• 방송공학회논문지
• /
• 제27권5호
• /
• pp.654-664
• /
• 2022

실감 콘텐츠는 COVID-19 팬데믹으로 인한 관심과 더불어 확장현실, 인공지능, 포토그래메트리 기술과 융합을 통해 공간적 한계를 극복하며 엔터테인먼트, 미디어, 공연, 전시 등 콘텐츠 시장에서 새로운 패러다임을 제시하며 수요 역시 증가하고 있다. 하지만 실감 콘텐츠가 대중들에게 지속된 관심을 가지기 위해서는 기술적 신선함보다 콘텐츠에 대한 몰입도를 높일 수 있는 스토리텔링 방법 연구가 필요하다는 것을 알 수 있다. 따라서 본 연구에서는 인공지능 및 포토그래메트리 기술을 활용한 실감 콘텐츠 스토리텔링 방법을 제안한다. 제안된 스토리텔링 방법은 대화형 가상존재와 참여자가 대화를 통한 상호작용으로 콘텐츠 스토리를 생성하는 것이다. 이에 관객 주도적 참여를 통해 콘텐츠 몰입도를 높일 수 있다. 본 연구는 가속화되는 실감 콘텐츠 시장에서 콘텐츠 제작자들에게 제안된 인공지능 기술이 활용된 가상존재를 통한 스토리텔링 방법론으로 효율적인 콘텐츠 제작에 도움을 줄 수 있을 것으로 기대한다. 또한 콘텐츠 제작에 있어 인공지능 및 포토그래메트리 기술을 활용한 실감 콘텐츠 제작 파이프라인 정립에 기여할 것이라고 생각한다.

• International Journal of Advanced Culture Technology
• /
• 제11권2호
• /
• pp.178-185
• /
• 2023

The Chinese calligraphy art, which still adheres to tradition, has fallen into the formalism deeper and deeper. The majority of studies on calligraphy still focus on the formal beauty and neglect the core spirit hidden behind the calligraphy art. The calligraphy art is an art defined by words. This definition is not only reflected in the form of the characters but also, and more importantly, in the meaning of the characters. It is not a form of writing, but a writing of lives, wills and feelings, a writing of the experience of daily life, and an improvised poetic writing. With the advent of the age of artificial intelligence, the Chinese traditional calligraphy art, which still adheres to the "supremacy of the brush and ink", has shown a sense of dystopia, and its end is inevitable. Only by truly understanding the core of the calligraphy art, by integrating it with contemporary daily life, and by focusing on the communication of ideas in calligraphy, will it be possible to obtain a new life.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2022년도 하계학술대회
• /
• pp.205-208
• /
• 2022

Multi-exposure high dynamic range (HDR) image reconstruction, the task of reconstructing an HDR image from multiple low dynamic range (LDR) images in a dynamic scene, often produces ghosting artifacts caused by camera motion and moving objects and also cannot deal with washed-out regions due to over or under-exposures. While there has been many deep-learning-based methods with motion estimation to alleviate these problems, they still have limitations for severely moving scenes. They also require large parameter counts, especially in the case of state-of-the-art methods that employ attention modules. To address these issues, we propose a frequency domain approach based on the idea that the transform domain coefficients inherently involve the global information from whole image pixels to cope with large motions. Specifically we adopt Residual Fast Fourier Transform (RFFT) blocks, which allows for global interactions of pixels. Moreover, we also employ Depthwise Overparametrized convolution (DO-conv) blocks, a convolution in which each input channel is convolved with its own 2D kernel, for faster convergence and performance gains. We call this LFFNet (Lightweight Frequency Fusion Network), and experiments on the benchmarks show reduced ghosting artifacts and improved performance up to 0.6dB tonemapped PSNR compared to recent state-of-the-art methods. Our architecture also requires fewer parameters and converges faster in training.

• International Journal of Advanced Culture Technology
• /
• 제12권1호
• /
• pp.123-127
• /
• 2024

In the early 20th century, Walter Benjamin analyzed the changes in the value of traditional art forms under the industrial era and the changes in the aesthetic attitude of the masses. A century later, in the contemporary multi-art world, the traditional medium of shelf painting is once again experiencing a similar situation as the last century. Emerging technology display modes such as digital virtual reality and digital immersive experience can achieve digital reproduction of paintings on shelves and reach a certain level of performance, which once again shocks the public's aesthetic perception. This paper attempts to illustrate the outstanding characteristics of the new art form after digital reconstruction by exploring the transformation and sublimation of digital technology to shelf painting. We predict that art research on future reality and augmented reality according to the artificial intelligence era will be conducted in depth in the future.

• ETRI Journal
• /
• 제44권3호
• /
• pp.476-490
• /
• 2022

With the recent advances in technology, automatic speech recognition (ASR) has been widely used in real-world applications. The efficiency of converting large amounts of speech into text accurately with limited resources has become more vital than ever. In this study, we propose a method to rapidly recognize a large speech database via a transformer-based end-to-end model. Transformers have improved the state-of-the-art performance in many fields. However, they are not easy to use for long sequences. In this study, various techniques to accelerate the recognition of real-world speeches are proposed and tested, including decoding via multiple-utterance-batched beam search, detecting end of speech based on a connectionist temporal classification (CTC), restricting the CTC-prefix score, and splitting long speeches into short segments. Experiments are conducted with the Librispeech dataset and the real-world Korean ASR tasks to verify the proposed methods. From the experiments, the proposed system can convert 8 h of speeches spoken at real-world meetings into text in less than 3 min with a 10.73% character error rate, which is 27.1% relatively lower than that of conventional systems.

• International Journal of Internet, Broadcasting and Communication
• /
• 제16권1호
• /
• pp.80-85
• /
• 2024

The concept of single-modal digital art originated in the 20th century and has evolved through three key stages. Over time, digital art has transformed into multi-modal interaction, representing a new era in art forms. Based on multi-modal theory, this paper aims to explore the characteristics of interactive digital art in innovative art forms and its impact on user experience. Through an analysis of practical application of multi-modal interactive digital art, this study summarises the impact of creative models of digital art on the physical and mental aspects of user experience. In creating audio-visual-based art, multi-modal digital art should seamlessly incorporate sensory elements and leverage computer image processing technology. Focusing on user perception, emotional expression, and cultural communication, it strives to establish an immersive environment with user experience at its core. Future research, particularly with emerging technologies like Artificial Intelligence(AR) and Virtual Reality(VR), should not merely prioritize technology but aim for meaningful interaction. Through multi-modal interaction, digital art is poised to continually innovate, offering new possibilities and expanding the realm of interactive digital art.

• 전자통신동향분석
• /
• 제33권6호
• /
• pp.107-117
• /
• 2018

In recent years, with the development of autonomous driving technology, high-performance artificial intelligence computing hardware platforms have been developed that can process multi-sensor data, object recognition, and vehicle control for autonomous vehicles. Most of these hardware platforms have been developed overseas, such as NVIDIA's DRIVE PX, Audi's zFAS, Intel GO, Mobile Eye's EyeQ, and BAIDU's Apollo Pilot. In Korea, however, ETRI's artificial intelligence computing platform has been developed. In this paper, we discuss the specifications, structure, performance, and development status centering on hardware platforms that support autonomous driving rather than the overall contents of autonomous driving technology.

• Journal of Information Processing Systems
• /
• 제17권3호
• /
• pp.453-461
• /
• 2021

Many deep learning approaches have been studied for image classification in computer vision. However, there are not enough data to generate accurate models in medical fields, and many datasets are not annotated. This study presents a new method that can use both unlabeled and labeled data. The proposed method is applied to classify cervix images into normal versus cancerous, and we demonstrate the results. First, we use a patch self-supervised learning for training the global context of the image using an unlabeled image dataset. Second, we generate a classifier model by using the transferred knowledge from self-supervised learning. We also apply attention learning to capture the local features of the image. The combined method provides better performance than state-of-the-art approaches in accuracy and sensitivity.

• International journal of advanced smart convergence
• /
• 제12권2호
• /
• pp.90-95
• /
• 2023

With the rapid development of deep learning and artificial intelligence, generative models have achieved remarkable success in the field of image generation. By combining the stable diffusion method with Web UI technology, a novel solution is provided for the application of AI painting generation. The application prospects of this technology are very broad and can be applied to multiple fields, such as digital art, concept design, game development, and more. Furthermore, the platform based on Web UI facilitates user operations, making the technology more easily applicable to practical scenarios. This paper introduces the basic principles of Stable Diffusion Web UI technology. This technique utilizes the stability of diffusion processes to improve the output quality of generative models. By gradually introducing noise during the generation process, the model can generate smoother and more coherent images. Additionally, the analysis of different model types and applications within Stable Diffusion Web UI provides creators with a more comprehensive understanding, offering valuable insights for fields such as artistic creation and design.

• Smart Structures and Systems
• /
• 제13권1호
• /
• pp.81-98
• /
• 2014

This paper presents the elastic buckling of smart lightweight column structures integrated with a pair of surface piezoelectric layers using artificial intelligence. The finite element modeling of Smart lightweight columns is found using $ANSYS^{(R)}$ software. Then, the first buckling load of the structure is calculated using eigenvalue buckling analysis. To determine the accuracy of the present finite element analysis, a compression study is carried out with literature. Later, parametric studies for length variations, width, and thickness of the elastic core and of the piezoelectric outer layers are performed and the associated buckling load data sets for artificial intelligence are gathered. Finally, the application of soft computing-based methods including artificial neural network (ANN), fuzzy inference system (FIS), and adaptive neuro fuzzy inference system (ANFIS) were carried out. A comparative study is then made between the mentioned soft computing methods and the performance of the models is evaluated using statistic measurements. The comparison of the results reveal that, the ANFIS model with Gaussian membership function provides high accuracy on the prediction of the buckling load in smart lightweight columns, providing better predictions compared to other methods. However, the results obtained from the ANN model using the feed-forward algorithm are also accurate and reliable.