Pub Date : 2022-06-01DOI: 10.1109/NicoInt55861.2022.00026
D. Miyazaki, Naoto Yoshimoto
We have proposed a method to remove specular reflection from a single polarization image. Most existing methods use color information for specular removal, however, those methods can neither be applied to monochrome images nor achromatic objects. To overcome this problem, we use polarization for specular removal. Most methods not only use polarization camera but also use polarized light, while we use polarization camera and unpolarized light. In addition to polarization, we also use a deep neural network to stably remove specular reflection in a grayscale image.
{"title":"Specular removal of monochrome image using polarization and deep learning","authors":"D. Miyazaki, Naoto Yoshimoto","doi":"10.1109/NicoInt55861.2022.00026","DOIUrl":"https://doi.org/10.1109/NicoInt55861.2022.00026","url":null,"abstract":"We have proposed a method to remove specular reflection from a single polarization image. Most existing methods use color information for specular removal, however, those methods can neither be applied to monochrome images nor achromatic objects. To overcome this problem, we use polarization for specular removal. Most methods not only use polarization camera but also use polarized light, while we use polarization camera and unpolarized light. In addition to polarization, we also use a deep neural network to stably remove specular reflection in a grayscale image.","PeriodicalId":328114,"journal":{"name":"2022 Nicograph International (NicoInt)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122190286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we propose a VR Aquarium, a marine environment experiencing system using fish swimming simulation, which reproduces the situation of fishes living in an underwater cave using 12 kinds of swimming simulations and provides an immersive aquarium-like scene to experience the underwater environment and learn more about biodiversity, including interactive design such as virtual hands and touch controls. The system proposed in this paper provides an interactive experience in a virtual space that is ideal for learning, without the limitations of places that are difficult to actually visit, such as underwater caves, or the unpredictability of when fish will appear. By interacting with the fish, the user can experience it as if they were actually present, which enhances the sense of immersion. In addition, the immersive experience of the VR system has a positive impact on the learning effect, which may ultimately increase the interest of the experiencer in marine life.
{"title":"Marine Environment Experiencing System Based On Fish Swimming Simulation","authors":"WenJu Sun, Yue Yu, Yuya Kinoshita, Junichi Hoshino","doi":"10.1109/NicoInt55861.2022.00019","DOIUrl":"https://doi.org/10.1109/NicoInt55861.2022.00019","url":null,"abstract":"In this paper, we propose a VR Aquarium, a marine environment experiencing system using fish swimming simulation, which reproduces the situation of fishes living in an underwater cave using 12 kinds of swimming simulations and provides an immersive aquarium-like scene to experience the underwater environment and learn more about biodiversity, including interactive design such as virtual hands and touch controls. The system proposed in this paper provides an interactive experience in a virtual space that is ideal for learning, without the limitations of places that are difficult to actually visit, such as underwater caves, or the unpredictability of when fish will appear. By interacting with the fish, the user can experience it as if they were actually present, which enhances the sense of immersion. In addition, the immersive experience of the VR system has a positive impact on the learning effect, which may ultimately increase the interest of the experiencer in marine life.","PeriodicalId":328114,"journal":{"name":"2022 Nicograph International (NicoInt)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132109294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-01DOI: 10.1109/NicoInt55861.2022.00037
Yuki Nemoto, Yasuhiro Inoue
Someone to meet you is an installation that the viewer encounters the presence of a person impressively by watching a faint silhouette through the occlusion of translucent surface. In this research, a method is proposed to quantitatively evaluate the effect of the occluded space in this art work as the creation of uncertainty for the visual space reconstructed by moving stereo vision on the 3D model environment. In order to develop a technique for presenting impressive information using uncertain space as a medium, the information entropy obtained in the evaluating process is used as an index to design the arrangement of uncertainty area in the environment.
{"title":"Someone to meet you: Introspective Encounter with the Presence of Someone from Uncertain Spatial Void","authors":"Yuki Nemoto, Yasuhiro Inoue","doi":"10.1109/NicoInt55861.2022.00037","DOIUrl":"https://doi.org/10.1109/NicoInt55861.2022.00037","url":null,"abstract":"Someone to meet you is an installation that the viewer encounters the presence of a person impressively by watching a faint silhouette through the occlusion of translucent surface. In this research, a method is proposed to quantitatively evaluate the effect of the occluded space in this art work as the creation of uncertainty for the visual space reconstructed by moving stereo vision on the 3D model environment. In order to develop a technique for presenting impressive information using uncertain space as a medium, the information entropy obtained in the evaluating process is used as an index to design the arrangement of uncertainty area in the environment.","PeriodicalId":328114,"journal":{"name":"2022 Nicograph International (NicoInt)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115087211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-01DOI: 10.1109/NicoInt55861.2022.00020
Daiki Fukushima, Tomokazu Ishikawa
Recently, machine learning has been used to improve the accuracy of computer vision, and the latest network model, Transformer, has been widely used in the fields of natural language translation and object recognition. A feature of ViT used in the field of object recognition is that its accuracy is improved by accumulating layers of Transformers. However, the latest models of the previous study of object tracking show that the accuracy decreases as the layers of the Transformer are accumulated. Therefore, in this study, we thought that the accuracy could be improved by changing the experimental conditions while the layers of transformers are accumulated. In addition, by searching for hyperparameters in the loss function, we expect to further improve the accuracy. The experimental results show that the accuracy can be improved by 5% by adjusting the parameters of regression loss and loss on bounding box size. Also, the model used in this study has a problem that the accuracy decreased by up to 7% when the number of Transformer layers is increased. Although the accuracy improved by 2% compared to the model without adjusting the parameters when the parameters of the loss function are adjusted with the number of Transformer layers increased.
{"title":"Experiments And Discussions On Vision Transformer (ViT) Parameters For Object Tracking","authors":"Daiki Fukushima, Tomokazu Ishikawa","doi":"10.1109/NicoInt55861.2022.00020","DOIUrl":"https://doi.org/10.1109/NicoInt55861.2022.00020","url":null,"abstract":"Recently, machine learning has been used to improve the accuracy of computer vision, and the latest network model, Transformer, has been widely used in the fields of natural language translation and object recognition. A feature of ViT used in the field of object recognition is that its accuracy is improved by accumulating layers of Transformers. However, the latest models of the previous study of object tracking show that the accuracy decreases as the layers of the Transformer are accumulated. Therefore, in this study, we thought that the accuracy could be improved by changing the experimental conditions while the layers of transformers are accumulated. In addition, by searching for hyperparameters in the loss function, we expect to further improve the accuracy. The experimental results show that the accuracy can be improved by 5% by adjusting the parameters of regression loss and loss on bounding box size. Also, the model used in this study has a problem that the accuracy decreased by up to 7% when the number of Transformer layers is increased. Although the accuracy improved by 2% compared to the model without adjusting the parameters when the parameters of the loss function are adjusted with the number of Transformer layers increased.","PeriodicalId":328114,"journal":{"name":"2022 Nicograph International (NicoInt)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116331252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-01DOI: 10.1109/NicoInt55861.2022.00032
Takuto Machida, A. Ito, Koji Mikami
In this study, two theoretical studies were combined. On the music theory side, we used Neo-Riemannian theory to analyze the music, and Bayesian networks on the mathematics side. R was used to construct the Bayesian network. Using these two methods, we have developed a mathematical model of musical transitions, and have also attempted to create music based on the probability of chord progressions.
{"title":"Research on Music Transition Using Neo- Riemannian Theory and Bayesian Network","authors":"Takuto Machida, A. Ito, Koji Mikami","doi":"10.1109/NicoInt55861.2022.00032","DOIUrl":"https://doi.org/10.1109/NicoInt55861.2022.00032","url":null,"abstract":"In this study, two theoretical studies were combined. On the music theory side, we used Neo-Riemannian theory to analyze the music, and Bayesian networks on the mathematics side. R was used to construct the Bayesian network. Using these two methods, we have developed a mathematical model of musical transitions, and have also attempted to create music based on the probability of chord progressions.","PeriodicalId":328114,"journal":{"name":"2022 Nicograph International (NicoInt)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132938631","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Urushi is a type of natural resin paint. It has been traditionally used to coat wooden crafts to protect them from degradation. A craft coated with urushi, called urushi-ware, has been used for centuries for daily necessities and has aspects of a work of art because it has a beautiful gloss and smooth feel on the surface. The goal of our study is to develop a set of techniques that allow designers to fabricate an urushi-ware with true interactivity, which can present visual information to provide an urushi-ware with both inputs and outputs while maintaining a beautiful gloss and a smooth feel on the surface. In this study, to achieve the above goal, we developed a technique for presenting visual information on urushi-ware. We create thermochromic colored urushi by mixing thermochromic pigments with a “Clear Urushi”. We conducted a pilot study to quantitatively evaluate the color change of thermochromic colored urushi with temperature. The result suggests that people could perceive a color change in thermochromic colored urushi.
{"title":"Prototyping an Urushi Display that Changes Color Interactively by Temperature Control","authors":"Hinako Nozaki, Ryo Ikeda, Yoshiki Nishikawa, Yuichi Atarashi, Yuki Hashimoto, B. Shizuki","doi":"10.1109/NicoInt55861.2022.00021","DOIUrl":"https://doi.org/10.1109/NicoInt55861.2022.00021","url":null,"abstract":"Urushi is a type of natural resin paint. It has been traditionally used to coat wooden crafts to protect them from degradation. A craft coated with urushi, called urushi-ware, has been used for centuries for daily necessities and has aspects of a work of art because it has a beautiful gloss and smooth feel on the surface. The goal of our study is to develop a set of techniques that allow designers to fabricate an urushi-ware with true interactivity, which can present visual information to provide an urushi-ware with both inputs and outputs while maintaining a beautiful gloss and a smooth feel on the surface. In this study, to achieve the above goal, we developed a technique for presenting visual information on urushi-ware. We create thermochromic colored urushi by mixing thermochromic pigments with a “Clear Urushi”. We conducted a pilot study to quantitatively evaluate the color change of thermochromic colored urushi with temperature. The result suggests that people could perceive a color change in thermochromic colored urushi.","PeriodicalId":328114,"journal":{"name":"2022 Nicograph International (NicoInt)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123785426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-01DOI: 10.1109/NicoInt55861.2022.00038
Saki Sakaguchi
We propose a method that can partially conceal a real environment by projection mapping and selectively show it to a specific user. This paper presents a prototype system that conceals paper documents by projection, and only users wearing active shutter-type 3D glasses, which open the shutter when the projected image is off in accordance with the blinking of the projected image, will be able to see the concealed area.
{"title":"Basic Study on Creation of Personal Vision by Projection Mapping","authors":"Saki Sakaguchi","doi":"10.1109/NicoInt55861.2022.00038","DOIUrl":"https://doi.org/10.1109/NicoInt55861.2022.00038","url":null,"abstract":"We propose a method that can partially conceal a real environment by projection mapping and selectively show it to a specific user. This paper presents a prototype system that conceals paper documents by projection, and only users wearing active shutter-type 3D glasses, which open the shutter when the projected image is off in accordance with the blinking of the projected image, will be able to see the concealed area.","PeriodicalId":328114,"journal":{"name":"2022 Nicograph International (NicoInt)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127517077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-01DOI: 10.1109/NicoInt55861.2022.00023
Midori Watanabe, Narumi Kuroko, Hayato Ohya, T. Itoh
Research and services on automatic music classification and recommendation have been active in recent years. Here, it is often unclear what kind of metadata and acoustic features strongly contribute to the feasibility of music classification and recommendation. Based on this discussion, we are working on the visualization of music pieces with metadata, acoustic features, machine learning methods, and visualization methods that are effective for music classification tasks, exploring whether new relationships between acoustic features and metadata can be discovered through visualization. Specifically, we calculated the acoustic features of a set of songs using music analysis tools and machine learning techniques, and visualized the distribution of the acoustic features and metadata. In this paper, we present the experimental results visualizing the relationship between acoustic features and metadata including released year, composer name, and artist name.
{"title":"Visualization of the Relationship between Metadata and Acoustic Feature Values of Song Collections*","authors":"Midori Watanabe, Narumi Kuroko, Hayato Ohya, T. Itoh","doi":"10.1109/NicoInt55861.2022.00023","DOIUrl":"https://doi.org/10.1109/NicoInt55861.2022.00023","url":null,"abstract":"Research and services on automatic music classification and recommendation have been active in recent years. Here, it is often unclear what kind of metadata and acoustic features strongly contribute to the feasibility of music classification and recommendation. Based on this discussion, we are working on the visualization of music pieces with metadata, acoustic features, machine learning methods, and visualization methods that are effective for music classification tasks, exploring whether new relationships between acoustic features and metadata can be discovered through visualization. Specifically, we calculated the acoustic features of a set of songs using music analysis tools and machine learning techniques, and visualized the distribution of the acoustic features and metadata. In this paper, we present the experimental results visualizing the relationship between acoustic features and metadata including released year, composer name, and artist name.","PeriodicalId":328114,"journal":{"name":"2022 Nicograph International (NicoInt)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126934703","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-01DOI: 10.1109/NicoInt55861.2022.00028
Hisashi Ishihara, Takanori Nagae
Today game engines deal with not only game contents or assets, but also gain the ability to play music. We will soon see that the DAW (digital audio workstation) and the game engine will be merged into a more general and sophisticated musical environment. The authors are developing a prototype ensemble system in which several client PCs are managed with a REST http server. Each client plays its cello, piano, or some synthesizer part conducted by the server. The clients also send control signals to others to change the tempo, rhythm or pitch improvisationally. Experimental results show that the Modular Synth component in the Unreal Engine 4 can play pieces of chamber music composed by the authors almost synchronously via LAN.
{"title":"An Autonomous Musical System via REST API Network","authors":"Hisashi Ishihara, Takanori Nagae","doi":"10.1109/NicoInt55861.2022.00028","DOIUrl":"https://doi.org/10.1109/NicoInt55861.2022.00028","url":null,"abstract":"Today game engines deal with not only game contents or assets, but also gain the ability to play music. We will soon see that the DAW (digital audio workstation) and the game engine will be merged into a more general and sophisticated musical environment. The authors are developing a prototype ensemble system in which several client PCs are managed with a REST http server. Each client plays its cello, piano, or some synthesizer part conducted by the server. The clients also send control signals to others to change the tempo, rhythm or pitch improvisationally. Experimental results show that the Modular Synth component in the Unreal Engine 4 can play pieces of chamber music composed by the authors almost synchronously via LAN.","PeriodicalId":328114,"journal":{"name":"2022 Nicograph International (NicoInt)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129700510","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-01DOI: 10.1109/NicoInt55861.2022.00025
Luna Yoshizawa, Hiroyuki Kubo
Spherical display is used in various places such as science museums. In this research, we develop a method to express the transparency on a spherical display using background image abstracting.
{"title":"Transparency Expression on Spherical Displays using Background Image Abstracting","authors":"Luna Yoshizawa, Hiroyuki Kubo","doi":"10.1109/NicoInt55861.2022.00025","DOIUrl":"https://doi.org/10.1109/NicoInt55861.2022.00025","url":null,"abstract":"Spherical display is used in various places such as science museums. In this research, we develop a method to express the transparency on a spherical display using background image abstracting.","PeriodicalId":328114,"journal":{"name":"2022 Nicograph International (NicoInt)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127849201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：