检索结果-内蒙古大学图书馆

International Symposium on Environmentally Conscious Design and Inverse Manufacturing (EcoDesign)

作者： Masaharu Nagashima Hyun-Woo Kim Myungjin Cho Min-Chul Lee Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka city Japan School of ICT Robotics and Mechanical Engineering IITC Hankyong National University Anseong-si Korea

ISBN: (数字)9798350363043

ISBN: (纸本)9798350363050

Digital Holographic Microscopy (DHM) can obtain three-dimensional (3D) information about the fine structure of an object by utilizing the phase information of coherent light. In DHM, during the process of reconstructing the shape of an object, phase information is extracted by windowing the sideband containing the phase information. The 3D information of the object is then obtained from the acquired phase information. When windowing the sideband in a narrow range, it can remove noise caused by the DC spectrum, but detailed shape information of the object is lost. On the other hand, when windowing in a wide range, detailed shape information of the object can be obtained, but noise from the DC spectrum increases. To solve this trade-off relationship, we propose a method of determining the range for windowing the sideband using a function and then averaging the windowed sidebands. This proposed method can reduce the impact of noise from the DC spectrum and enables the acquisition of the detailed shape information. In this paper, we explain the reconstruction algorithm of this method and compare it with conventional methods and the previous study, phase differences averaging (PDA).

关键词： Three-dimensional displays Filtering Shape Microscopy Noise Noise reduction Reconstruction algorithms Amplitude modulation Data mining Informatics

来源：评论

学校读者我要写书评

暂无评论

Category re-balancing based domain adaptive semantic segmentation 11

Category re-balancing based domain adaptive semantic segment...

引用

11th International Conference on Information technology and Quantitative Management, ITQM 2024

作者： Zhu, Siyu Zhou, Fenfen Li, Kai Liu, Minghao Wen, Haonan Computer School Beijing Information Science and Technology University 102206 No.55 Taihang RoadChangping District Beijing China Beijing Key Laboratory of Information Service Engineering Beijing Union University Beijing100101 China College of Robotics Beijing Union University Beijing100027 China National Engineering Research Center of Visual Technology School of Computer Science Peking University Beijing100871 China Yuquan Road Shijingshan District Beijing100049 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences No. 80 of Zhongguancun East Road Haidian District Beijing100190 China

The semantic segmentation task faces the bottleneck of high manual annotation costs. Domain adaptive learning provides an effective solution through inter domain knowledge transfer. However, existing domain adaptive semantic segmentation tasks face the situation of category asymmetry between scenes when dealing with complex scenes. Existing methods lack handling of class imbalance in the prediction process. In domain adaptive semantic segmentation tasks, class imbalance limits the performance of inter domain transfer. Our work focuses on the impact of category distribution on domain adaptive semantic segmentation tasks in image pairs. Inspired by long tail learning, we divided categories into head, middle, and tail categories, and designed effective strategies to enhance the contribution of tail categories in domain adaptation tasks. We introduce the concept of category re-balancing into domain adaptive image matching, and our method is lightweight and effective, proving its effectiveness on general datasets. © 2024 The Authors.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Semantic Level Image Retrieval in Domain Adaptive Semantic Segmentation 11

Semantic Level Image Retrieval in Domain Adaptive Semantic S...

引用

11th International Conference on Information technology and Quantitative Management, ITQM 2024

作者： Zhu, Siyu Zhou, Fenfen Li, Kai Wen, Haonan Liu, Minghao Computer School Beijing Information Science and Technology University 102206 No.55 Taihang RoadChangping District Beijing China Beijing Key Laboratory of Information Service Engineering Beijing Union University Beijing100101 China College of Robotics Beijing Union University Beijing100027 China National Engineering Research Center of Visual Technology School of Computer Science Peking University Beijing100871 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences No. 80 of Zhongguancun East Road Haidian District Beijing100190 China Yuquan Road Shijingshan District Beijing100049 China

The traditional domain adaptation task is not sufficient in mining inter domain image context. We propose a solution from the perspective of image semantic level retrieval. Image semantic level retrieval is based on the high-level semantics of images, retrieving the similarity or correspondence between images in terms of content and scene between domains. Our work focuses on the meaning, structure, and contextual information expressed by the target image, and retrieves the most relevant image from the source domain to improve the accuracy of domain adaptation. Furthermore, in response to the negative transfer brought about by image retrieval, we will introduce a category level weight adjustment module to further improve the accuracy of semantic level retrieval and weaken the negative impact caused by low precision categories. Finally, we demonstrated the effectiveness of semantic level image retrieval through experiments. © 2024 The Authors.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A research on optimization of fog estimation process in Peplography

A research on optimization of fog estimation process in Pepl...

引用

International Conference on Control, Automation and Systems ( ICCAS)

作者： Seiya Ono Jin-Ung Ha Hyun-Woo Kim Myungjin Cho Min-Chul Lee Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Fukuoka Japan School of ICT Robotics and Mechanical Engineering IITC Hankyong National University Anseong Republic of Korea

ISBN: (数字)9788993215380

ISBN: (纸本)9798331517939

In recent years, imaging techniques are essential in our lives, such as security cameras and drive recorders. However, the visualization quality of these techniques sometimes is affected by scattering media, such as smoke at a fire or fog during driving. To solve this problem, Peplography has been proposed. Peplography is an optical algorithm that emphasizes the object information presented in the scattering media, even when the density of the scattering media varies within the image. On the other hand, Peplography estimates the scattering media in each local region, and when the region is not defined appropriately, the estimation of the scattering media will not be visualized. Therefore, the purpose of this research is to find the optimal processing for each environment by experiment with various situations, such as when the size of the object in the image is small, when the density of the scattering media is heavy, and when the target object is various.

关键词： YOLO Visualization Optical recording Scattering Process control Estimation Media Security Optical scattering Optimization

来源：评论

学校读者我要写书评

暂无评论

Kalman filtering optimization in Digital Holographic Microscopy (DHM)

Kalman filtering optimization in Digital Holographic Microsc...

引用

International Conference on Control, Automation and Systems ( ICCAS)

作者： Taishi Ono Jongpil Jeong Hyun-Woo Kim Myungjin Cho Min-Chul Lee Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Fukuoka Japan School of ICT Robotics and Mechanical Engineering IITC Hankyong National University Anseong Republic of Korea

ISBN: (数字)9788993215380

ISBN: (纸本)9798331517939

Digital Holographic Microscopy (DHM) can obtain a 3D profile of a micro-object. However, the obtained 3D profile includes the noise. One reason for this is the problem of the extraction method of phase information in DHM. Conventional methods cannot extract only the phase information from the Fourier domain, and noise components are included. To solve this problem, we propose a use of the Kalman filter in DHM systems. In this method, multiple frequency components are obtained from the Fourier domain as time-series data for Kalman filtering. 3D profiles are obtained from each frequency component and stored in an array as time-series data. This is used to remove randomly generated noise. In this process, it remains unclear how many 3D profiles obtained from frequency components are needed as time-series data. Therefore, the optimization of the number of windowed sidebands in the Fourier domain is the objective in this paper. The objective is to use the Kalman filter efficiently by performing quantitative evaluation using image quality metrics and optimization based on processing time.

关键词： Measurement Time-frequency analysis Three-dimensional displays Accuracy Filtering Microscopy Noise Kalman filters Data mining Optimization

来源：评论

学校读者我要写书评

暂无评论

Photon counting integral imaging using Kalman estimation 13

Photon counting integral imaging using Kalman estimation

引用

13th International Conference on Information and Communication technology Convergence, ICTC 2022

作者： Shinohara, Ryo Kim, Hyun-Woo Lee, Jaehoon Huh, Jong-Hoon Cho, Myungjin Lee, Min-Chul Kyushu Institute of Technology Department of Computer Science and Networks Iizuka Japan Department of Physics and Information Technology Kyushu Institute of technology Iizuka Japan School of ICT Robotics and Mechanical Engineering Iitc Hankyong National University Kyonggi-do Anseong Korea Republic of

ISBN: (数字)9781665499392

ISBN: (纸本)9781665499392

In this paper, we propose 3D photon counting integral imaging using the Kalman estimation. Photons are emitted in unit time and space independently. To visualize the 3D object under low luminance conditions, computational photon counting imaging may be used. It can estimate the photons by statistical methods such as the Poisson random distribution. Then, it can reconstruct the 3D information through the integral imaging. However, since the Poisson random process always generates different photon counting images, the image quality is not consistent and also errors may occur. Therefore, it is difficult to maintain the high 3D image quality under photon-starved conditions. To solve these problems, we utilize Kalman estimation to estimate the photons accurately and generate the high image quality consistently under various low light conditions. To evaluate our proposed method, we implemented optical experiments and image quality evaluation by calculating image quality metrics. © 2022 IEEE.

关键词： Photons

来源：评论

学校读者我要写书评

暂无评论

ESVO2: Direct Visual-Inertial Odometry with Stereo Event Cameras

arXiv

引用

arXiv 2024年

作者： Niu, Junkai Zhong, Sheng Lu, Xiuyuan Shen, Shaojie Gallego, Guillermo Zhou, Yi School of Robotics Hunan University Changsha China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong TU Berlin The Science of Intelligence Excellence Cluster The Robotics Institute Germany Einstein Center Digital Future Berlin Germany

Event-based visual odometry is a specific branch of visual Simultaneous Localization and Mapping (SLAM) techniques, which aims at solving tracking and mapping sub-problems (typically in parallel), by exploiting the special working principles of neuromorphic (i.e., event-based) cameras. Due to the motion-dependent nature of event data, explicit data association (i.e., feature matching) under large-baseline viewpoint changes is difficult to establish, making direct methods a more rational choice. However, state-of-the-art direct methods are limited by the high computational complexity of the mapping sub-problem and the degeneracy of camera pose tracking in certain degrees of freedom (DoF) in rotation. In this paper, we tackle these issues by building an event-based stereo visual-inertial odometry system on top of a direct pipeline [1]. Specifically, to speed up the mapping operation, we propose an efficient strategy for sampling contour points according to the local dynamics of events. The mapping performance is also improved in terms of structure completeness and local smoothness by merging the temporal stereo and static stereo results. To circumvent the degeneracy of camera pose tracking in recovering the pitch and yaw components of general 6-DoF motion, we introduce IMU measurements as motion priors via pre-integration. To this end, a compact back-end is proposed for continuously updating the IMU bias and predicting the linear velocity, enabling an accurate motion prediction for camera pose tracking. The resulting system scales well with modern high-resolution event cameras and leads to better global positioning accuracy in large-scale outdoor environments. Extensive evaluations on five publicly available datasets featuring different resolutions and scenarios justify the superior performance of the proposed system against five state-of-the-art methods. Compared to ESVO [1], our new pipeline significantly reduces the camera pose tracking error by 40%–80% and 20%—80%

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

VARIQuery: VAE Segment-Based Active Learning for Query Selection in Preference-Based Reinforcement Learning

VARIQuery: VAE Segment-Based Active Learning for Query Selec...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Daniel Marta Simon Holk Christian Pek Jana Tumova Iolanda Leite Division of Robotics Perception and Learning School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Digital Futures

Human-in-the-loop reinforcement learning (RL) methods actively integrate human knowledge to create reward functions for various robotic tasks. Learning from preferences shows promise as alleviates the requirement of demonstrations by querying humans on state-action sequences. However, the limited granularity of sequence-based approaches complicates temporal credit assignment. The amount of human querying is contingent on query quality, as redundant queries result in excessive human involvement. This paper addresses the often-overlooked aspect of query selection, which is closely related to active learning (AL). We propose a novel query selection approach that leverages variational autoencoder (VAE) representations of state sequences. In this manner, we formulate queries that are diverse in nature while simultaneously taking into account reward model estimations. We compare our approach to the current state-of-the-art query selection methods in preference-based RL, and find ours to be either on-par or more sample efficient through extensive benchmarking on simulated environments relevant to robotics. Lastly, we conduct an online study to verify the effectiveness of our query selection approach with real human feedback and examine several metrics related to human effort.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Aligning Human Preferences with Baseline Objectives in Reinforcement Learning

Aligning Human Preferences with Baseline Objectives in Reinf...

引用

IEEE International Conference on robotics and Automation (ICRA)

Practical implementations of deep reinforcement learning (deep RL) have been challenging due to an amplitude of factors, such as designing reward functions that cover every possible interaction. To address the heavy burden of robot reward engineering, we aim to leverage subjective human preferences gathered in the context of human-robot interaction, while taking advantage of a baseline reward function when available. By considering baseline objectives to be designed beforehand, we are able to narrow down the policy space, solely requesting human attention when their input matters the most. To allow for control over the optimization of different objectives, our approach contemplates a multi-objective setting. We achieve human-compliant policies by sequentially training an optimal policy from a baseline specification and collecting queries on pairs of trajectories. These policies are obtained by training a reward estimator to generate Pareto optimal policies that include human preferred behaviours. Our approach ensures sample efficiency and we conducted a user study to collect real human preferences, which we utilized to obtain a policy on a social navigation environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Non-smooth Control Barrier Functions for Stochastic Dynamical Systems

arXiv

引用

arXiv 2023年

作者： Vahs, Matti Tumova, Jana The Division of Robotics Perception and Learning School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Digital Futures

Uncertainties arising in various control systems, such as robots that are subject to unknown disturbances or environmental variations, pose significant challenges for ensuring system safety, such as collision avoidance. At the same time, safety specifications are getting more and more complex, e.g., by composing multiple safety objectives through Boolean operators resulting in non-smooth descriptions of safe sets. Control Barrier Functions (CBFs) have emerged as a control technique to provably guarantee system safety. In most settings, they rely on an assumption of having deterministic dynamics and smooth safe sets. This paper relaxes these two assumptions by extending CBFs to encompass control systems with stochastic dynamics and safe sets defined by non-smooth functions. By explicitly considering the stochastic nature of system dynamics and accommodating complex safety specifications, our method enables the design of safe control strategies in uncertain and complex systems. We provide formal guarantees on the safety of the system by leveraging the theoretical foundations of stochastic CBFs and non-smooth safe sets. Numerical simulations demonstrate the effectiveness of the approach in various scenarios. Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic systems

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：