Pub Date : 2019-07-01DOI: 10.1109/NICOInt.2019.00015
Megumi Kido, Hiroki Takahashi
Laundry folding has the role that makes laundry compact and easy to store. It is, however, less preferred than other housework. This paper, therefore, describes to present folding procedure by using clothing model fitting for laundry folding assistance. A clothing model is constituted by mesh, where each node has its state transition, in order to handle cloth folding procedures with the same model. The clothing model fits on a contour of a target clothes generated by background subtraction. After that, each node is relocated to the optimal position to minimize a sum of some energy functions. IoU(Intersection over Union) is greater than 0.97 for all test images and the average difference of the folds becomes 2.3 pixels.
衣物折叠有使衣物紧凑和易于储存的作用。然而，与其他家务劳动相比，家务劳动不那么受欢迎。因此，本文描述了目前的折叠程序，利用服装模型拟合洗衣折叠辅助。服装模型由网格构成，网格中的每个节点都有自己的状态转换，以便用相同的模型处理布料折叠过程。该服装模型拟合在通过背景减法生成的目标服装轮廓上。然后，将每个节点重新定位到最优位置，以最小化一些能量函数的和。所有测试图像的IoU(Intersection over Union)均大于0.97，折叠的平均差为2.3像素。
{"title":"Clothing Model Fitting for Laundry Folding Assistance","authors":"Megumi Kido, Hiroki Takahashi","doi":"10.1109/NICOInt.2019.00015","DOIUrl":"https://doi.org/10.1109/NICOInt.2019.00015","url":null,"abstract":"Laundry folding has the role that makes laundry compact and easy to store. It is, however, less preferred than other housework. This paper, therefore, describes to present folding procedure by using clothing model fitting for laundry folding assistance. A clothing model is constituted by mesh, where each node has its state transition, in order to handle cloth folding procedures with the same model. The clothing model fits on a contour of a target clothes generated by background subtraction. After that, each node is relocated to the optimal position to minimize a sum of some energy functions. IoU(Intersection over Union) is greater than 0.97 for all test images and the average difference of the folds becomes 2.3 pixels.","PeriodicalId":436332,"journal":{"name":"2019 Nicograph International (NicoInt)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125751300","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 : 2019-07-01DOI: 10.1109/NICOInt.2019.00036
Rika Sumitomo, Mitsunori Matsushita
This paper proposes an optical material combination method to diversify the nature of shadows. The proposed method permits four types of catabolized shadows to be generated: those with fine detail, those with color, those with details changed according to the lighting direction, and those that appear on the near side of the object.
{"title":"Expanding the Characteristics of Shadows by Combining Optical Materials","authors":"Rika Sumitomo, Mitsunori Matsushita","doi":"10.1109/NICOInt.2019.00036","DOIUrl":"https://doi.org/10.1109/NICOInt.2019.00036","url":null,"abstract":"This paper proposes an optical material combination method to diversify the nature of shadows. The proposed method permits four types of catabolized shadows to be generated: those with fine detail, those with color, those with details changed according to the lighting direction, and those that appear on the near side of the object.","PeriodicalId":436332,"journal":{"name":"2019 Nicograph International (NicoInt)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123895310","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 : 2019-07-01DOI: 10.1109/NICOInt.2019.00026
Nan Geng, Xu Jiang, Xuemei Feng, Shaojun Hu, Long Yang, Zhiyi Zhang
Registration for tree point cloud presents a high registration error due to the complex structure of trees and serious self-shielding. The paper proposes a registration algorithm based on pseudo feature point. This algorithm includes two steps. In initial registration, we use pseudo feature points to adjust the position of two original point clouds quickly and roughly at first. However, pseudo feature points sometimes can't fully represent the feature of original point cloud owing to the noise, it leads to a high registration error obtained in initial registration, and then need to use the improved sparse iterative closest point algorithm to adjust two original point clouds again. Experiments show that the proposed algorithm can register both non-leafy tree and leafy tree. Compared with iterative closest point registration and sparse iterative closest point registration, the method significantly reduces the registration error by 41.1% and 16.8% respectively under the same number of iterations. The method can also register nonplant point cloud.
{"title":"Registration of Botanic Tree Point Cloud Based on Pseudo Feature Point","authors":"Nan Geng, Xu Jiang, Xuemei Feng, Shaojun Hu, Long Yang, Zhiyi Zhang","doi":"10.1109/NICOInt.2019.00026","DOIUrl":"https://doi.org/10.1109/NICOInt.2019.00026","url":null,"abstract":"Registration for tree point cloud presents a high registration error due to the complex structure of trees and serious self-shielding. The paper proposes a registration algorithm based on pseudo feature point. This algorithm includes two steps. In initial registration, we use pseudo feature points to adjust the position of two original point clouds quickly and roughly at first. However, pseudo feature points sometimes can't fully represent the feature of original point cloud owing to the noise, it leads to a high registration error obtained in initial registration, and then need to use the improved sparse iterative closest point algorithm to adjust two original point clouds again. Experiments show that the proposed algorithm can register both non-leafy tree and leafy tree. Compared with iterative closest point registration and sparse iterative closest point registration, the method significantly reduces the registration error by 41.1% and 16.8% respectively under the same number of iterations. The method can also register nonplant point cloud.","PeriodicalId":436332,"journal":{"name":"2019 Nicograph International (NicoInt)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130701941","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 : 2019-07-01DOI: 10.1109/NICOInt.2019.00007
Zhiyi Zhang, Di Wang, Ni Liu, Xuemei Feng, Nan Geng, Shaojun Hu
This paper presents a new method of linear structured light scanning combining monocular and binocular. The red moving light stripe projected by miniature projector is used to replace the traditional laser, which not only reduces hardware costs but is also easier to use. In order to obtain the light plane equation with high precision, the cylindrical paper tube is scanned in the binocular system, then in the monocular system, the three-dimensional point coordinates of the object are calculated according to the principle of transmission projection geometry. Experimental results show that this method can effectively balance the requirements of accuracy and speed, and has certain practical value.
{"title":"Research on 3D Point Cloud Data Acquisition Technology Based on Linear Structured Light","authors":"Zhiyi Zhang, Di Wang, Ni Liu, Xuemei Feng, Nan Geng, Shaojun Hu","doi":"10.1109/NICOInt.2019.00007","DOIUrl":"https://doi.org/10.1109/NICOInt.2019.00007","url":null,"abstract":"This paper presents a new method of linear structured light scanning combining monocular and binocular. The red moving light stripe projected by miniature projector is used to replace the traditional laser, which not only reduces hardware costs but is also easier to use. In order to obtain the light plane equation with high precision, the cylindrical paper tube is scanned in the binocular system, then in the monocular system, the three-dimensional point coordinates of the object are calculated according to the principle of transmission projection geometry. Experimental results show that this method can effectively balance the requirements of accuracy and speed, and has certain practical value.","PeriodicalId":436332,"journal":{"name":"2019 Nicograph International (NicoInt)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134022936","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 : 2019-07-01DOI: 10.1109/NICOInt.2019.00017
Haoran Xie, Atsushi Watatani, K. Miyata
In this paper, we propose a visual feedback system for core training using a monocular camera image. To support the user in maintaining the correct postures from target poses, we adopt 3D human shape estimation for both the target image and input camera video. Because it is expensive to capture human pose using depth cameras or multiple cameras using conventional approaches, we employ the skinned multi-person linear model of human shape to recover the 3D human pose from 2D images using pose estimation and human mesh recovery methods. We propose a user interface for providing visual guidance based on the estimated target and current human shapes. To clarify the differences between the target and current postures of 3D models, we adopt markers for visualization at ten body parts with color changes. From user studies conducted, the proposed visual feedback system is effective and convenient in performing core training.
{"title":"Visual Feedback for Core Training with 3D Human Shape and Pose","authors":"Haoran Xie, Atsushi Watatani, K. Miyata","doi":"10.1109/NICOInt.2019.00017","DOIUrl":"https://doi.org/10.1109/NICOInt.2019.00017","url":null,"abstract":"In this paper, we propose a visual feedback system for core training using a monocular camera image. To support the user in maintaining the correct postures from target poses, we adopt 3D human shape estimation for both the target image and input camera video. Because it is expensive to capture human pose using depth cameras or multiple cameras using conventional approaches, we employ the skinned multi-person linear model of human shape to recover the 3D human pose from 2D images using pose estimation and human mesh recovery methods. We propose a user interface for providing visual guidance based on the estimated target and current human shapes. To clarify the differences between the target and current postures of 3D models, we adopt markers for visualization at ten body parts with color changes. From user studies conducted, the proposed visual feedback system is effective and convenient in performing core training.","PeriodicalId":436332,"journal":{"name":"2019 Nicograph International (NicoInt)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123235266","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}
The Workshop’s goal is to gather together practitioners, researchers and people from industry to discuss the progresses on the research and on the practical usage of blockchain technologies and smart contracts, focusing on the application and definition of software engineering principles and practices specific for such software technology, and for the technologies relying on it. Such technologies are rapidly evolving and rise more and more interest among scientists, researchers and industry. The focus of BOSE is on the stil unsatisfactory application of specific software engineering development best practices to blockchain oriented software and in particular to Smart Contracts. These novelties cal for specific tools, paradigms, principles, approaches and research to deal with it and for a specific Blockchain Oriented Software Engineering (BOSE ) [1].
{"title":"Message from the Chairs","authors":"D. Zowghi, V. Gervasi, Sarah C. Gregory","doi":"10.1109/ECOWS.2005.16","DOIUrl":"https://doi.org/10.1109/ECOWS.2005.16","url":null,"abstract":"The Workshop’s goal is to gather together practitioners, researchers and people from industry to discuss the progresses on the research and on the practical usage of blockchain technologies and smart contracts, focusing on the application and definition of software engineering principles and practices specific for such software technology, and for the technologies relying on it. Such technologies are rapidly evolving and rise more and more interest among scientists, researchers and industry. The focus of BOSE is on the stil unsatisfactory application of specific software engineering development best practices to blockchain oriented software and in particular to Smart Contracts. These novelties cal for specific tools, paradigms, principles, approaches and research to deal with it and for a specific Blockchain Oriented Software Engineering (BOSE ) [1].","PeriodicalId":436332,"journal":{"name":"2019 Nicograph International (NicoInt)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133711807","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 : 2019-07-01DOI: 10.1109/NICOInt.2019.00020
Haruka Yajima, K. Ochi, Y. Obuchi
Surround sound provides realistic experiences, but it has a problem that it is hard to perceive the fore-aft direction. In addition, its reality and spatial recognition deeply depend on whether the listener is accustomed to the surround environment, and whether the listener has ever heard the sound. Therefore, in this study, we conducted a set of experiments of fore-aft perception in order to investigate the human perception of front and back. We examined the effect of visual information and the difference between familiar and unfamiliar sounds. Experimental results showed that the listener got accustomed to the surround environment and the number of misperception decreased gradually.
{"title":"Learning Effect of Fore-Aft Perception of Familiar and Unfamiliar Sounds","authors":"Haruka Yajima, K. Ochi, Y. Obuchi","doi":"10.1109/NICOInt.2019.00020","DOIUrl":"https://doi.org/10.1109/NICOInt.2019.00020","url":null,"abstract":"Surround sound provides realistic experiences, but it has a problem that it is hard to perceive the fore-aft direction. In addition, its reality and spatial recognition deeply depend on whether the listener is accustomed to the surround environment, and whether the listener has ever heard the sound. Therefore, in this study, we conducted a set of experiments of fore-aft perception in order to investigate the human perception of front and back. We examined the effect of visual information and the difference between familiar and unfamiliar sounds. Experimental results showed that the listener got accustomed to the surround environment and the number of misperception decreased gradually.","PeriodicalId":436332,"journal":{"name":"2019 Nicograph International (NicoInt)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130457675","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 : 2019-07-01DOI: 10.1109/NICOInt.2019.00011
Xin Lu, Chunyuan Li, Tsutomu Kinoshita, Akio Kimura, K. Konno
The Haniwa belong to one kind of terracotta figurines made in ancient Japan, which have been scanned and saved as 3D models composed of point cloud and triangular meshes for archaeology research. In order to align and analyze the face parts of the Haniwa, this paper proposes an ellipsoid-fitting-based segmentation method to extract the nose points, and a hole detection method to locate the contours of eyes and mouth. Our experiments show the proposed methods can be used to achieve the face alignment for the Haniwa with high precision, and make the corresponding face analysis a reality.
{"title":"3D Face Alignment for Japanese Terracotta Figurines (Haniwa)","authors":"Xin Lu, Chunyuan Li, Tsutomu Kinoshita, Akio Kimura, K. Konno","doi":"10.1109/NICOInt.2019.00011","DOIUrl":"https://doi.org/10.1109/NICOInt.2019.00011","url":null,"abstract":"The Haniwa belong to one kind of terracotta figurines made in ancient Japan, which have been scanned and saved as 3D models composed of point cloud and triangular meshes for archaeology research. In order to align and analyze the face parts of the Haniwa, this paper proposes an ellipsoid-fitting-based segmentation method to extract the nose points, and a hole detection method to locate the contours of eyes and mouth. Our experiments show the proposed methods can be used to achieve the face alignment for the Haniwa with high precision, and make the corresponding face analysis a reality.","PeriodicalId":436332,"journal":{"name":"2019 Nicograph International (NicoInt)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132449188","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 : 2019-07-01DOI: 10.1109/NICOInt.2019.00034
Yoshina Takano, Hideyasu Inoue, R. Thawonmas, Tomohiro Harada
In this paper, we train a general fighting game AI from self-play games to outperform an unseen opponent AI. It has been reported that an AI using Deep Q Network (DQN) can outperform the training partner. However, according to our experience, the DQN AI is not always superior to a new opponent, unseen before. By learning from self-play, we overcome this drawback while maintaining the DQN AI’s strong points. Our experimental results show that it is more effective to use a variety of AIs with different behaviors as training partners.
{"title":"Self-Play for Training General Fighting Game AI","authors":"Yoshina Takano, Hideyasu Inoue, R. Thawonmas, Tomohiro Harada","doi":"10.1109/NICOInt.2019.00034","DOIUrl":"https://doi.org/10.1109/NICOInt.2019.00034","url":null,"abstract":"In this paper, we train a general fighting game AI from self-play games to outperform an unseen opponent AI. It has been reported that an AI using Deep Q Network (DQN) can outperform the training partner. However, according to our experience, the DQN AI is not always superior to a new opponent, unseen before. By learning from self-play, we overcome this drawback while maintaining the DQN AI’s strong points. Our experimental results show that it is more effective to use a variety of AIs with different behaviors as training partners.","PeriodicalId":436332,"journal":{"name":"2019 Nicograph International (NicoInt)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123266944","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 : 2019-07-01DOI: 10.1109/NICOInt.2019.00023
Mingwei Cai, R. Sato, Kenji Yoshida, K. Takayasu
It is a must-have content for medical students to attend school at the surgery site. It enables students to deepen their study and understanding of the surgical content by observing the surgical procedure. But usually a long-time Da Vinci Surgical System observation can only see the in-vivo surgery shown on the screen, lack of detailed explanations makes it difficult for students to concentrate on the details of the operation. The use of the VR support system to simultaneously demonstrate and explain the surgical status makes it easier for students to understand and mitigate the fatigue and distraction of long-term observation.
{"title":"Development and Application of VR Support System for Medical Students","authors":"Mingwei Cai, R. Sato, Kenji Yoshida, K. Takayasu","doi":"10.1109/NICOInt.2019.00023","DOIUrl":"https://doi.org/10.1109/NICOInt.2019.00023","url":null,"abstract":"It is a must-have content for medical students to attend school at the surgery site. It enables students to deepen their study and understanding of the surgical content by observing the surgical procedure. But usually a long-time Da Vinci Surgical System observation can only see the in-vivo surgery shown on the screen, lack of detailed explanations makes it difficult for students to concentrate on the details of the operation. The use of the VR support system to simultaneously demonstrate and explain the surgical status makes it easier for students to understand and mitigate the fatigue and distraction of long-term observation.","PeriodicalId":436332,"journal":{"name":"2019 Nicograph International (NicoInt)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128919063","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：