
• 2019

In this paper, we propose a deep neural network which extracts SIFT feature points by determining whether the center pixel of a cropped image is a SIFT feature point. The data set of this network consists of a DIV2K dataset cut into $33{\times}33$ size and uses RGB image unlike SIFT which uses black and white image. The ground truth consists of the RobHess SIFT features extracted by setting the octave (scale) to 0, the sigma to 1.6, and the intervals to 3. Based on the VGG-16, we construct an increasingly deep network of 13 to 23 and 33 convolution layers, and experiment with changing the method of increasing the image scale. The result of using the sigmoid function as the activation function of the output layer is compared with the result using the softmax function. Experimental results show that the proposed network not only has more than 99% extraction accuracy but also has high extraction repeatability for distorted images.

• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.898-910
• /
• 2020

Single image-based super-resolution has been studied for a long time in computer vision because of various applications. Various deep learning-based super-resolution algorithms are introduced recently to improve the performance by reducing side effects like blurring and staircase effects. Most deep learning-based approaches have focused on how to implement the network architecture, loss function, and training strategy to improve performance. Meanwhile, Several approaches using Attention Module, which emphasizes the extracted features, are introduced to enhance the performance of the network without any additional layer. Attention module emphasizes or scales the feature map for the purpose of the network from various perspectives. In this paper, we propose the various channel attention and spatial attention in single image-based super-resolution and analyze the results and performance according to the architecture of the attention module. Also, we explore that designing multi-attention module to emphasize features efficiently from various perspectives.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.332-340
• /
• 2022

Recently, with the development of deep learning and artificial neural network technologies, research on the application of neural network has been actively conducted in the field of video coding. In particular, deep learning-based intra prediction is being studied as a way to overcome the performance limitations of the existing intra prediction techniques. This paper presents a method of context-adaptive neural network-based intra prediction model training and its coding performance analysis. In other words, in this paper, we implement and train a known intra prediction model based on convolutional neural network (CNN) that predicts a current block using contextual information from reference blocks. Then, we integrate the trained model into HM16.19 as an additional intra prediction mode and evaluate the coding performance of the trained model. Experimental results show that the trained model gives 0.28% BD-rate bit saving over HEVC in All Intra (AI) coding mode. In addition, the coding performance change of training considering block partition is also presented.

• The Journal of the Korea Contents Association
• /
• v.22 no.4
• /
• pp.83-93
• /
• 2022

Research is underway to solve the traffic problem by using crowdsourcing, where drivers use their mobile devices to provide traffic information. If it is used for traffic event detection through crowdsourcing, the task of collecting related data is reduced, which lowers time cost and increases accuracy. In this paper, we propose a scheme to collect traffic-related data using crowdsourcing and to detect events affecting traffic through this. The proposed scheme uses machine learning algorithms for processing large amounts of data to determine the event type of the collected data. In addition, to find out the location where the event occurs, a keyword indicating the location is extracted from the collected data, and the administrative area of the keyword is returned. In this way, it is possible to resolve a location that is broadly defined in the existing location information or incorrect location information. Various performance evaluations are performed to prove the superiority and feasibility of the proposed scheme.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.33 no.2
• /
• pp.75-95
• /
• 2022

This study was carried out with the aim of analyzing the development and functional changes of Webdewey, which has become a basic tool of classification learning, analyzing it in terms of usability for learners, and suggesting specific ways to improve WebDewey's usability. In order to achieve this research objective, the concepts and principles of UI and usability were first laid out, and Webdewey's structure and key functions were analyzed. Since then, Webdewey's media changes and periodical feature changes have been analyzed. In addition, an opinion survey was conducted on the usability of WebDewey among learners who used WebDewey in the learning process, and proposed ways to improve WebDewey's usability based on the implications and direction of improvement derived from it. In terms of UI, proposals have been made to introduce display methods, visualization devices, the advantages of printed versions, and the development of Korean versions. In terms of the 'Create built number' function, suggestions have been made to improve usability in terms of basic number selection, composite route guidance and error message provision, new reference and route construction, screen and button design, and built-number component guidance.

• Journal of Creative Information Culture
• /
• v.7 no.4
• /
• pp.197-206
• /
• 2021

This study is a case of convergence education using the AI model of entry in elementary schools. The subject is English, and the class was conducted based on the image learning model among the convergence activities with the art department drawing and the AI model of the entry. In order to effectively achieve the learning goals of speaking and writing in English education. The class was designed by combining art and SW. Students experienced communication using AI, improved confidence, and were able to improve creativity and communication skills by expressing not only listening and speaking but also expressing through various media such as pictures and photos. In addition, in order to find out the effectiveness of the class, a survey was conducted on students and the results were analyzed. As a result of the analysis, it was found that it had a positive effect on students' participation rate, degree of understanding AI after class, interest in AI, satisfaction with AI classes.