• Journal of the Korea Institute of Building Construction
• /
• v.14 no.1
• /
• pp.29-36
• /
• 2014

To meet changing education needs due to globalization, interdisciplinary convergence, and ICT development, it is necessary for engineering disciplines to provide student-centered education. Not only do teaching methods using ICT reproduce teaching contents in a digital format, but they are also expected to be effective media for constructive student-centered learning whereby learners build knowledge themselves. The aim of this study was to develop a tool for safety education using virtual reality technology. To achieve the objectives, the author defined the requirements and constraints of the tool, and implemented a 3D educational tool in a virtual reality environment. A pilot test with 10 students showed positive results.

• Journal of Broadcast Engineering
• /
• v.23 no.1
• /
• pp.115-125
• /
• 2018

This paper presents a fast partition decision framework for High Efficiency Video Coding (HEVC) Screen Content Coding (SCC) based on machine learning. Currently, the HEVC performs quad-tree block partitioning process to achieve optimal coding efficiency. Since this process requires a high computational complexity of the encoding device, the fast encoding process has been studied as determining the block structure early. However, in the case of the screen content video coding, it is difficult to apply the conventional early partition decision method because it shows different partition characteristics from natural content. The proposed method solves the problem by classifying the screen content blocks after partition decision, and it shows an increase of 3.11% BD-BR and 42% time reduction compared to the SCC common test condition.

• Journal of Broadcast Engineering
• /
• v.23 no.4
• /
• pp.526-535
• /
• 2018

Many steganography algorithms have been studied, and steganalysis for detecting stego images which steganography is applied to has also been studied in parallel. Especially, in the case of the image steganalysis, the features such as ALE, SPAM, and SRMQ are extracted from the statistical characteristics of the image, and stego images are classified by learning the classifier using various machine learning algorithms. However, these studies did not consider the effect of image size, aspect ratio, or message-embedding rate, and thus the features might not function normally for images with conditions different from those used in the their studies. In this paper, we analyze the classification rate of the SPAM-based image stegnalysis against variety image sizes aspect ratios and message-embedding rates and verify its versatility.

• Journal of Internet Computing and Services
• /
• v.21 no.3
• /
• pp.113-121
• /
• 2020

Human Pose Estimation (HPE) which localizes the human body joints becomes a high potential for high-level applications in the field of computer vision. The main challenges of HPE in real-time are occlusion, illumination change and diversity of pose appearance. The single RGB image is fed into HPE framework in order to reduce the computation cost by using depth-independent device such as a common camera, webcam, or phone cam. However, HPE based on the single RGB is not able to solve the above challenges due to inherent characteristics of color or texture. On the other hand, depth information which is fed into HPE framework and detects the human body parts in 3D coordinates can be usefully used to solve the above challenges. However, the depth information-based HPE requires the depth-dependent device which has space constraint and is cost consuming. Especially, the result of depth information-based HPE is less reliable due to the requirement of pose initialization and less stabilization of frame tracking. Therefore, this paper proposes a new method of HPE which is robust in estimating self-occlusion. There are many human parts which can be occluded by other body parts. However, this paper focuses only on head self-occlusion. The new method is a combination of the RGB image-based HPE framework and the depth information-based HPE framework. We evaluated the performance of the proposed method by COCO Object Keypoint Similarity library. By taking an advantage of RGB image-based HPE method and depth information-based HPE method, our HPE method based on RGB-D achieved the mAP of 0.903 and mAR of 0.938. It proved that our method outperforms the RGB-based HPE and the depth-based HPE.

• Journal of Broadcast Engineering
• /
• v.18 no.3
• /
• pp.401-408
• /
• 2013

In this paper, we propose a method that automatically detects organs having similar appearances in medical images by learning both context and appearance features. Since only the appearance feature is used to learn the classifier in most existing detection methods, detection errors occur when the medical images include multiple organs having similar appearances. In the proposed method, based on the probabilities acquired by the appearance-based classifier, new classifier containing the context feature is created by iteratively learning the characteristics of probability distribution around the interest voxel. Furthermore, both the efficiency and the accuracy are improved through 'region based voting scheme' in test stage. To evaluate the performance of the proposed method, we detect femur and tibia which have similar appearance from SKI10 knee joint dataset. The proposed method outperformed the detection method only using appearance feature in aspect of overall detection performance.

• Journal of Broadcast Engineering
• /
• v.25 no.2
• /
• pp.242-251
• /
• 2020

Recently, many deep convolutional neural networks for image super-resolution have been studied. Existing deep learning-based super-resolution algorithms are architecture that up-samples the resolution at the end of the network. The post-upsampling architecture has an inefficient structure at large scaling factor result of predicting a lot of information for mapping from low-resolution to high-resolution at once. In this paper, we propose a single image super-resolution using Channel Attention Residual Dense Block based on an iterative up-down sampling architecture. The proposed algorithm efficiently predicts the mapping relationship between low-resolution and high-resolution, and shows up to 0.14dB performance improvement and enhanced subjective image quality compared to the existing algorithm at large scaling factor result.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 1999.12a
• /
• pp.301-313
• /
• 1999

Recently, the rabid development of information technology has brought enormous changes in education. Consolidation of communications and multimedia technologies are enabling the new educational paradigm such as distance learning and virtual education. Furthermore, many studies in the education engineering field report that teaching using multimedia technologies more enhances students' performance than the traditional instructor-teaching method. However, little research regarding the education using multimedia has been done in the MIS filed. None of multimedia-related studies could be found in the top-ranked MIS journals published in Korea for the last five years, and only a few studies were found even worldwide. In this regard, the purpose of this study is to investigate which features of multimedia software are most important to enhance the teaching results of students. From the previous research, we found out the specific features of the educational multimedia software which are considered to affect the students'performance, and defined the research variables related to those educational software features. And, based on the constructivism and motivation theory of the education engineering field a theoretical research model and research hypotheses were developed. Perceived usefulness of the class and a student's perceived interests in the class were used as surrogate variables to measure teaching performance. Total 277 students participated separately in one of the two multimedia classes which have continued for three weeks. One was C programming language class and the other was multimedia CD-title development class. Each student listened for the multimedia session of the class using multimedia software and, at the end of the multimedia session, answered the survey questionnaire. The results of the study show that motivation to the class and the contents of education were statistically significant to the students'performance in the class. That implies, not only in the traditional instructor-teaching method but also in the multimedia class, that the contents of education itself and student's motivation to the class are most important to raise instructional results.

• Journal of radiological science and technology
• /
• v.41 no.5
• /
• pp.487-491
• /
• 2018

The purpose of this study was to analyze questionnaires of 161 college students attending radiology departments in order to investigate the actual condition of internet use of radiology students. As a result, 95% of college students using the Internet showed 5.8% of general knowledge, 56.9% of radiation major, and 45.8% of general education. In the field of Internet use, basic medicine was 71.2%, anatomy 59.5% and physiology 51.6%. Radiation theory was 39.9% in radiation physics, 31.4% in radiation biology, and 18.3% in radiation management. The radiological applications were followed by radiography and radiography in order of 31.4% and 20.3%, respectively. The radiological imaging was 45.8%, MRI was 37.9%, CT was 37.3%, ultrasound was 24.2%, And radiation nuclear medicine 25.5%. The results of the descriptive statistics of the satisfaction of the contents using the Internet media showed that the overall satisfaction was below 2.5 Based on the results of this study, it is necessary to develop a program with high accessibility to provide various opportunities for internet-based opportunities to increase the academic achievement value of major subjects through the internet and to solve the difficulties in the major subject.

• Journal of Broadcast Engineering
• /
• v.23 no.5
• /
• pp.598-605
• /
• 2018

Behavior awareness is a technology that recognizes human behavior through data and can be used in applications such as risk behavior through video surveillance systems. Conventional behavior recognition algorithms have been performed using the 2D camera image device or multi-mode sensor or multi-view or 3D equipment. When two-dimensional data was used, the recognition rate was low in the behavior recognition of the three-dimensional space, and other methods were difficult due to the complicated equipment configuration and the expensive additional equipment. In this paper, we propose a method of recognizing human behavior using only CCTV images without additional equipment using only RGB and depth information. First, the skeleton extraction algorithm is applied to extract points of joints and body parts. We apply the equations to transform the vector including the displacement vector and the relational vector, and study the continuous vector data through the RNN model. As a result of applying the learned model to various data sets and confirming the accuracy of the behavior recognition, the performance similar to that of the existing algorithm using the 3D information can be verified only by the 2D information.

• Korean Institute of Interior Design Journal
• /
• v.22 no.3
• /
• pp.195-204
• /
• 2013

Today, the children's museum evolved from place of exhibition for seeing and feeling, to that of exhibition for searching and touching, or so-called the hands-on exhibition. This will allow for grabbing the interest from children and provide an opportunity for learning by an actual experience at this intellectual and benign environment. But in this modern society that constantly undergoes evolution even as we speak, it is not an easy task to bring our children to museums, because they are vastly exposed to various media. Moreover, if the children who visited museums carelessly bypass the specific areas intended for exhibition, the educational purpose of "enhanced learning effect with hands-on experience" is easily underachieved. According to children's visual stimuli, their behavioral charactoristics are appeared to freewill curiosity but they show shorter elapsed time(impermanence), intensity(stubbornness), frequent occurrence(frequentness) and changeable (translatability). So, We need Improvement of visual image affordance through the measurement of stay time. Firstly, five factors are extracted by factor analysis on twenty questions based on visual image factors; Color accessability and Satistaction(factor1), brightness and color harmony(factor2), feeling on harmonization of color and stay time(factor3), simplex & complex of space(factor4), feeling on scale(factor5) Secondly, the following result are derived through a distribution chart on an exhibition room of K-museum. As shown above, this study based on various analyzed aspects proposes the directions of a color image plan to improve stay time in exhibition space of children museums with a hope to support educational goals of experience education-focused children museums.