检索结果-内蒙古大学图书馆

Constricting Normal Latent Space for Anomaly Detection with Normal-only Training Data

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Astrid, Marcella Zaheer, Muhammad Zaigham Lee, Seung-Ik Department of Artificial Intelligence University of Science and Technology Korea Republic of Field Robotics Research Section Electronics and Telecommunications Research Institute Korea Republic of Interdisciplinary Centre for Security Reliability and Trust University of Luxembourg Luxembourg Department of Computer Vision Mohamed Bin Zayed University of Artificial Intelligence United Arab Emirates

In order to devise an anomaly detection model using only normal training data, an autoencoder (AE) is typically trained to reconstruct the data. As a result, the AE can extract normal representations in its latent space. During test time, since AE is not trained using real anomalies, it is expected to poorly reconstruct the anomalous data. However, several researchers have observed that it is not the case. In this work, we propose to limit the reconstruction capability of AE by introducing a novel latent constriction loss, which is added to the existing reconstruction loss. By using our method, no extra computational cost is added to the AE during test time. Evaluations using three video anomaly detection benchmark datasets, i.e., Ped2, Avenue, and ShanghaiTech, demonstrate the effectiveness of our method in limiting the reconstruction capability of AE, which leads to a better anomaly detection model. © 2024, CC BY-NC-SA.

关键词： Anomaly detection

CodeEnhance: A Codebook-Driven Approach for Low-Light Image Enhancement

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Xu Hou, XianXu Lai, Zhihui Zhou, Jie Zhang, Ya-Nan Pedrycz, Witold Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China The Department of Electrical & Computer Engineering University of Alberta University of Alberta Canada

Low-light image enhancement (LLIE) aims to improve low-illumination images. However, existing methods face two challenges: (1) uncertainty in restoration from diverse brightness degradations;(2) loss of texture and color information caused by noise suppression and light enhancement. In this paper, we propose a novel enhancement approach, CodeEnhance, by leveraging quantized priors and image refinement to address these challenges. In particular, we reframe LLIE as learning an image-to-code mapping from low-light images to discrete codebook, which has been learned from high-quality images. To enhance this process, a Semantic Embedding Module (SEM) is introduced to integrate semantic information with low-level features, and a Codebook Shift (CS) mechanism, designed to adapt the pre-learned codebook to better suit the distinct characteristics of our low-light dataset. Additionally, we present an Interactive Feature Transformation (IFT) module to refine texture and color information during image reconstruction, allowing for interactive enhancement based on user preferences. Extensive experiments on both real-world and synthetic benchmarks demonstrate that the incorporation of prior knowledge and controllable information transfer significantly enhances LLIE performance in terms of quality and fidelity. The proposed CodeEnhance exhibits superior robustness to various degradations, including uneven illumination, noise, and color distortion. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

Experimental Trials with a Shared Autonomy Controller Framework and the da Vinci Research Kit: Pattern Cutting Tasks using Thin Elastic Materials

学校读者我要写书评

暂无评论

Experimental Trials with a Shared Autonomy Controller Framew...

International Symposium on Medical robotics (ISMR)

作者： Paramjit Singh Bawejaab Radian Gondokaryonobcd Lueder A. Kahrs Manipal Institute of Technology Karnataka India Medical Computer Vision and Robotics Lab University of Toronto Canada Department of Computer Science University of Toronto Canada The Wilfred and Joyce Posluns CIGITI SickKids Toronto Canada Department of Mathematical and Computational Sciences University of Toronto Mississauga Canada Institute of Biomedical Engineering University of Toronto Canada

A technical challenge in robotic soft material cutting is to avoid large local deformations that result in inaccuracies or failure of the task. Additionally, reducing procedure time and human errors that occur due to fatigue and monotony are two of the most anticipated advantages of using robots in execution of repetitive subtasks for minimally invasive surgery. In our paper, we evaluate pattern cutting tasks of 2D elastic materials with shared control using the da Vinci Research Kit (dVRK). For this purpose, we developed a shared autonomy motion generator framework for pattern cutting. The framework registers user-defined Cartesian positions, creates smooth splines, interpolates the Cartesian positions, and generates a trajectory with Cartesian and joint constraints. While a pre-planned trajectory is being executed, the user may provide Cartesian offsets to modify the trajectory. We repeatedly cut shapes on 3 materials with different elasticity. Our shared control method achieved 100% success rate while performing a circular cutting task in a sheet of gauze. The user input compensated for deformations due to tearing. Task completion time of those experiments was 86 seconds (median) / 88 seconds (mean). Median and mean errors were 3.1 mm and 3 mm, respectively. Our work improves the success rate and time of completion of published pattern cutting tasks.

关键词： Minimally invasive surgery Medical robotics Deformation Shape Fatigue Generators Trajectory

Assisted Physical Interaction: Autonomous Aerial Robots with Neural Network Detection, Navigation, and Safety Layers

学校读者我要写书评

暂无评论

Assisted Physical Interaction: Autonomous Aerial Robots with...

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Andrea Berra Viswa Narayanan Sankaranarayanan Achilleas Santi Seisa Julien Mellet Udayanga G.W.K.N. Gamage Sumeet Gajanan Satpute Fabio Ruggiero Vincenzo Lippiello Silvia Tolu Matteo Fumagalli George Nikolakopoulos Miguel Ángel Trujillo Soto Guillermo Heredia CATEC Advanced Center for Aerospace Technologies Seville Spain Department of Computer Electrical and Space Engineering Robotics and AI Team Luleå University of Technology Luleå Sweden Department of Electrical Engineering and Information Technology PRISMA Lab University of Naples Federico II Naples Italy Department of Electrical Engineering and Photonics Automation and Control Group Technical University of Denmark Denmark Robotics Vision and Control Group School of Engineering University of Seville Seville Spain

ISBN: (数字)9798350357882

ISBN: (纸本)9798350357899

The paper introduces a novel framework for safe and autonomous aerial physical interaction in industrial settings. It comprises two main components: a neural network-based target detection system enhanced with edge computing for reduced onboard computational load, and a control barrier function (CBF)-based controller for safe and precise maneuvering. The target detection system is trained on a dataset under challenging visual conditions and evaluated for accuracy across various unseen data with changing lighting conditions. Depth features are utilized for target pose estimation, with the entire detection framework offloaded into low-latency edge computing. The CBF-based controller enables the UAV to converge safely to the target for precise contact. Simulated evaluations of both the controller and target detection are presented, alongside an analysis of real-world detection performance.

关键词： Visualization Pose estimation Neural networks Lighting Object detection Autonomous aerial vehicles Aircraft navigation

Learning Deep Sensorimotor Policies for vision-based Autonomous Drone Racing

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Fu, Jiawei Song, Yunlong Wu, Yan Yu, Fisher Scaramuzza, Davide Robotics and Perception Group Department of Informatics University of Zurich Department of Neuroinformatics University of Zurich ETH Zurich Switzerland Visual Intelligence and Systems Group in the Computer Vision Lab at ETH Zurich Switzerland

unstructured environments, enabling various real-world applications. However, the lack of effective vision-based algorithms has been a stumbling block to achieving this goal. Existing systems often require hand-engineered components for state estimation, planning, and control. Such a sequential design involves laborious tuning, human heuristics, and compounding delays and errors. This paper tackles the vision-based autonomous-drone-racing problem by learning deep sensorimotor policies. We use contrastive learning to extract robust feature representations from the input images and leverage a two-stage learning-by-cheating framework for training a neural network policy. The resulting policy directly infers control commands with feature representations learned from raw images, forgoing the need for globally-consistent state estimation, trajectory planning, and handcrafted control design. Our experimental results indicate that our vision-based policy can achieve the same level of racing performance as the state-based policy while being robust against different visual disturbances and distractors. We believe this work serves as a stepping-stone toward developing intelligent vision-based autonomous systems that control the drone purely from image inputs, like human pilots. Copyright © 2022, The Authors. All rights reserved.

关键词： Drones

SFDA-rPPG: Source-Free Domain Adaptive Remote Physiological Measurement with Spatio-Temporal Consistency

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xie, Yiping Yu, Zitong Wu, Bingjie Xie, Weicheng Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Singapore

Remote Photoplethysmography (rPPG) is a non-contact method that uses facial video to predict changes in blood volume, enabling physiological metrics measurement. Traditional rPPG models often struggle with poor generalization capacity in unseen domains. Current solutions to this problem is to improve its generalization in the target domain through Domain Generalization (DG) or Domain Adaptation (DA). However, both traditional methods require access to both source domain data and target domain data, which cannot be implemented in scenarios with limited access to source data, and another issue is the privacy of accessing source domain data. In this paper, we propose the first Source-free Domain Adaptation benchmark for rPPG measurement (SFDA-rPPG), which overcomes these limitations by enabling effective domain adaptation without access to source domain data. Our framework incorporates a Three-Branch Spatio-Temporal Consistency Network (TSTC-Net) to enhance feature consistency across domains. Furthermore, we propose a new rPPG distribution alignment loss based on the Frequency-domain Wasserstein Distance (FWD), which leverages optimal transport to align power spectrum distributions across domains effectively and further enforces the alignment of the three branches. Extensive cross-domain experiments and ablation studies demonstrate the effectiveness of our proposed method in source-free domain adaptation settings. Our findings highlight the significant contribution of the proposed FWD loss for distributional alignment, providing a valuable reference for future research and applications. The source code is available at https://***/XieYiping66/SFDA-rPPG. Copyright © 2024, The Authors. All rights reserved.

关键词： Photoplethysmography

Low-Light Enhancement Effect on Classification and Detection: An Empirical Study

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Xu Lai, Zhihui Jie, Zhou Gao, Can Hou, Xianxu Zhang, Ya-Nan Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China The National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China

Low-light images are commonly encountered in real-world scenarios, and numerous low-light image enhancement (LLIE) methods have been proposed to improve the visibility of these images. The primary goal of LLIE is to generate clearer images that are more visually pleasing to humans. However, the impact of LLIE methods in high-level vision tasks, such as image classification and object detection, which rely on high-quality image datasets, is not well explored. To explore the impact, we comprehensively evaluate LLIE methods on these high-level vision tasks by utilizing an empirical investigation comprising image classification and object detection experiments. The evaluation reveals a dichotomy: While Low-Light Image Enhancement (LLIE) methods enhance human visual interpretation, their effect on computer vision tasks is inconsistent and can sometimes be harmful. Our findings suggest a disconnect between image enhancement for human visual perception and for machine analysis, indicating a need for LLIE methods tailored to support high-level vision tasks effectively. This insight is crucial for the development of LLIE techniques that align with the needs of both human and machine vision. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine vision

A Toolkit to Generate Social Navigation Datasets 21st

学校读者我要写书评

暂无评论

A Toolkit to Generate Social Navigation Datasets

21st International Workshop of Physical Agents, WAF 2020

作者： Baghel, Rishabh Kapoor, Aditya Bachiller, Pilar Jorvekar, Ronit R. Rodriguez-Criado, Daniel Manso, Luis J. Department of Computer Science and Engineering Indian Institute of Information Technology Guwahati Guwahati India Department of Computer Science and Information Systems Birla Institute of Technology and Science Goa Pilani India Robotics and Artificial Vision Laboratory University of Extremadura Badajoz Spain Department of Computer Engineering Pune Institute of Computer Technology Pune India Department of Computer Science College of Engineering and Physical Sciences Aston University Birmingham United Kingdom

ISBN: (纸本)9783030625788

Social navigation datasets are necessary to assess social navigation algorithms and train machine learning algorithms. Most of the currently available datasets target pedestrians’ movements as a pattern to be replicated by robots. It can be argued that one of the main reasons for this to happen is that compiling datasets where real robots are manually controlled, as they would be expected to behave when moving, is a very resource-intensive task. Another aspect that is often missing in datasets is symbolic information that could be relevant, such as human activities, relationships or interactions. Unfortunately, the available datasets targeting robots and supporting symbolic information are restricted to static scenes. This paper argues that simulation can be used to gather social navigation data in an effective and cost-efficient way and presents a toolkit for this purpose. A use case studying the application of graph neural networks to create learned control policies using supervised learning is presented as an example of how it can be used. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Navigation

Design of a Flexible Robot Arm for Safe Aerial Physical Interaction

学校读者我要写书评

暂无评论

Design of a Flexible Robot Arm for Safe Aerial Physical Inte...

IEEE International Conference on Soft robotics (RoboSoft)

作者： Julien Mellet Andrea Berra Achilleas Santi Seisa Viswa Sankaranarayanan Udayanga G.W.K.N. Gamage Miguel Ángel Trujillo Soto Guillermo Heredia George Nikolakopoulos Vincenzo Lippiello Fabio Ruggiero Department of Electrical Engineering and Information Technology PRISMA Lab University of Naples Federico II Naples Italy CATEC Advanced Center for Aerospace Technologies Seville Spain Department of Computer Robotics and AI Team Electrical and Space Engineering LuleåUIniversity of Technology Luleå Sweden Department of Electrical Engineering and Photonics Automation and Control Group Technical University of Denmark Denmark Robotics Vision and Control Group School of Engineering University of Seville Seville Spain

This paper introduces a novel compliant mechanism combining lightweight and energy dissipation for aerial physical interaction. Weighting 400 g at take-off, the mechanism is actuated in the forward body direction, enabling precise position control for force interaction and various other aerial manipulation tasks. The robotic arm, structured as a closed-loop kinematic chain, employs two deported servomotors. Each joint is actuated with a single tendon for active motion control in compression of the arm at the end-effector. Its elasto-mechanical design reduces weight and provides flexibility, allowing passive-compliant interactions without impacting the motors' integrity. Notably, the arm's damping can be adjusted based on the proposed inner frictional bulges. Experimental applications showcase the aerial system performance in both free-flight and physical interaction. The presented work may open safer applications for Micro Aerial Vehicle (MAV) in real environments subject to perturbations during interaction.

关键词：