检索结果-内蒙古大学图书馆

12th International Conference on Learning Representations, ICLR 2024

作者： Lee, Junoh Jung, Hyunjun Park, Jin-Hwi Bae, Inhwan Jeon, Hae-Gon School of Electrical Engineering and Computer Science Gwangju Korea Republic of AI Graduate School Gwangju Institute of Science and Technology Gwangju Korea Republic of

Estimating neural radiance fields (NeRFs) is able to generate novel views of a scene from known imagery. Recent approaches have afforded dramatic progress on small bounded regions of the scene. For an unbounded scene where cameras point in any direction and contents exist at any distance, certain mapping functions are used to represent it within a bounded space, yet they either work in object-centric scenes or focus on objects close to the camera. The goal of this paper is to understand how to design a proper mapping function that considers per-scene optimization, which remains unexplored. We first present a geometric understanding of existing mapping functions that express the relation between the bounded and unbounded scenes. Here, we exploit a stereographic projection method to explain failures of the mapping functions, where input ray samples are too sparse to account for scene geometry in unbounded regions. To overcome the failures, we propose a novel mapping function based on a p-norm distance, allowing to adaptively sample the rays by adjusting the p-value according to scene geometry, even in unbounded regions. To take the advantage of our mapping function, we also introduce a new ray parameterization to properly allocate ray samples in the geometry of unbounded regions. Through the incorporation of both the novel mapping function and the ray parameterization within existing NeRF frameworks, our method achieves state-ofthe-art novel view synthesis results on a variety of challenging datasets. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Moving target detection from the roadside by millimeter-wave radar

Moving target detection from the roadside by millimeter-wave...

引用

2024 International Symposium on Antennas and Propagation, ISAP 2024

作者： Moriyama, Toshifumi Matsumoto, Sora Chang, Yang-Lang Graduate School of Engineering Nagasaki University Nagasaki Japan College of Electrical Engineering and Computer Science National Taipei University of Technology Taipei Taiwan

ISBN: (纸本)9798350364774

In this study, we investigate a traffic monitoring method to detect passing cars, bikes, and humans from roadsides using millimeter-wave radar during road work. Because a road worker is one of the most dangerous occupations, the number of people trying to get this type of job is decreasing. To give a safety work condition and reduce road accidents with respect to the road works, a millimeter-wave radar is one of the candidates for infrastructure sensors that can be expected to offer robust detection performance regardless of the surrounding environment. Then, we applied millimeter-wave radar to traffic monitoring during road work. We examine that the radar detects passing cars, bikes, and humans, and estimates their direction with two corner reflectors from the roadside. These experiments were carried out, and the results are presented in this paper. © 2024 IEEE.

关键词： Roadsides

来源：评论

学校读者我要写书评

暂无评论

STViT+: improving self-supervised multi-camera depth estimation with spatial-temporal context and adversarial geometry regularization

引用

Applied Intelligence 2025年第5期55卷 1-20页

作者： Chen, Zhuo Zhao, Haimei Hao, Xiaoshuai Yuan, Bo Li, Xiu Shenzhen International Graduate School Tsinghua University Guangdong Shenzhen518055 China School of Computer Science The University of Sydney SydneyNSW2008 Australia Beijing Academy of Artificial Intelligence Beijing China School of Electrical Engineering and Computer Science The University of Queensland BrisbaneQLD4072 Australia

Multi-camera depth estimation has gained significant attention in autonomous driving due to its importance in perceiving complex environments. However, extending monocular self-supervised methods to multi-camera setups introduces unique challenges that existing techniques often fail to address. In this paper, we propose STViT+, a novel Transformer-based framework for self-supervised multi-camera depth estimation. Our key contributions include: 1) the Spatial-Temporal Transformer (STTrans), which integrates local spatial connectivity and global context to capture enriched spatial-temporal cross-view correlations, resulting in more accurate 3D geometry reconstruction;2) the Spatial-Temporal Photometric Consistency Correction (STPCC) strategy that mitigates the impact of varying illumination, ensuring brightness consistency across frames during photometric loss calculation;3) the Adversarial Geometry Regularization (AGR) module, which employs Generative Adversarial Networks to impose spatial constraints by using unpaired depth maps, enhancing performance under adverse conditions such as rain and nighttime driving. Extensive evaluations on large-scale autonomous driving datasets, including Nuscenes and DDAD, confirm that STViT+ sets a new benchmark for multi-camera depth estimation. © The Author(s) 2025.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Wind turbine inspection with drone: Advantages and disadvantages

Journal of Energy Systems

引用

Journal of Energy Systems 2023年第1期7卷 57-66页

作者： Tanrıverdi, Harun Karakuş, Güzide Ulukan, Ahmet Abdullah Gul University Graduate School of Engineering and Science Electrical and Computer Engineering Kayseri Turkey Necmettin Erbakan University Faculty of Aeronautics and Astronautics Department of Aviation Management Konya Turkey

The facilities on wind energy generation are increasingly finding usage areas in line with the ecologically friendly energy generation approach. One of the important activities of wind power generation facilities, which have high investment cost, low operating cost and low environmental impact is the maintenance and repair of wind turbines. A preventive maintenance approach is dominant to reduce maintenance times and eliminate lost time in wind turbines. Damage inspection of turbines has been evolved from tower crane access, rope access, camera viewing, and other applications to image with manual drones over the years. However, when these methods are evaluated within the framework of criteria such as cost, performance, occupational safety and data reliability, they are still insufficient and the need for inspection with autonomous drones arises. The advantages and disadvantages of autonomous drones used in the determination of damage in wind turbines are analyzed and the results are considered to contribute to the practitioners operating in the sector and academicians working in the field. © 2023 Published by peer-reviewed open access scientific journal.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of DeepLabCut and Other Open-Source Pupillometry Data Analysis Algorithms – Which to Choose?

引用

Machine Graphics and Vision 2024年第2期33卷 77-90页

作者： Badkul, Amitesh Mishra, Sonakshi Kommajosyula, Srinivasa P. Department of Electrical & Electronics Engineering Birla Institute of Technology and Science Hyderabad Campus Jawahar Nagar Hyderabad India Department of Pharmacy Birla Institute of Technology and Science Hyderabad Campus Jawahar Nagar Hyderabad India Ph.D. Program in Computer Science The Graduate Center The City University of New York New YorkNY United States

Pupillometry measures pupil size, and several open-source algorithms are available to analyse pupillometry data. However, only a few studies compared these algorithms’ accuracy and computational resources. This study aims to compare the accuracy of computer vision-based algorithms (Swirski, Starburst, PuRe, ElSe, ExCuSe algorithms) and the machine learning algorithm, DeepLabCut, to the double-blinded human examiners (gold-standard). Training of DeepLabCut with different architectures and a variable number of markers (2-9 markers) was done on an open-source dataset. The duration of training was statistically longer for the ResNet152 model compared to the MobileNet model. The pupil diameters in computer vision-based software such as PuRe, Starburst, and Swirski were statistically different from human measurements. MobileNet 2 and 3 marker models were the closest to the human measurements. In conclusion, this work highlights the efficiency of lower marker models based on MobileNet architecture in DeepLabCut, which consumes fewer computational resources and is more accurate. © 2024 Institute of Information Technology, Warsaw University of Life sciences - SGGW. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

On Robust Cross-view Consistency in Self-supervised Monocular Depth Estimation

引用

Machine Intelligence Research 2024年第3期21卷 495-513页

作者： Haimei Zhao Jing Zhang Zhuo Chen Bo Yuan Dacheng Tao School of Computer Science University of SydneySydney2008Australia Shenzhen International Graduate School Tsinghua UniversityShenzhen518055China School of Information Technology&Electrical Engineering University of QueenslandBrisbane4072Australia

Remarkable progress has been made in self-supervised monocular depth estimation (SS-MDE) by exploring cross-view consistency, e.g., photometric consistency and 3D point cloud consistency. However, they are very vulnerable to illumination variance, occlusions, texture-less regions, as well as moving objects, making them not robust enough to deal with various scenes. To address this challenge, we study two kinds of robust cross-view consistency in this paper. Firstly, the spatial offset field between adjacent frames is obtained by reconstructing the reference frame from its neighbors via deformable alignment, which is used to align the temporal depth features via a depth feature alignment (DFA) loss. Secondly, the 3D point clouds of each reference frame and its nearby frames are calculated and transformed into voxel space, where the point density in each voxel is calculated and aligned via a voxel density alignment (VDA) loss. In this way, we exploit the temporal coherence in both depth feature space and 3D voxel space for SS-MDE, shifting the “point-to-point” alignment paradigm to the “region-to-region” one. Compared with the photometric consistency loss as well as the rigid point cloud alignment loss, the proposed DFA and VDA losses are more robust owing to the strong representation power of deep features as well as the high tolerance of voxel density to the aforementioned challenges. Experimental results on several outdoor benchmarks show that our method outperforms current state-of-the-art techniques. Extensive ablation study and analysis validate the effectiveness of the proposed losses, especially in challenging scenes. The code and models are available at https://***/sunnyHelen/RCVC-depth.

关键词： 3D vision depth estimation cross-view consistency self-supervised learning monocular perception

来源：评论

学校读者我要写书评

暂无评论

Dynamic Sampling-Based Meta-Learning Using Multilingual Acoustic Data for Under-Resourced Speech Recognition

引用

IEEE Access 2024年 12卷 106070-106083页

作者： Hsieh, I-Ting Wu, Chung-Hsien Zhao, Zhe-Hong National Cheng Kung University Graduate Program of Multimedia Systems and Intelligent Computing Tainan70101 Taiwan National Cheng Kung University Department of Computer Science and Information Engineering Tainan70101 Taiwan

Under-resourced automatic speech recognition (ASR) has become an active field of research and has experienced significant progress during the past decade. However, the performance of under-resourced ASR trained by existing methods is still far inferior to high-resourced ASR for practical applications. In this paper, speech data from languages that share the most phonemes with the under-resourced language are selected as supplementary resources for meta-training based on the Model-Agnostic Meta-Learning (MAML) strategy. Besides supplementary language selection, this paper proposes a dynamic sampling method instead of the original random sampling method to select support and query sets for each task in MAML to improve meta-training performance. In this study, Taiwanese is selected as the under-resourced language, and the speech corpus of five languages, including Mandarin, English, Japanese, Cantonese, and Thai, are chosen as supplementary training data for acoustic model training. The proposed dynamic sampling approach uses phonemes, pronunciation, and speech recognition models as the basis to determine the proportion of each supplementary language to select helpful utterances for MAML. For evaluation, with the selected utterances from each supplementary language for meta-training, we obtained a Word Error Rate of 20.24% and a Syllable Error Rate of 8.35% for Taiwanese ASR, which were better than the baseline model (26.18% and 13.99%) using only the Taiwanese corpus and other methods. © 2013 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Enhancing Local Area Power Stability: Integrative Oscillation Damping with PV Systems and BESS

Enhancing Local Area Power Stability: Integrative Oscillatio...

引用

2024 International Conference on Technology and Policy in Energy and Electric Power, ICT-PEP 2024

作者： Akbar, Ilham Zakaria, Ariesa Budi Muljadi, Eduard Graduate Program PLN ITB PLN Corporate University Auburn United States Electrical and Computer Engineering Auburn University Auburn United States

ISBN: (纸本)9798331518646

This research delves into enhancing local area power stability by integrating battery energy storage systems (BESS) with photovoltaic (PV) systems to address and accelerate the damping of post-fault oscillations following short-circuit disturbances within power grids incorporating variable renewable energy sources. Focused on implementing a power oscillation damping (POD) mechanism within PV plants, this study aims to mitigate post-fault oscillations effectively within a specified timeframe. The proposed POD within the PV plant is strategically designed to augment the grid's resilience by supplying additional active and reactive power in response to system demands post-disturbance. The integration of a 25 MW BESS has demonstrated a significant enhancement in the system's recovery speed, reducing oscillation duration from 60 seconds to 45 seconds. Moreover, a configuration with double PV systems and a 50 MW BESS further reduced the oscillation duration to 42 seconds. Utilizing PSCAD software, this study presents an innovative approach to visualize the system's behavior post-short-circuit disturbances, confirming the efficacy of BESS integration in improving system stability and reliability. These results pave the way for further exploration of optimal BESS sizing and placement strategies to maximize grid resilience. © 2024 IEEE.

关键词： Renewable energy

来源：评论

学校读者我要写书评

暂无评论

Fast-Response FFS LC Device with Multi-rubbing Angle for VR Applications

Fast-Response FFS LC Device with Multi-rubbing Angle for VR ...

引用

International Symposium, Seminar, and Exhibition, Display Week 2024

作者： Chen, Shi-Rui Choi, Wing-Kit Graduate Institute of Photonics and Optoelectronics College of Electrical Engineering and Computer Science National Taiwan University Taiwan

In this paper, we propose new fast response FFS LC devices with virtual walls by using alternating (or multi) rubbing directions, which can be generated by using photo-alignment. These new devices can offer much-enhanced response-speed compared to the conventional FFS LC device. By choosing different types of "local" LC molecular arrangements or designs (easily achievable by using photo-alignment), we may be able to alter the virtual wall pitch length, and hence also alter the response speed and transmission of these fast response LC devices. These new designs can provide a new and alternative approach to generating virtual walls by "locally" varying the rubbing angle using photo-alignment. These devices are attractive for VR applications where high-speed operation of liquid crystal devices is required. © 2024, John Wiley and Sons Inc. All rights reserved.

关键词： Liquid crystals

来源：评论

学校读者我要写书评

暂无评论

Expanding chiral metamaterials for retrieving fingerprints via vibrational circular dichroism

引用

Light(science & Applications) 2023年第7期12卷 1401-1414页

作者： Cheng Xu Zhihao Ren Hong Zhou Jingkai Zhou Chong Pei Ho Nan Wang Chengkuo Lee Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore Center for Inteligent Sensors and MEMS(CISM) National University of SingaporeSingapore 117608Singapore institute of Microelectronics(IME) Agency for ScienceTechnology and Research(A*STAR)Singapore 138634Singapore NUS Graduate School for Integrative Science and Engineering Program(ISEP) National University of SingaporeSingapore 117456Singapore

Circular dichroism(CD)spectroscopy has been widely demonstrated for detecting chiral ***,the determination of chiral mixtures with various concentrations and enantiomeric ratios can be a challenging *** solve this problem,we report an enhanced vibrational circular dichroism(VCD)sensing platform based on plasmonic chiral metamaterials,which presents a 6-magnitude signal enhancement with a selectivity of chiral *** by coupled-mode theory,we leverage both in-plane and out-of-plane symmetry-breaking structures for chiral metamaterial design enabled by a two-step lithography process,which increases the near-field coupling strengths and varies the ratio between absorption and radiation loss,resulting in improved chiral light-matter interaction and enhanced molecular VCD ***,we demonstrate the thin-film sensing process of BSA andβ-lactoglobulin proteins,which contain secondary structures a-helix andβ-sheet and achieve a limit of detection down to zeptomole ***,we also,for the first time,explore the potential of enhanced VCD spectroscopy by demonstrating a selective sensing process of chiral mixtures,where the mixing ratio can be successfully differentiated with our proposed chiral *** findings improve the sensing signal of molecules and expand the extractable information,paving the way toward label-free,compact,small-volume chiral molecule detection for stereochemical and clinical diagnosisapplications.

关键词： chiral vibrational circular

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：