检索结果-内蒙古大学图书馆

Long-Term Invariant Local Features via Implicit Cross-Domain Correspondences

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Pataki, Zador Altillawi, Mohammad Kanakis, Menelaos Pautrat, Rémi Shen, Fengyi Liu, Ziyuan Van Gool, Luc Pollefeys, Marc The Computer Vision and Geometry Lab Department of Computer Science ETH Zurich Switzerland The Computer Vision Center CVC-Barcelona The Intelligent Robotics Cloud Technology lab of Huawei-Munich Germany The Computer Vision Lab Department Electrical Engineering ETH Zurich Switzerland The Intelligent Robotics Cloud Technology lab of Huawei-Munich Germany The Intelligent Robotics Cloud Technology lab of Huawei-Munich Germany The Center for Processing Speech and Images KU Leuven The Computer Vision Lab ETH Zurich Switzerland

Modern learning-based visual feature extraction networks perform well in intra-domain localization, however, their performance significantly declines when image pairs are captured across long-term visual domain variations, such as different seasonal and daytime variations. In this paper, our first contribution is a benchmark to investigate the performance impact of long-term variations on visual localization. We conduct a thorough analysis of the performance of current state-of-the-art feature extraction networks under various domain changes and find a significant performance gap between intra- and cross-domain localization. We investigate different methods to close this gap by improving the supervision of modern feature extractor networks. We propose a novel data-centric method, Implicit Cross-Domain Correspondences (iCDC). iCDC represents the same environment with multiple Neural Radiance Fields, each fitting the scene under individual visual domains. It utilizes the underlying 3D representations to generate accurate correspondences across different long-term visual conditions. Our proposed method enhances cross-domain localization performance, significantly reducing the performance gap. When evaluated on popular long-term localization benchmarks, our trained networks consistently outperform existing methods. This work serves as a substantial stride toward more robust visual localization pipelines for long-term deployments, and opens up research avenues in the development of long-term invariant descriptors. Copyright © 2023, The Authors. All rights reserved.

关键词： Feature extraction

CLEAR-Net: A Cascaded Local and External Attention Network for Enhanced Dehazing of Remote Sensing Images

学校读者我要写书评

暂无评论

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年

作者： Ali, Anas M. El-Rabaie, El-Sayed M. Ramadan, Khalil F. El-Samie, Fathi E. Abd El-Shafai, Walid Prince Sultan University Robotics and Internet-of-Things Laboratory Riyadh12435 Saudi Arabia Faculty of Electronic Engineering Menoufia University Department of Electronics and Electrical Communications Engineering Menouf32952 Egypt Computer Science Department Riyadh11586 Saudi Arabia

Atmospheric haze degrades remote sensing images by obscuring critical details, diminishing data interpretation accuracy. This paper presents CLEAR-Net: Cascaded Local and External Attention Resource Network, a novel dehazing framework designed to enhance clarity and detail in remote sensing images. CLEAR-Net employs a two-block cascaded architecture to address both global and local haze effects. The first block utilizes an Outer Global Attention (OGA) mechanism, processing global features via a U-Net Inner Attention (UIA) module to mitigate widespread haze. The second block focuses on Outer Local Attention (OLA), refining local image features through reintegration with the UIA module. An ensemble method selects the most effective model weights based on perceptual quality metrics, and a composite loss function emphasizes the preservation of high-frequency details to maintain textural and edge fidelity. CLEAR-Net's efficacy is evaluated on the SateHaze1k and RICE datasets, outperforming existing state-of-theart dehazing techniques. On SateHaze1k, CLEAR-Net achieves an average PSNR of 27.876 dB, surpassing the next best model by approximately 4.81%;under moderate fog, it attains a PSNR of 30.824 dB, about 9.8% higher than existing methods. On the RICE dataset, which includes challenging cloud cover, CLEARNet achieves PSNRs of 36.873 dB on RICE1 and 34.624 dB on RICE2, improving over next-best models by approximately 18.2% and 12%, respectively, and attains the lowest LPIPS values, indicating superior perceptual quality. © 2008-2012 IEEE.

关键词： Demulsification

TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud Analysis

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Melnyk, Pavlo Robinson, Andreas Felsberg, Michael Wadenbäck, Mårten Computer Vision Laboratory Department of Electrical Engineering Linköping University Sweden

In many practical applications, 3D point cloud analysis requires rotation invariance. In this paper, we present a learnable descriptor invariant under 3D rotations and reflections, i.e., the O(3) actions, utilizing the recently introduced steerable 3D spherical neurons and vector neurons. Specifically, we propose an embedding of the 3D spherical neurons into 4D vector neurons, which leverages end-to-end training of the model. In our approach, we perform TetraTransform-an equivariant embedding of the 3D input into 4D, constructed from the steerable neurons-and extract deeper O(3)-equivariant features using vector neurons. This integration of the TetraTransform into the VN-DGCNN framework, termed TetraSphere, negligibly increases the number of parameters by less than 0.0002%. TetraSphere sets a new state-of-the-art performance classifying randomly rotated real-world object scans of the challenging subsets of ScanObjectNN. Additionally, TetraSphere outperforms all equivariant methods on randomly rotated synthetic data: classifying objects from ModelNet40 and segmenting parts of the ShapeNet shapes. Thus, our results reveal the practical value of steerable 3D spherical neurons for learning in 3D Euclidean space. The code is available at https://***/pavlo-melnyk/tetrasphere. Copyright © 2022, The Authors. All rights reserved.

关键词： Neurons

ODD: Omni Differential Drive for Simultaneous Reconfiguration and Omnidirectional Mobility of Wheeled Robots

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhao, Ziqi Xie, Peijia Meng, Max Q.-H. Shenzhen Key Laboratory of Robotics Perception and Intelligence The Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China The Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong The Department of Electrical and Computer Engineering The University of Alberta Canada

Wheeled robots are highly efficient in human living environments. However, conventional wheeled designs, with their limited degrees of freedom and constraints in robot configuration, struggle to simultaneously achieve stability, passability, and agility due to varying footprint needs. This paper proposes a novel robot drive model inspired by human movements, termed as the Omni Differential Drive (ODD). The ODD model innovatively utilizes a lateral differential drive to adjust wheel spacing without adding additional actuators to the existing omnidirectional drive. This approach enables wheeled robots to achieve both simultaneous reconfiguration and omnidirectional mobility. To validate the feasibility of the ODD model, a functional prototype was developed, followed by comprehensive kinematic analyses. Control systems for self-balancing and motion control were designed and implemented. Experimental validations confirmed the feasibility of the ODD mechanism and the effectiveness of the control strategies. The results underline the potential of this innovative drive system to enhance the mobility and adaptability of robotic platforms. Copyright © 2024, The Authors. All rights reserved.

关键词： Kinematics

ODD: Omni Differential Drive for Simultaneous Reconfiguration and Omnidirectional Mobility of Wheeled Robots

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhao, Ziqi Xie, Peijia Meng, Max Q.-H. Shenzhen Key Laboratory of Robotics Perception and Intelligence The Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong Department of Electrical and Computer Engineering The University of Alberta Canada

Wheeled robots are highly efficient in human living environments. However, conventional wheeled designs, limited by degrees of freedom, struggle to meet varying footprint needs and achieve omnidirectional mobility. This paper proposes a novel robot drive model inspired by human movements, termed as the Omni Differential Drive (ODD). The ODD model innovatively utilizes a lateral differential drive to adjust wheel spacing without adding additional actuators to the existing omnidirectional drive. This approach enables wheeled robots to achieve both simultaneous reconfiguration and omnidirectional mobility. Additionally, a prototype was developed to validate the ODD, followed by kinematic analysis. Control systems for self-balancing and motion were designed and implemented. Experimental validations confirmed the feasibility of the ODD mechanism and the effectiveness of the control strategies. The results underline the potential of this innovative drive system to enhance the mobility and adaptability of robotic platforms. Copyright © 2024, The Authors. All rights reserved.

关键词： Wheels

When SAM2 meets video camouflaged object segmentation: a comprehensive evaluation and adaptation

学校读者我要写书评

暂无评论

Visual Intelligence 2025年第1期3卷 1-14页

作者： Zhou, Yuli Sun, Guolei Li, Yawei Xie, Guo-Sen Benini, Luca Konukoglu, Ender Computer Vision Laboratory ETH Zürich Zürich Switzerland Department of Informatics University of Zürich Zürich Switzerland Integrated System Laboratory ETH Zürich Zürich Switzerland School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Department of Electrical Electronic and Information Engineering University of Bologna Bologna Italy

This study investigates the application and performance of the Segment Anything Model 2 (SAM2) in the challenging task of video camouflaged object segmentation (VCOS). VCOS involves detecting objects that blend seamlessly in the surroundings for videos due to similar colors and textures and poor light conditions. Compared to the objects in normal scenes, camouflaged objects are much more difficult to detect. SAM2, a video foundation model, has shown potential in various tasks. However, its effectiveness in dynamic camouflaged scenarios remains under-explored. This study presents a comprehensive study on SAM2’s ability in VCOS. First, we assess SAM2’s performance on camouflaged video datasets using different models and prompts (click, box, and mask). Second, we explore the integration of SAM2 with existing multimodal large language models (MLLMs) and VCOS methods. Third, we specifically adapt SAM2 by fine-tuning it on the video camouflaged dataset. Our comprehensive experiments demonstrate that SAM2 has the excellent zero-shot ability to detect camouflaged objects in videos. We also show that this ability could be further improved by specifically adjusting SAM2’s parameters for VCOS.

关键词：

Analyzing Infrared Linescan Profiles of Steel Strips for Enhanced Cooling Pattern Prediction

学校读者我要写书评

暂无评论

Analyzing Infrared Linescan Profiles of Steel Strips for Enh...

IEEE Industry Applications Society Annual Meeting (IAS)

作者： Rubén Usamentiaga Adrian G. Gayo Francisco J. DelaCalle Dario G. Lema Stefano Sfarra Hai Zhang Department of Computer Science and Engineering University of Oviedo Gijón Asturias Spain Department of Industrial and Information Engineering and Economics (DIIIE) University of L'Aquila L'Aquila Italy Department of Electrical and Computer Engineering Computer Vision and Systems Laboratory (CVSL) Laval University Quebec Canada

ISBN: (数字)9798350372717

ISBN: (纸本)9798350372724

Real-time temperature information is crucial for optimizing cooling processes during steel strip rolling, ensuring the attainment of desired microstructural properties and surface quality at an optimal cooling rate. Infrared line scanners emerge as the preferred choice for temperature measurement in highspeed rolling operations, delivering temperature readings with high resolution and enabling the capture of detailed temperature profiles. By analyzing these profiles, cooling systems can be finely adjusted and precisely controlled to optimize the rolling operation. However, developing effective cooling strategies becomes challenging when dealing with temperature profiles comprising numerous discrete data points, often numbering in the thousands per profile. This study presents an innovative approach that integrates the detection of steel strip boundaries within temperature profiles and subsequent temperature pattern characterization using polynomial fitting. A significant advantage is demonstrated by leveraging the coefficients of Legendre polynomials, which provide a concise description of temperature profile shapes, facilitating straightforward approaches to cooling strategies. By integrating boundary detection with temperature characterization, the system enhances its ability to predict tailored cooling patterns, optimizing cooling efficiency, and enhancing product quality in the manufacturing process. Rigorous testing using both synthetic data and real-world applications in cold and hot rolling validates the proposed system's practical utility and reliability. These results underscore its potential to enhance efficiency and quality in industrial steel manufacturing operations.

关键词： Temperature measurement Temperature sensors Strips Cooling Shape Polynomials Real-time systems Steel Monitoring Testing

Task-Oriented Grasp Prediction with Visual-Language Inputs

学校读者我要写书评

暂无评论

Task-Oriented Grasp Prediction with Visual-Language Inputs

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

作者： Chao Tang Dehao Huang Lingxiao Meng Weiyu Liu Hong Zhang Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen China Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China Stanford University United States

To perform household tasks, assistive robots receive commands in the form of user language instructions for tool manipulation. The initial stage involves selecting the intended tool (i.e., object grounding) and grasping it in a task-oriented manner (i.e., task grounding). Nevertheless, prior researches on visual-language grasping (VLG) focus on object grounding, while disregarding the fine-grained impact of tasks on object grasping. Task-incompatible grasping of a tool will inevitably limit the success of subsequent manipulation steps. Motivated by this problem, this paper proposes GraspCLIP, which addresses the challenge of task grounding in addition to object grounding to enable task-oriented grasp prediction with visual-language inputs. Evaluation on a custom dataset demonstrates that GraspCLIP achieves superior performance over established baselines with object grounding only. The effectiveness of the proposed method is further validated on an assistive robotic arm for grasping previously unseen kitchen tools given the task specification. Our presentation video is available at: https://***/watch?v=e1wfYQPeAXU.

关键词：

Learning-based Detection of GPS Spoofing Attack for Quadrotors

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Pengyu Yang, Zhaohua Li, Jialu Shi, Ling Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Shenzhen Key Laboratory of Robotics Perception and Intelligence The Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China

Safety-critical cyber-physical systems (CPS), such as quadrotor UAVs, are particularly prone to cyber attacks, which can result in significant consequences if not detected promptly and accurately. During outdoor operations, the nonlinear dynamics of UAV systems, combined with non-Gaussian noise, pose challenges to the effectiveness of conventional statistical and machine learning methods. To overcome these limitations, we present QUADFormer, an advanced attack detection framework for quadrotor UAVs leveraging a transformer-based architecture. This framework features a residue generator that produces sequences sensitive to anomalies, which are then analyzed by the transformer to capture statistical patterns for detection and classification. Furthermore, an alert mechanism ensures UAVs can operate safely even when under attack. Extensive simulations and experimental evaluations highlight that QUADFormer outperforms existing state-of-the-art techniques in detection accuracy. (Video1) Copyright © 2025, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)