• Trans-
• /
• v.13
• /
• pp.1-16
• /
• 2022

Recently, the method of contacting and purchasing NFT art has been popularly evolving, and various prospects and predictions for NFT art have emerged. The discussion of NFT art is mainly a hot topic in terms of market size, profit, and sustainability. As the transition to digital accelerated after COVID-19, almost all genres of culture and arts faced a forced transition with the topic of combining digital and technology, but in terms of profitability, it was generally difficult to guarantee positive continuity. On the other hand, the combination of art and blockchain, and the new distribution method called NFT, attracted a lot of attention by causing fundamental changes that lead to technological transformation, continuity through profit creation, and even genre expansion of visual art. The discourse on NFT and the art market is a recent phenomenon and is being discussed focusing on statistics and numerical reports through data from newspapers and art-related research institutes rather than academic analysis or research. However, discussions related to NFT art should be considered in various aspects, such as the incorporation of technology and art, changes in distribution methods, and changes in creative methods according to media changes, not just short stories of phenomena such as high prices and winning bids. In this paper, we would like to examine the impact of changes in creators and distribution methods.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.166-172
• /
• 2022

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.2
• /
• pp.119-125
• /
• 2023

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.