• Journal of Broadcast Engineering
• /
• v.27 no.6
• /
• pp.897-905
• /
• 2022

Research for video key frame detection has been actively conducted in the fields of computer vision. Recently with the advances on deep learning techniques, performance of key frame detection has been improved, but the various type of video content and complicated background are still a problem for efficient learning. In this paper, we propose a novel method for key frame detection, witch utilizes contrastive learning and memory bank module. The proposed method trains the feature extracting network based on the difference between neighboring frames and frames from separate videos. Founded on the contrastive learning, the method saves and updates key frames in the memory bank, witch efficiently reduce redundancy from the video. Experimental results on video dataset show the effectiveness of the proposed method for key frame detection.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1282-1290
• /
• 2017

Since the mitigation of fear of crime significantly enhances the consumptions in a city, studies focusing on urban safety analysis have received much attention as means of revitalizing the local economy. In addition, with the development of computer vision and machine learning technologies, efficient and automated analysis methods have been developed. Previous studies have used global features to predict the safety of cities, yet this method has limited ability in accurately predicting abstract information such as safety assessments. Therefore we used a Convolutional Context Neural Network (CCNN) that considered "context" as a decision criterion to accurately predict safety of cities. CCNN model is constructed by combining a stacked auto encoder with a fully connected network to find the context and use it in the CNN model to predict the score. We analyzed the RMSE and correlation of SVR, Alexnet, and Sharing models to compare with the performance of CCNN model. Our results indicate that our model has much better RMSE and Pearson/Spearman correlation coefficient.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1271-1281
• /
• 2017

It is essential to collect and analyze target information around the vehicle for autonomous driving of the vehicle. Based on the analysis, environmental information such as location and direction should be analyzed in real time to control the vehicle. In particular, obstruction or cutting of objects in the image must be handled to provide accurate information about the vehicle environment and to facilitate safe operation. In this paper, we propose a method to simultaneously generate 2D and 3D bounding box proposals using LiDAR Edge generated by filtering LiDAR sensor information. We classify the classes of each proposal by connecting them with Region-based Fully-Covolutional Networks (R-FCN), which is an object classifier based on Deep Learning, which uses two-dimensional images as inputs. Each 3D box is rearranged by using the class label and the subcategory information of each class to finally complete the 3D bounding box corresponding to the object. Because 3D bounding boxes are created in 3D space, object information such as space coordinates and object size can be obtained at once, and 2D bounding boxes associated with 3D boxes do not have problems such as occlusion.

• Proceedings of the Korea Contents Association Conference
• /
• 2007.11a
• /
• pp.622-626
• /
• 2007

As the time of edutainment has come, the importance of storytelling is attracting attention gradually in order to facilitate learners to receive and absorb information and knowledge. This research aims at observing how animations in the design of storytelling of edutainment affect elementary students and proposing learning-procedure and storyboard regarding to the storytellings based on animation. Thus, it could successfully establish plots and characters of the proverb learning appropriate to the elementary students and by applying them to the animations raise the importance of storytellings in the development of edutainment contents.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.12
• /
• pp.6038-6053
• /
• 2017

In this study, we propose an automatic melody extraction algorithm using deep learning. In this algorithm, feature images, generated using the energy of frequency band, are extracted from polyphonic audio files and a deep learning technique, a convolutional neural network (CNN), is applied on the feature images. In the training data, a short frame of polyphonic music is labeled as a musical note and a classifier based on CNN is learned in order to determine a pitch value of a short frame of audio signal. We want to build a novel structure of melody extraction, thus the proposed algorithm has a simple structure and instead of using various signal processing techniques for melody extraction, we use only a CNN to find a melody from a polyphonic audio. Despite of simple structure, the promising results are obtained in the experiments. Compared with state-of-the-art algorithms, the proposed algorithm did not give the best result, but comparable results were obtained and we believe they could be improved with the appropriate training data. In this paper, melody extraction and the proposed algorithm are introduced first, and the proposed algorithm is then further explained in detail. Finally, we present our experiment and the comparison of results follows.

• Smart Media Journal
• /
• v.9 no.2
• /
• pp.92-98
• /
• 2020

This paper proposes a vehicle license plate recognition system using light weight deep learning models without high-end server. The proposed license plate recognition system consists of 3 steps: [license plate detection]-[character area segmentation]-[character recognition]. SSD-Mobilenet was used for license plate detection, ResNet with localization was used for character area segmentation, ResNet was used for character recognition. Experiemnts using Samsung Galaxy S7 and LG Q9, accuracy showed 85.3% accuracy and around 1.1 second running time.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.01a
• /
• pp.413-414
• /
• 2014

최근 스마트기기 보급의 확산과 이러닝 환경의 고도화로 이러닝 산업의 패러디임이 변화하면서 스마트 디바이스를 통한 학습형태의 스마트러닝이 주목받고 있다. 이처럼 스마트러닝이 부각되면서 기존의 이러닝 콘텐츠를 스마트 디바이스 환경에서도 제공 받고자 하는 사용자들의 요구가 증가하고 있지만 현재 기존 PC기반으로 구현된 이러닝 콘텐츠를 스마트기기에 적용하는데 있어 다양한 문제가 발생하고 있다. 특히 가장 근본적인 문제는 표준에 기인한다고 할 수 있으며 이를 해결하기 위해서는 콘텐츠에 대한 표준화가 필수적인 요소로 작용한다. 이에 본 논문에서는 최근 국내에서 전자책 및 디지털교과서 개발에 표준으로 자리잡고 있는 EPUB 3.0을 준용하여 기존 이러닝 콘텐츠의 데이터 포맷을 변경하고 표준화된 형태로 다양한 스마트 디바이스에 적용이 가능한 디지털교과서 솔루션을 설계하였다.

• Journal of Information Processing Systems
• /
• v.16 no.3
• /
• pp.541-556
• /
• 2020

Wireless networks have become integral to society as they provide mobility and scalability advantages. However, their disadvantage is that they cannot control the media, which makes them vulnerable to various types of attacks. One example of such attacks is the evil twin access point (AP) attack, in which an authorized AP is impersonated by mimicking its service set identifier (SSID) and media access control (MAC) address. Evil twin APs are a major source of deception in wireless networks, facilitating message forgery and eavesdropping. Hence, it is necessary to detect them rapidly. To this end, numerous methods using clock skew have been proposed for evil twin AP detection. However, clock skew is difficult to calculate precisely because wireless networks are vulnerable to noise. This paper proposes an evil twin AP detection method that uses a multiple-feature-based machine learning classification algorithm. The features used in the proposed method are clock skew, channel, received signal strength, and duration. The results of experiments conducted indicate that the proposed method has an evil twin AP detection accuracy of 100% using the random forest algorithm.

• Cross-Cultural Studies
• /
• v.31
• /
• pp.415-438
• /
• 2013

This paper explores how to teach Chinese, using multi-media resources such as Chinese dramas and focusing on one of Jin Yong's dramas, The Return of the Condor Heroes. The purpose of this study is to develop teaching methodologies for university students learning Chinese through drama to integrate language skills: enhancing communicative competence and understanding Chinese cultures. First, the overview of previous studies provides several cases of foreign language education using drama. Teaching Chinese through drama can be an integrative education because students can develop their communicative competence as well as understand the cultures of the target language. In other words, the contexts of drama may offer rich sources of the history of China, Han Chinese ethnocentrism, and knowledge of Chinese literature as well as geography. Second, this study applies the principles of Tomlinson (2010) for materials development in language teaching into the case of Chinese drama. It concentrates on Jin Yong's The Return of the Condor Heroes that the author has used in the Chinese language courses for three years. It examines the characteristics of the drama for developing effective ways of teaching and learning Chinese language and culture. Furthermore, it discusses the impact of using drama on changes in students' pervasive perceptions about unnecessity of Chinese classical literature. Third, this paper presents some sample lessons which may help teachers to develop understanding of how to organize lessons through drama. Finally, it illustrates university students' opinions about using drama to learn Chinese.

• Smart Media Journal
• /
• v.8 no.2
• /
• pp.74-79
• /
• 2019

Traditional compound noun decomposition algorithms often face challenges of decomposing compound nouns into separated nouns when unregistered unit noun is included. It is very difficult for those traditional approach to handle such issues because it is impossible to register all existing unit nouns into the dictionary such as proper nouns, coined words, and foreign words in advance. In this paper, in order to solve this problem, compound noun decomposition problem is defined as tag sequence labeling problem and compound noun decomposition method to use syllable unit embedding and deep learning technique is proposed. To recognize unregistered unit nouns without constructing unit noun dictionary, compound nouns are decomposed into unit nouns by using LSTM and linear-chain CRF expressing each syllable that constitutes a compound noun in the continuous vector space.