检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Kim, Junho Jeong, Jiwon Kim, Young Min Dept. of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University Korea Republic of Dept. of Electrical Engineering Stanford University United States

We introduce a lightweight and accurate localization method that only utilizes the geometry of 2D-3D lines. Given a pre-captured 3D map, our approach localizes a panorama image, taking advantage of the holistic 360◦ view. The system mitigates potential privacy breaches or domain discrepancies by avoiding trained or hand-crafted visual descriptors. However, as lines alone can be ambiguous, we express distinctive yet compact spatial contexts from relationships between lines, namely the dominant directions of parallel lines and the intersection between nonparallel lines. The resulting representations are efficient in processing time and memory compared to conventional visual descriptor-based methods. Given the groups of dominant line directions and their intersections, we accelerate the search process to test thousands of pose candidates in less than a millisecond without sacrificing accuracy. We empirically show that the proposed 2D-3D matching can localize panoramas for challenging scenes with similar structures, dramatic domain shifts or illumination changes. Our fully geometric approach does not involve extensive parameter tuning or neural network training, making it a practical algorithm that can be readily deployed in the real world. Project page including the code is available through this link: https://***/fgpl/. © 2024, CC BY.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Learning 3D Scene Analogies with Neural Contextual Scene Maps

arXiv

引用

arXiv 2025年

作者： Kim, Junho Bae, Gwangtak Lee, Eun Sun Kim, Young Min Dept. of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University Korea Republic of

Understanding scene contexts is crucial for machines to perform tasks and adapt prior knowledge in unseen or noisy 3D environments. As data-driven learning is intractable to comprehensively encapsulate diverse ranges of layouts and open spaces, we propose teaching machines to identify relational commonalities in 3D spaces. Instead of focusing on point-wise or object-wise representations, we introduce 3D scene analogies, which are smooth maps between 3D scene regions that align spatial relationships. Unlike well-studied single instance-level maps, these scene-level maps smoothly link large scene regions, potentially enabling unique applications in trajectory transfer in AR/VR, long demonstration transfer for imitation learning, and context-aware object rearrangement. To find 3D scene analogies, we propose neural contextual scene maps, which extract descriptor fields summarizing semantic and geometric contexts, and holistically align them in a coarse-to-fine manner for map estimation. This approach reduces reliance on individual feature points, making it robust to input noise or shape variations. Experiments demonstrate the effectiveness of our approach in identifying scene analogies and transferring trajectories or object placements in diverse indoor scenes, indicating its potential for robotics and AR/VR applications. © 2025, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

DCGAN-based Medical Image Augmentation to Improve ELM Classification Performance 11

DCGAN-based Medical Image Augmentation to Improve ELM Classi...

引用

11th IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2022

作者： Rando Setiawan, Noor Akhmad Permanasari, Adhistya Erna Rulaningtyas, Riries Suksmono, Andriyan Bayu Sitanggang, Imas Sukaesih Universitas Gadjah Mada Dept. of Electrical and Information Engineering Yogyakarta Indonesia Biomedical Engineering Program Dept. of Physics Universitas Airlangga Surabaya Indonesia Institut Teknologi Bandung School of Electrical Engineering and Informatics Bandung Indonesia Ipb University Department of Computer Science Bogor Indonesia

ISBN: (纸本)9781665460309

Cervical cancer is one of the deadliest diseases in women. One of the cervical cancer screening methods is pap smear method. However, using a pap smear method to detect cervical cancer takes a long time for a pathologist to diagnose. Hence, a rapid development of medical computerization for early detection to get the results quickly is needed. This paper proposes synthetic data augmentation by using Deep Convolutional Generative Adversarial Network (DCGAN) to increase number of pap smear samples in dataset. Gray Level Co-occurrence Matrix (GLCM) is employed to extract features from dataset. Classification of 3 classes which are Adenocarcinoma, High-Grade Squamous Intraepithelial Lesion (HSIL), and Squamous Cell Carcinoma (SCC) is conducted using Extreme Learning Machine (ELM). The result shows that the addition of synthetic data improves the performance of ELM with the accuracy of 90%. This accuracy is better than the accuracy of ELM using only the original dataset which is 85%. © 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

A Hybrid E-nose System based on Metal Oxide Semiconductor Gas Sensors and Compact Colorimetric Sensors

A Hybrid E-nose System based on Metal Oxide Semiconductor Ga...

引用

2021 IEEE International Conference on Automatic Control and Intelligent Systems, I2CACIS 2021

作者： Maw, Aung Khant Somboon, Pakpum Srituravanich, Werayut Teeramongkonrasmee, Arporn Chulalongkorn University Dept. of Electrical Engineering Bangkok Thailand Chulalongkorn University Biomedical Engineering Program Bangkok Thailand

ISBN: (纸本)9781665403436

Commercial metal-oxide semiconductor (MOS) gas sensors have been widely used by recent studies as detection units of electronic noses (e-nose) in various applications including disease diagnosis. However, the enoses employing the MOS sensors can only discriminate a limited number of odor groups due to their poor selectivity. Preliminary studies have shown that the selectivity of the MOS sensors can be enhanced by jointly integrating with other sensory units such as QCM or potentiometric sensors, which, however, involves complex interface circuitry and measurement procedures. In contrast, this paper presents a hybrid electronic nose that combines olfactory information from an MOS sensor array together with a compact paperbased colorimetric sensor array which is simpler and easier to utilize. The proposed system employs total 8 MOS sensors, and the compact paper-based colorimetric sensors are fabricated with indicator dyes such as phenol red, methyl red, and methylene blue. Color profiles of the paper-based sensors are captured using a USB-microscope and the alterations of the dyes during the gas exposure are monitored. The improvement of the system performance in classifying six volatile organic compounds (VOC) are investigated by comparing the classification results of the system with and without the colorimetric sensors. The measurement data from both sensor arrays are mapped to the feature space using principal component analysis (PCA) for pattern extraction. It was confirmed that pattern separation among the target VOCs could be improved based on data fusion of these two sensor arrays. This hybrid e-nose system may be useful for improvement of VOC classification performance. © 2021 IEEE.

关键词： Electronic nose

来源：评论

学校读者我要写书评

暂无评论

ReMP: Reusable Motion Prior for Multi-domain 3D Human Pose Estimation and Motion Inbetweening

arXiv

引用

arXiv 2024年

作者： Jang, Hojun Kim, Young Min Dept. of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University Korea Republic of

We present Reusable Motion prior (ReMP), an effective motion prior that can accurately track the temporal evolution of motion in various downstream tasks. Inspired by the success of foundation models, we argue that a robust spatio-temporal motion prior can encapsulate underlying 3D dynamics applicable to various sensor modalities. We learn the rich motion prior from a sequence of complete parametric models of posed human body shape. Our prior can easily estimate poses in missing frames or noisy measurements despite significant occlusion by employing a temporal attention mechanism. More interestingly, our prior can guide the system with incomplete and challenging input measurements to quickly extract critical information to estimate the sequence of poses, significantly improving the training efficiency for mesh sequence recovery. ReMP consistently outperforms the baseline method on diverse and practical 3D motion data, including dept. point clouds, LiDAR scans, and IMU sensor data. Project page is available in https://***/ReMP. Copyright © 2024, The Authors. All rights reserved.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

LDL: Line Distance Functions for Panoramic Localization

LDL: Line Distance Functions for Panoramic Localization

引用

International Conference on Computer Vision (ICCV)

作者： Junho Kim Changwoon Choi Hojun Jang Young Min Kim Dept. of Electrical and Computer Engineering Seoul National University Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University

We introduce LDL, a fast and robust algorithm that localizes a panorama to a 3D map using line segments. LDL focuses on the sparse structural information of lines in the scene, which is robust to illumination changes and can potentially enable efficient computation. While previous line-based localization approaches tend to sacrifice accuracy or computation time, our method effectively observes the holistic distribution of lines within panoramic images and 3D maps. Specifically, LDL matches the distribution of lines with 2D and 3D line distance functions, which are further decomposed along principal directions of lines to increase the expressiveness. The distance functions provide coarse pose estimates by comparing the distributional information, where the poses are further optimized using conventional local feature matching. As our pipeline solely leverages line geometry and local features, it does not require costly additional training of line-specific features or correspondence matching. Nevertheless, our method demonstrates robust performance on challenging scenarios including object layout changes, illumination shifts, and large-scale scenes, while exhibiting fast pose search terminating within a matter of milliseconds. We thus expect our method to serve as a practical solution for line-based localization, and complement the well-established point-based paradigm. The code for LDL is available through the following link: https://***/82magnolia/panoramic-localization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Calibrating Panoramic dept. Estimation for Practical Localization and Mapping

Calibrating Panoramic Depth Estimation for Practical Localiz...

引用

International Conference on Computer Vision (ICCV)

作者： Junho Kim Eun Sun Lee Young Min Kim Dept. of Electrical and Computer Engineering Seoul National University Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University

The absolute dept. values of surrounding environments provide crucial cues for various assistive technologies, such as localization, navigation, and 3D structure estimation. We propose that accurate dept. estimated from panoramic images can serve as a powerful and light-weight input for a wide range of downstream tasks requiring 3D information. While panoramic images can easily capture the surrounding context from commodity devices, the estimated dept. shares the limitations of conventional image-based dept. estimation; the performance deteriorates under large domain shifts and the absolute values are still ambiguous to infer from 2D observations. By taking advantage of the holistic view, we mitigate such effects in a self-supervised way and fine-tune the network with geometric consistency during the test phase. Specifically, we construct a 3D point cloud from the current dept. prediction and project the point cloud at various viewpoints or apply stretches on the current input image to generate synthetic panoramas. Then we minimize the discrepancy of the 3D structure estimated from synthetic images without collecting additional data. We empirically evaluate our method in robot navigation and map-free localization where our method shows large performance enhancements. Our calibration method can therefore widen the applicability under various external conditions, serving as a key component for practical panorama-based machine vision systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Mesh Recovery from Partial Point Cloud Sequence

Dynamic Mesh Recovery from Partial Point Cloud Sequence

引用

International Conference on Computer Vision (ICCV)

作者： Hojun Jang Minkwan Kim Jinseok Bae Young Min Kim Dept. of Electrical and Computer Engineering Seoul National University Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University

The exact 3D dynamics of the human body provides crucial evidence to analyze the consequences of the physical interaction between the body and the environment, which can eventually assist everyday activities in a wide range of applications. However, optimizing for 3D configurations from image observation requires a significant amount of computation, whereas real-world 3D measurements often suffer from noisy observation or complex occlusion. We resolve the challenge by learning a latent distribution representing strong temporal priors. We use a conditional variational autoencoder (CVAE) architecture with a transformer to train the motion priors with a large-scale motion dataset. Then our feature follower effectively aligns the feature spaces of noisy, partial observation with the necessary input for pre-trained motion priors, and quickly recovers a complete mesh sequence of motion. We demonstrate that the transformer-based autoencoder can collect necessary spatio-temporal correlations robust to various adversaries, such as missing temporal frames, or noisy observation under severe occlusion. Our framework is general and can be applied to recover the full 3D dynamics of other subjects with parametric representations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of VOCs Mixture Biomarker Classification System Based on Preconcentrator with Embedded Sensing Control

Development of VOCs Mixture Biomarker Classification System ...

引用

International Conference on Electrical engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON

作者： Pornpawit Sinsukudomchai Arporn Teeramongkonrasmee Chadin Kulsing Isaya Thaveesangsakulthai Pakpum Somboon Biomedical Engineering Program Chulalongkorn University Bangkok Thailand Dept. of Electrical Engineering Chulalongkorn University Bangkok Thailand Chemistry Faculty of Science Chulalongkorn University Bangkok Thailand

ISBN: (数字)9798350381559

ISBN: (纸本)9798350381566

A volatile organic compound (VOCs) classification system is developed for non-invasive biomarker screening tests. The developed system utilizes a preconcentrator, which contains an absorbent material for trapping VOCs at low temperatures and thermally desorbing at specific elevated temperatures. This system is especially useful for detection of odor mixture at low concentration and target VOCs biomarkers in the odor sample can also be measured with enhanced selectivity. All sensing processes, including a PID temperature controller for heating preconcentrator, odor sensor interface, and solenoid valve control, are performed using only a single embedded microcontroller. An odor mixture with low concentration is measured and classified in order to investigate the developed system. The result of the experiment and the principal component analysis (PCA) shows that the system with the preconcentrator can measure the VOCs mixture of odor sample in terms of sensitivity and selectivity. This system prototype is useful for screening tests of exhaled breath biomarker.

关键词： Temperature measurement Temperature sensors Volatile organic compounds Temperature distribution Sensitivity Microcontrollers Valves

来源：评论

学校读者我要写书评

暂无评论

Developing a Respiratory Pressure Simulation Platform for a Portable Negative Pressure Filtering Chest Drainage System 16

Developing a Respiratory Pressure Simulation Platform for a ...

引用

16th IEEE International Conference on Nano/Molecular Medicine and engineering, NANOMED 2023

作者： Liao, Hao-Yen Chu, Cheng-Shane Wu, Yang-Shun Lin, Sheng-Chieh Lin, Chia-Tsai Hung, Kuo-Yung Ming Chi University of Technology Dept. of Intl. Ph.D Program in Innovative Technology of Biomedical Engineering and Medical Devices Taiwan Ming Chi University of Technology Department of Mechanical Engineering Taiwan Ming Chi University of Technology Research Center for Intelligent Medical Devices Taiwan

ISBN: (纸本)9798350343700

This study aims to reduce the risk of aerosol infection in patients and healthcare workers by establishing a portable negative pressure filtering chest drainage system (PNPFCDS) that filters aerosols and microparticles. By controlling the negative pressure precisely, the system can prevent aerosol transmission under different air leaks. By using a respiratory pressure simulation platform (RPSP), it has been demonstrated that the negative pressure filtering chest drainage system can achieve a minimum measured pressure error of 1.6% without simulated intrapleural pressure changes when the air leak flow rises to 800 ml/min. When the target pressure is -1.5 kPa under simulated intrapleural pressure changes with air leak of 500 ml/min, the measured pressure change rate ranges from -16.7 % to +22.7%. When the target pressure is -9 kPa, the measured pressure change rates ranges from -2% to +6.7%. According to ISO 10079-1, this study provides a model of a negative pressure filtering chest drainage system that is effective and safe. © 2023 IEEE.

关键词： Aerosols

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：