• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.6
• /
• pp.137-144
• /
• 2020

As the spread of COVID-19, the demand for interactive online class is increasing. Universities are introducing various types of online classes, but many problems arise in the field. Learners complain about the quality of the lecture, and professors have difficulty in preparing and conducting online classes. This study analyzed teaching & learning situation in interactive online class and drew teacher's pain point through case studies. Also, we suggested a method to solve the problem divided into a systemic approach and an administrative approach. The stable settlement of interactive online lectures is expected to accelerate the digital transformation of universities.

• Journal of Information Technology Applications and Management
• /
• v.29 no.1
• /
• pp.59-70
• /
• 2022

Recently, in platforms such as YouTube and Instagram, virtual characters resembling human life become the main characters, produce various contents, breathe with the public, and create the era of virtual humans. For example, existing game characters appear as virtual characters with unique AUs, or AI characters created by reflecting the public's preferences are actively communicating with the public through advertisements and SNS activities. As the consumption of video content through smart devices increases significantly in the post-corona era, virtual influencers are being used as all-round entertainers because there is little risk of personality controversy or production cost. there is a trend In this study, we investigated the characteristics of the case of being active as an influencer among the activities of a virtual character, and how the interactive aspect of the influencer appears by identifying the current situation through major cases. Combining this, based on the analysis of the influence of virtual influencers, the parts that producers should recognize are derived, and the differentiated characteristics of interactive virtual influencers are summarized. In addition, the difficulties of virtual influencers were investigated and problems were identified, and for the development of the content industry, a more favorable method for interaction was presented and suggestions were made to secure inner sincerity.

• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.81-89
• /
• 2023

In modern society, blind people face difficulties in navigating common environments such as sidewalks, elevators, and crosswalks. Research has been conducted to alleviate these inconveniences for the visually impaired through the use of visual and audio aids. However, such research often encounters limitations when it comes to practical implementation due to the high cost of wearable devices, high-performance CCTV systems, and voice sensors. In this paper, we propose an artificial intelligence fusion algorithm that utilizes low-cost video sensors integrated into smartphones to help blind people safely navigate their surroundings during walking. The proposed algorithm combines motion capture and object detection algorithms to detect moving people and various obstacles encountered during walking. We employed the MediaPipe library for motion capture to model and detect surrounding pedestrians during motion. Additionally, we used object detection algorithms to model and detect various obstacles that can occur during walking on sidewalks. Through experimentation, we validated the performance of the artificial intelligence fusion algorithm, achieving accuracy of 0.92, precision of 0.91, recall of 0.99, and an F1 score of 0.95. This research can assist blind people in navigating through obstacles such as bollards, shared scooters, and vehicles encountered during walking, thereby enhancing their mobility and safety.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1109-1116
• /
• 2023

Object tracking is used to track a goal in a video sequence by using coordinate information provided as annotation in the first frame of the video. In this paper, we propose a tracking algorithm that combines deep features and region inference modules to improve object tracking accuracy. In order to obtain sufficient object information, a convolution neural network was designed with a Siamese network structure. For object region inference, the region proposal network and overlapping confidence module were applied and used for tracking. The performance of the proposed tracking algorithm was evaluated using the Object Tracking Benchmark dataset, and it achieved 69.1% in the Success index and 89.3% in the Precision Metrics.

• Journal of Broadcast Engineering
• /
• v.24 no.6
• /
• pp.983-991
• /
• 2019

This study aims to analyze movies which contain various stories according to the size of their shots. To achieve this, it is needed to classify dataset according to the shot size, such as extreme close-up shots, close-up shots, medium shots, full shots, and long shots. However, a typical video storytelling is mainly composed of close-up shots, medium shots, full shots, and long shots, it is not an easy task to construct an appropriate dataset for extreme close-up shots. To solve this, we propose an image cropping method based on the region of interest (ROI) detection. In this paper, we use the face detection and saliency detection to estimate the ROI. By cropping the ROI of close-up images, we generate extreme close-up images. The dataset which is enriched by proposed method is utilized to construct a model for classifying shots based on its size. The study can help to analyze the emotional changes of characters in video stories and to predict how the composition of the story changes over time. If AI is used more actively in the future in entertainment fields, it is expected to affect the automatic adjustment and creation of characters, dialogue, and image editing.

• Journal of Korea Multimedia Society
• /
• v.12 no.2
• /
• pp.290-299
• /
• 2009

Evolutionary Artificial Neural Networks (EANNs) has been highly effective in Artificial Intelligence (AI) and in training NPCs in video games. When EANNs is applied to design game NPCs' smart AI which can make the game more interesting, there always comes two important problems: the more complex situation NPCs are in, the more complex structure of neural networks needed which leads to large operation cost. In this paper, the Dynamic State Evolutionary Neural Networks (DSENNs) is proposed based on EANNs which deletes or fixes the connection of the neurons to reduce the operation cost in evolution and evaluation process. Darwin Platform is chosen as our test bed to show its efficiency: Darwin offers the competitive team game playing behaviors by teams of virtual football game players.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.18 no.1
• /
• pp.55-64
• /
• 2022

This study analyzes the success factors of OTT original content through big data, and intends to suggest scenarios, casting, fun, and moving elements when producing the next work. In addition, I would like to offer suggestions for the success of 'Squid Game Season 2'. The success factor of 'Squid Game' through big data is first, it is a simple psychological experimental game. Second, it is a retro strategy. Third, modern visual beauty and color. Fourth, it is simple aesthetics. Fifth, it is the platform of OTT Netflix. Sixth, Netflix's video recommendation algorithm. Seventh, it induced Binge-Watch. Lastly, it can be said that the consensus was high as it was related to the time to think about 'death' and 'money' in a pandemic situation. The suggestions for 'Squid Game Season 2' are as follows. First, it is a fusion of famous traditional games of each country. Second, it is an AI-based planned MD product production and sales strategy. Third, it is casting based on artificial intelligence big data. Fourth, secondary copyright and copyright sales strategy. The limitations of this study were analyzed only through external data. Data inside the Netflix platform was not utilized. In this study, if AI big data is used not only in the OTT field but also in entertainment and film companies, it will be possible to discover better business models and generate stable profits.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.11
• /
• pp.1577-1585
• /
• 2022

As the interest in the 4th industrial revolution and metaverse increases, metaverse with multi edge structure is proposed and noted. Metaverse is a structure that can create digital doctor-like system through a large amount of image processing and data transmission in a multi edge system. Since metaverse application requires calculating performance, which can reconstruct 3-D space, edge hardware's insufficient calculating performance has been a problem. To provide streamable AI software in runtime, image processing, and data transmission, which is edge's loads, needs to be lightweight. Also lightweight at the edge leads to power consumption reduction of the entire metaverse application system. In this paper, we propose collaborative edge-cloud image processing with remote image processing method and Region of Interest (ROI) to overcome edge's power performance and build streamable and runtime executable AI software. The proposed structure was implemented using a PC and an embedded board, and the reduction of time, power, and network communications were verified.

• Journal of Advanced Marine Engineering and Technology
• /
• v.38 no.1
• /
• pp.56-63
• /
• 2014

An offshore plant needs costly maintenance and has difficulty coping with various accidents coming from the exposure to the environmental threats such as typhoons, tidal waves and etc., in addition to the artificial ones such as fire, collision of ships and etc. In this paper, we develop the video-complex remote monitoring system for an offshore plant, using AtoN AIS and multi-stage database to monitor an offshore plant and solve those problems. The system handles real time video cameras to collect and monitor images on an offshore plant. So, users can be exactly and quickly aware of the information on various situations with the monitoring application based on ENC.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.3A
• /
• pp.337-344
• /
• 2006

In this paper, we propose a multi-view video codec for 3DTV system. The proposed algorithm is not only to reduce the temporal and spatial redundancy but also to reduce the redundancy among each view. With these results, we can improve the coding efficiency for multi-view video sequences. In order to reduce the redundancy of each view more efficiently, we define the assembled image(AI) that is generated by the global disparity compensation of each view. In addition, the proposed algorithm is based on MPEG-2 structure so that we can easily implement 3DTV system without changing the conventional 2D digital TV system. Experimental results show that the proposed algorithm performs very well. It also performs better than MPEG-2 simulcast coding method. The newly proposed codec also supports the view scalability, accurate temporal synchronization among multiple views and random access capability in view dimension.