检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Mizutani, Koyu Mitarai, Haruki Miyazaki, Kakeru Kumano, Soichiro Yamasaki, Toshihiko The Department of Information and Communication Engineering Graduate School of Information Science and Technology The University of Tokyo Tokyo Japan The Emerging Design and Informatics Course Graduate School of Interdisciplinary Information Studies The University of Tokyo Tokyo Japan

deadly natural disasters that humans face. Accurately forecasting the extent of earthquake damage and assessing potential risks can be instrumental in saving numerous lives. In this study, we developed linear regression models capable of predicting seismic intensity distributions based on earthquake parameters: location, depth, and magnitude. Because it is completely data-driven, it can predict intensity distributions without geographical information. The dataset comprises seismic intensity data from earthquakes that occurred in the vicinity of Japan between 1997 and 2020, specifically containing 1,857 instances of earthquakes with a magnitude of 5.0 or greater, sourced from the Japan Meteorological Agency. We trained both regression and classification models and combined them to take advantage of both to create a hybrid model. The proposed model outperformed commonly used Ground Motion Prediction Equations (GMPEs) in terms of the correlation coefficient, F1 score, and MCC. Furthermore, the proposed model can predict even abnormal seismic intensity distributions, a task at conventional GMPEs often struggle. © 2024, CC BY-NC-SA.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Direct face pose estimation using multiple camera views and deep learning 4

Direct face pose estimation using multiple camera views and ...

引用

AI and Optical Data Sciences IV 2023

作者： Kim, Hyuno Lee, Seohyun Yamakawa, Yuji Department of Mechanical and Biofunctional Systems Institute of Industrial Science The University of Tokyo 4-6-1 Komaba Meguro-ku Tokyo Japan Laboratory of Computational Genomics Institute for Quantitative Biosciences The University of Tokyo 1-1-1 Yayoi Bunkyo-ku Tokyo Japan Emerging Design and Informatics Course Interfaculty Initiative in Information Studies Graduate School of Interdisciplinary Information Studies The University of Tokyo 4-6-1 Komaba Meguro-ku Tokyo Japan

ISBN: (纸本)9781510659810

Face pose estimation is essential for interactive remote video communication as well as human-computer interaction. In the case of a vision system for video communication using multiple cameras, not only precise but also fast estimation is required for the switching control of the camera views. However, most of the methods based on facial landmarks are not fast enough due to the calculation cost for the detection and alignment of the landmarks. This paper proposes a straightforward method to directly estimate the face pose from input camera images, using multiple camera views and deep learning. © 2023 SPIE.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

GAN-Based Semantic-Aware Translation for Day-to-Night Images

GAN-Based Semantic-Aware Translation for Day-to-Night Images

引用

2022 IEEE International Conference on Consumer Electronics, ICCE 2022

作者： Shiotsuka, Daiki Lee, Jinho Endo, Yuki Javanmardi, Ehsan Takahashi, Kunio Nakao, Kenta Kamijo, Shunsuke Emerging Design and Informatics Course Graduate School of Interdisciplinary Information Studies University of Tokyo Tokyo Japan Graduate School of Information Science and Technology University of Tokyo Department of Information and Communication Engineering Tokyo Japan University of Tokyo Tokyo Japan Mitsubishi Heavy Industries Machinery Systems Ltd. Hyogo Japan Mitsubishi Heavy Industries Ltd. Hyogo Japan

ISBN: (纸本)9781665441544

Perception in autonomous driving has achieved robustness and high accuracy through deep learning. CNN-based methods require a large amount of data collection and annotation. However, most of the current datasets are built on daytime scenes, and there are few datasets for adverse conditions such as night-time. Recently, data augmentation by image-to-image translation using Generative Adversarial Networks (GANs) has attracted attention. GANs based image-to-image translation performs well for various image translation tasks. On the other hand, semantic information may be lost in problems with the significant domain gap, such as day and night. In this paper, we propose a semantic-aware image translation. This framework preserves semantic consistency by transfer learning a semantic segmentation network to GANs. Experimental results show that the proposed method achieved to generate natural night images compared to previous studies. © 2022 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Advanced LiDAR Translation for Huge Domain Gap to Handle Adverse Weather Change

Advanced LiDAR Translation for Huge Domain Gap to Handle Adv...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Jinho Lee Geonkyu Bang Toshiaki Nishimori Kenta Nakao Shunsuke Kamijo Emerging Design and Informatics Course Graduate School of Interdisciplinary Information Studies The University of Tokyo Meguro City Tokyo Japan Mitsubishi Heavy Industries Machinery Systems Ltd. Hyogo-ku Kobe Japan Mitsubishi Heavy Industries Ltd. Hyogo-ku Kobe Japan The Institute of Industrial Science (IIS) The University of Tokyo Meguro City Tokyo Japan

Perception task is a key technology for autonomous vehicles. Among the perception tasks, image perception has achieved powerful performance in contrast to perception tasks with other sensors. This is because of a lack of data. When comparing large amounts of image data, other sensors’ data is not sufficient, particularly in LiDAR data. To deal with the lack of data problem, many translation methods have been proposed. Although most of them focus only on image translation and LiDAR translation between simulated and real data, [1] proposed by us is the first LiDAR translation method that can convert sunny data to data of adverse weather conditions while maintaining 3D point cloud information. It is possible to generate fake LiDAR data for weather changes from sunny data. However, there is a big limitation in that noisy points are generated for a huge domain gap, such as the translation between sunny and heavily foggy conditions. Thus, we propose an advanced LiDAR translation for a huge domain gap to handle adverse weather change.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic Attention-guided Day-to-Night Image Translation Network

Semantic Attention-guided Day-to-Night Image Translation Net...

引用

International Conference on Intelligent Transportation

作者： Geonkyu Bang Jinho Lee Yuki Endo Toshiaki Nishimori Kenta Nakao Shunsuke Kamijo Emerging Design and Informatics Course Graduate School of Interdisciplinary Information Studies the University of Tokyo Tokyo Japan Department of Information and Communication Engineering Graduate School of Information Science and Technology the University of Tokyo Tokyo Japan Mitsubishi Heavy Industries Machinery Systems Ltd Hyogo Japan Mitsubishi Heavy Industries Ltd Hyogo Japan Institute of Industrial Science the University of Tokyo Tokyo Japan

Perception tasks are critical for an autonomous driving system. In recent years, advancements in deep learning have enabled highly accurate perception. However, conquering perception tasks in poor visibility environments remains challenging. One of the main reasons is that most of the existing datasets are concentrated on visually clear environments. This makes it difficult to train deep learning-based perception models in limited visibility environments. Building a new dataset requires significant time and human resources, and annotating data from adverse visibility environments is even more challenging. To address these problems, many image translation methods have been proposed to translate annotated daytime images into nighttime ones to build a nighttime dataset without annotation. In this paper, we present an unsupervised day-to-night image translation network for generating synthetic data. Our proposed method extracts semantic information from input images. The extracted information is then applied to the image-to-image translation network as spatial attention maps. We conduct experiments to evaluate the proposed method. The experimental results show that our method outperforms the related works both qualitative and quantitative.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LiDAR Translation Based on Empirical Approach between Sunny and Foggy for Driving Simulation

LiDAR Translation Based on Empirical Approach between Sunny ...

引用

International Symposium on Wireless Personal Multimedia Communications (WPMC)

作者： Jinho Lee Daiki Shiotsuka Toshiaki Nishimori Kenta Nakao Shunsuke Kamijo Emerging Design and Informatics Course Graduate School of Interdisciplinary Information Studies The university of Tokyo 4 Chome-6-1 Komaba Meguro City Tokyo japan Mitsubishi Heavy Industries Machinery Systems Ltd. Kobe Japan Mitsubishi Heavy Industries Ltd. Kobe Japan The Institute of Industrial Science (IIS) The University of Tokyo Meguro City Tokyo Japan

Autonomous driving requires perception technologies with robustness and high accuracy. Lots of deep learning algorithms satisfy this requirement. However, they focus on only image processing and few such algorithms are based on LiDAR. A lack of data is the main reason why there exist few deep learning algorithms based on LiDAR. Various translation technologies have been suggested to handle this problem. Though a lack of data occurs more often with LiDAR than with images, these technologies also focus on only image-to-image translation. Translation technology based on LiDAR is required not only for data augmentation but also for driving simulation, which allows algorithms to practice driving as if they were commanding a real vehicle, before doing so in the real world. Among many translations for data augmentation and driving simulation, translation to foggy is the most challenging task. To verify algorithms for driving simulation, generating foggy data is necessary. Also, it leads to a potential solution for data augmentation. Thus, we propose a GAN-based LiDAR translation algorithm between sunny and foggy for driving simulation. It is the first LiDAR translation approach based on an empirical approach. We tested the proposed method on the JARI data set, which was collected with controlling diverse visible distance settings.

关键词： Deep learning Wireless communication Training Laser radar Snow Roads Data models

来源：评论

学校读者我要写书评

暂无评论

Development and Functional Evaluation of a Deformable Membrane Capsule for an Open Ball Glenohumeral Joint

Development and Functional Evaluation of a Deformable Membra...

引用

IEEE International Conference on Biomedical Robotics and Biomechatronics

作者： Ayaka Fujii Shinsuke Nakashima Masaya Kawamura Kento Kawaharazuka Shogo Makino Yuki Asano Kei Okada Masayuki Inaba Graduate School of Interdisciplinary Information Studies Emerging design and informatics course The University of Tokyo

ISBN: (纸本)9781538681848

Human has open ball joints in shoulder or hip joints, and can move such joints in wide range of motion without dislocation. One of the reason of it is that there is joint capsule in human joints. Joint capsule is a membrane structure which surrounds a joint and consists of two kinds of membrane, external one is fibrous membrane and internal one is synovial membrane. There is synovial fluid inside synovial membrane and plays a role of lubricant and cushioning material of the joint. However, there is no humanoid robots with joint capsule and human mimetic humanoids which have open ball joints sometimes dislocate their shoulders. In this paper, in reference to joint capsules, we developed an open ball joint which has membrane structure made of vulcanized natural rubber and moved the joint by tendon drive using motor modules which was disposed similar to human shoulder muscle arrangement. We also tested its function such as strength and range of motion for future use in glenohumeral joint of human mimetic musculoskeletal humanoids and showed that the joint becomes less likely to dislocate when there is membrane structure surrounding the joint.

关键词： Joint Capsule Joints Joints membrane structure functional evaluation Shoulder Joint Shoulder Synovial Membrane BALL JOINT Fibrous membranes Cushioning materials Joint Range of Motion Humanoid robots Hip Joint Human

来源：评论

学校读者我要写书评

暂无评论

Analysis of bidirectional information transfer on drumming ensemble using robotic session system

Analysis of bidirectional information transfer on drumming e...

引用

2012 21st IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2012

作者： Sato, Hiroki Kuniyoshi, Yasuo Emerging Design and Informatics Course Graduate School of Interdisciplinary Information Studies University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo 113-8656 Japan Department of Mechano-Informatics Graduate School of Information Science and Technology University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo 113-8656 Japan

ISBN: (纸本)9781467346054

For the design of artificial systems with the ability to co-create with humans, it is necessary to consider how robots interpret and apply its human partner's actions in its own actions. Nowadays many robots with the ability to co-create with human appeared but few research succeeded in quantifying the interaction between humans and robots, making it difficult to assess the importance of the robot's contribution to the interaction. © 2012 IEEE.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

Evaluation of action-similarity awareness effect in rhythm ensemble co-creation

Evaluation of action-similarity awareness effect in rhythm e...

引用

20th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2011

ISBN: (纸本)9781457715716

There are many robots which have communication skills with human but most of their actions and responses are preprogrammed and few researches inspect psychological aspects of behavior in human-robot co-creation. In this paper, we focus on action-similarity awareness as a key for building up co-creative relationship with humans. Here, action-similarity awareness means that one recognizes affinity to one's own actions derived from other's actions. As a simple task involving action-similarity awareness, we focused on rhythm ensemble. The ensemble is a type of drumming session in which even people who have little musical experience easily take part. In this research we expect to realize the awareness in the rhythm ensemble session by employing the other's past action and mixing it to metrical structure, a basic beat structure in music. To make sure of this idea in real session, we developed a robot system which can actually play a drumming session with humans and control action-similarity awareness. We conducted a subjective experiment and analyzed questionnaire and interaction record. From the questionnaire results, it was confirmed that the sense of prediction increases with action contributing rate and that it is effective to imitate humans actions and add 10% to 30% originality. From the interaction record it was confirmed that phrase structure was shared by making consent on which part to be varied or fixed. © 2011 IEEE.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：