http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Study on Process of Creating 3D Models Using the Application of Artificial Intelligence Technology
Jiayuan Liang,Xinyi Shan,정진헌 국제문화기술진흥원 2023 International Journal of Advanced Culture Technolo Vol.11 No.4
With the rapid development of Artificial Intelligence (AI) technology, there is an increasing variety of methods for creating 3D models. These include innovations such as text-only generation, 2D images to 3D models, and combining images with cue words. Each of these methods has unique advantages, opening up new possibilities in the field of 3D modeling. The purpose of this study is to explore and summarize these methods in-depth, providing researchers and practitioners with a comprehensive perspective to understand the potential value of these methods in practical applications. Through a comprehensive analysis of pure text generation, 2D images to 3D models, and images with cue words, we will reveal the advantages and disadvantages of the various methods, as well as their applicability in different scenarios. Ultimately, this study aims to provide a useful reference for the future direction of AI modeling and to promote the innovation and progress of 3D model generation technology.
Exploring the Convergence and Innovation of AI Technology in Short Dramas Production
Jiayuan Liang,Xinyi Shan,정진헌 한국인터넷방송통신학회 2024 International journal of advanced smart convergenc Vol.13 No.3
In the context of exploring how Artificial Intelligence(AI) can revolutionize the entertainment industry, more and more film and television productions have begun to try to intervene AI technology in various aspects of content creation. However, despite the fact that AI can generate a large amount of textual content and dynamic visual effects, it still faces challenges in terms of plot expression and delivery. This thesis explores the strengths and weaknesses, innovations, and future developments of AI technology in plot production by analyzing existing film and television productions and production practices generated using AI technology. The study proves that as AI technology continues to improve, its use in short-form production will become more and more prevalent in the future, helping human creators become more efficient and even able to produce Short Dramas in full flow.
Wang Shanshan,Zou Xinyi,Zhu Wei,Zeng Liang 대한전기학회 2023 Journal of Electrical Engineering & Technology Vol.18 No.4
The safe operation of the power grid system depends partly on regular inspections of transmission lines, in which the insulator is one of the most important inspections objects. The manual inspection of transmission lines is a chaotic process that is both time and cost-consuming since it involves an accurate manual inspection by an expert. For insulator defect detection, an improved YOLOv4 algorithm is proposed. First, a new data augmentation method is proposed to solve the problem of insufficient sample size. Then, the size of the anchor boxes is redesigned base on the K-means algorithm to further improve the detection precision. Finally, an insulator defects detection network is constructed based on YOLOv4. Experimental results show that the detection precision of the improved network is 37.2% higher after data enhancement and anchor boxes redesign. In addition, the detection method proposed in this paper is superior to other popularity detection algorithms, including the single shot detector, region-convolutional neural networks (Faster-RCNN) and released version of you only look once (YOLO). The value of mean average precision is 99.08% and frame per second is 56. The robustness test results demonstrate that our proposed algorithm performs well under different light intensities and complex environmental backgrounds, and can accurately detect all targets, which is significantly better than other comparative algorithms. In terms of detection accuracy, test speed and robustness, our proposed algorithm meets the requirements of industrial field applications of insulator defect detection.