检索结果-内蒙古大学图书馆

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

P1AC: Revisiting Absolute Pose From a Single Affine Correspondence

学校读者我要写书评

暂无评论

P1AC: Revisiting Absolute Pose From a Single Affine Correspo...

International Conference on computer vision (ICCV)

作者： Jonathan Ventura Zuzana Kukelova Torsten Sattler Dániel Baráth Department of Computer Science & Software Engineering Cal Poly San Luis Obispo Visual Recognition Group Faculty of Electrical Engineering Czech Technical University in Prague Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Computer Vision and Geometry Group ETH Zürich

Affine correspondences have traditionally been used to improve feature matching over wide baselines. While recent work has successfully used affine correspondences to solve various relative camera pose estimation problems, less attention has been given to their use in absolute pose estimation. We introduce the first general solution to the problem of estimating the pose of a calibrated camera given a single observation of an oriented point and an affine correspondence. The advantage of our approach (P1AC) is that it requires only a single correspondence, in comparison to the traditional point-based approach (P3P), significantly reducing the combinatorics in robust estimation. P1AC provides a general solution that removes restrictive assumptions made in prior work and is applicable to large-scale image-based localization. We propose a minimal solution to the P1AC problem and evaluate our novel solver on synthetic data, showing its numerical stability and performance under various types of noise. On standard image-based localization benchmarks we show that P1AC achieves more accurate results than the widely used P3P algorithm. Code for our method is available at https://***/jonathanventura/P1AC/.

关键词：

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

Inspecting Mega Solar Plants through computer vision and Drone Technologies

学校读者我要写书评

暂无评论

Inspecting Mega Solar Plants through Computer Vision and Dro...

Frontiers of Information Technology (FIT)

作者： Syed Umaid Ahmed Muhammad Affan Muhammad Ilyas Raza Muhammad Harris Hashmi Department of Computer Sciences National University of Computer and Emerging Sciences Karachi Pakistan SeaTech School of Engineering University of Toulon La Garde France Institute of Robotics and Computer Vision Innopolis University Innopolis Russia Department of Computer Science University of Alabama at Birmingham Birmingham United States

ISBN: (纸本)9798350345940

This research presents a unique approach for monitoring the large-scale grid-connected photovoltaic modules in solar power plants using state-of-art object detection YOLOv5 algorithm and classical image processing techniques. We have highlighted an integral part of the fully automated system in which a drone takes flight over the solar park and shoot the videos. Videos are preprocessed and used for trained YOLOv5 model to recognize the clean and dirty panels. The process is defined for a selected site and can be implemented using a Raspberry Pi. This system processes the images taken by drones, generates a report, and sends it to the concerned department automatically via email every day so that timely maintenance can be done for the long-life and safe operation of solar arrays. The inspection timeline for the same process was about one hundred and twenty hours, reduced to five minutes. It means that 99.93% of the time is saved through vision and robust automation techniques.

关键词： Photovoltaic systems computer vision Image processing Object detection Maintenance engineering Inspection Information technology

Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Yuyang Cong, Yang Goswami, Dipam Liu, Xialei van de Weijer, Joost State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences China University of Chinese Academy of Sciences China South China University of Technology China Computer Vision Center Barcelona Spain VCIP CS Nankai University China Department of Computer Science Universitat Autònoma de Barcelona Spain

In incremental learning, replaying stored samples from previous tasks together with current task samples is one of the most efficient approaches to address catastrophic forgetting. However, unlike incremental classification, image replay has not been successfully applied to incremental object detection (IOD). In this paper, we identify the overlooked problem of foreground shift as the main reason for this. Foreground shift only occurs when replaying images of previous tasks and refers to the fact that their background might contain foreground objects of the current task. To overcome this problem, a novel and efficient Augmented Box Replay (ABR) method is developed that only stores and replays foreground objects and thereby circumvents the foreground shift problem. In addition, we propose an innovative Attentive RoI Distillation loss that uses spatial attention from region-of-interest (RoI) features to constrain current model to focus on the most important information from old model. ABR significantly reduces forgetting of previous classes while maintaining high plasticity in current classes. Moreover, it considerably reduces the storage requirements when compared to standard image replay. Comprehensive experiments on Pascal-VOC and COCO datasets support the state-of-the-art performance of our model 1 © 2023, CC BY.

关键词： Object detection

Motion-X++: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Yuhong Lin, Jing Zeng, Ailing Wu, Guanlin Lu, Shunlin Fu, Yurong Cai, Yuanhao Zhang, Ruimao Wang, Haoqian Zhang, Lei Shenzhen International Graduate School Tsinghua University Guangdong 518000 China Department of Computer Vision and Robotics IDEA Guangdong 518000 China Whiting School of Engineering Johns Hopkins University MD21218 United States School of Data Science The Chinese University of Hong Kong Guangdong GD Shenzhen518000 China

In this paper, we introduce Motion-X++, a large-scale multimodal 3D expressive whole-body human motion dataset. Existing motion datasets predominantly capture body-only poses, lacking facial expressions, hand gestures, and fine-grained pose descriptions, and are typically limited to lab settings with manually labeled text descriptions, thereby restricting their scalability. To address this issue, we develop a scalable annotation pipeline that can automatically capture 3D whole-body human motion and comprehensive textural labels from RGB videos and build the Motion-X dataset comprising 81.1K text-motion pairs. Furthermore, we extend Motion-X into Motion-X++ by improving the annotation pipeline, introducing more data modalities, and scaling up the data quantities. Motion-X++ provides 19.5M 3D whole-body pose annotations covering 120.5K motion sequences from massive scenes, 80.8K RGB videos, 45.3K audios, 19.5M frame-level whole-body pose descriptions, and 120.5K sequence-level semantic labels. Comprehensive experiments validate the accuracy of our annotation pipeline and highlight Motion-X++’s significant benefits for generating expressive, precise, and natural motion with paired multimodal labels supporting several downstream tasks, including text-driven whole-body motion generation, audio-driven motion generation, 3D whole-body human mesh recovery, and 2D whole-body keypoints estimation, etc. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

Maize EfficientNet Fusion: Advancing Maize Disease Detection with MF-NET

学校读者我要写书评

暂无评论

Maize EfficientNet Fusion: Advancing Maize Disease Detection...

Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)

作者： Fatima Khalid Muhammad Hanif Qurat Ul Ain Faculty of Computer Science and Engineering Ghulam Ishaq Khan Institute of Engineering Sciences and Engineering Topi KPK Pakistan Aerial Robotics and Vision Lab Ghulam Ishaq Khan Institute of Engineering Sciences and Engineering Topi KPK Pakistan Department of Computing Shifa Tameer-E-Millat University Islamabad Pakistan

ISBN: (数字)9798350379037

ISBN: (纸本)9798350379044

Maize is a vital global crop, essential for food security but highly susceptible to diseases that threaten yield and quality. Traditional methods for detecting these diseases are computationally intensive and rely on high-quality images, limiting their practical use in diverse field conditions. This research addresses these challenges by proposing MF-Net, a novel model that leverages two EfficientNet-b0 architectures with ReLU and Swish activation functions. Our approach involves partially training Model R with frozen early layers using ReLU, and fully training Model S with Swish activation for enhanced optimization and robustness. We employ model concatenation and feature fusion techniques to create a lightweight yet powerful model, complemented by additional layers for improved feature extraction and regularization. Experimental results on the Corn Disease and Severity (CD&S) dataset are compelling: MF-Net achieves a remarkable 95.7% accuracy and 96% precision in disease classification, and 88.3% accuracy and 88.46% precision in severity level detection. These results highlight the model's effectiveness under challenging conditions such as cluttered backgrounds and variable lighting, significantly reducing computation time without compromising accuracy. Hence, MF-Net presents an innovative and efficient solution for maize disease detection and severity assessment, offering significant advancements for agricultural practices and crop management.

关键词： Training Adaptation models Accuracy Computational modeling Crops Lighting computer architecture Feature extraction Robustness Diseases

Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Luo, Cheng Song, Siyang Xie, Weicheng Shen, Linlin Gunes, Hatice Computer Vision Institute Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Key Laboratory of Intelligent Information Processing China Department of Computer Science and Technology University of Cambridge United Kingdom

The activations of Facial Action Units (AUs) mutually influence one another. While the relationship between a pair of AUs can be complex and unique, existing approaches fail to specifically and explicitly represent such cues for each pair of AUs in each facial display. This paper proposes an AU relationship modelling approach that deep learns a unique graph to explicitly describe the relationship between each pair of AUs of the target facial display. Our approach first encodes each AU’s activation status and its association with other AUs into a node feature. Then, it learns a pair of multi-dimensional edge features to describe multiple task-specific relationship cues between each pair of AUs. During both node and edge feature learning, our approach also considers the influence of the unique facial display on AUs’ relationship by taking the full face representation as an input. Experimental results on BP4D and DISFA datasets show that both node and edge feature learning modules provide large performance improvements for CNN and transformer-based backbones, with our best systems achieving the state-of-the-art AU recognition results. Our approach not only has a strong capability in modelling relationship cues for AU recognition but also can be easily incorporated into various backbones. Our PyTorch code is made available at https://***/CVI-SZU/ME-GraphAU. Copyright © 2022, The Authors. All rights reserved.

关键词： Chemical activation

Introducing the structural bases of typicality effects in deep learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Pino, Omar Vidal Nascimento, Erickson R. Campos, Mario F.M. Computer Vision and Robotics Laboratory Computer Science Department Universidade Federal de Minas Gerais Belo Horizonte31270-010 Brazil

In this paper, we hypothesize that the effects of the degree of typicality in natural semantic categories can be generated based on the structure of artificial categories learned with deep learning models. Motivated by the human approach to representing natural semantic categories and based on the foundations of Prototype Theory, we propose a novel Computational Prototype Model (CPM) to represent the internal structure of semantic categories. Unlike other prototype learning approaches, our mathematical framework proposes a first approach to provide deep neural networks with the ability to model abstract semantic concepts such as category central semantic meaning (semantic prototype), typicality degree of object's image, and family resemblance relationship. We proposed several methodologies based on the typicality's concept to evaluate our CPM model in image semantic processing tasks such as image classification, a global semantic description of images, and transfer learning. Our experiments on different image datasets, such as ImageNet and Coco, showed that our approach might be an admissible proposition in the effort to endow machines with greater power of abstraction for the semantic representation of objects' *** Codes 68T07 (Primary) 68Q55 (Secondary) Copyright © 2021, The Authors. All rights reserved.

关键词： Semantics