检索结果-内蒙古大学图书馆

HIPA: Hierarchical Patch Transformer for Single Image Super Resolution

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Cai, Qing Qian, Yiming Li, Jinxing Lyu, Jun Yang, Yee-Hong Wu, Feng Zhang, David The Faculty of Information Science and Engineering Ocean University of China Shandong Qingdao266100 China The Department of Computer Science University of Manitoba WinnipegMBR3T 2N2 Canada The School of Computer Science and Technology Harbin Institute of Technology Guangdong Shenzhen518055 China The School of Nursing The Hong Kong Polytechnic University Hong Kong The Department of Computing Science University of Alberta EdmontonABT6G 2E9 Canada The School of Information Science and Technology University of Science and Technology of China Anhui Hefei230026 China The School of Data Science The Chinese University of Hong Kong Guangdong Shenzhen518172 China The Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518000 China Linklogis Joint Laboratory of Computer Vision and Artificial Intelligence Guangdong Shenzhen518172 China

Transformer-based architectures start to emerge in single image super resolution (SISR) and have achieved promising performance. However, most existing vision Transformer-based SISR methods still have two shortcomings: (1) they divide images into the same number of patches with a fixed size, which may not be optimal for restoring patches with different levels of texture richness;and (2) their position encodings treat all input tokens equally and hence, neglect the dependencies among them. This paper presents a HIPA, which stands for a novel Transformer architecture that progressively recovers the high resolution image using a hierarchical patch partition. Specifically, we build a cascaded model that processes an input image in multiple stages, where we start with tokens with small patch sizes and gradually merge them to form the full resolution. Such a hierarchical patch mechanism not only explicitly enables feature aggregation at multiple resolutions but also adaptively learns patch-aware features for different image regions, e.g., using a smaller patch for areas with fine details and a larger patch for textureless regions. Meanwhile, a new attention-based position encoding scheme for Transformer is proposed to let the network focus on which tokens should be paid more attention by assigning different weights to different tokens, which is the first time to our best knowledge. Furthermore, we also propose a multi-receptive field attention module to enlarge the convolution receptive field from different branches. The experimental results on several public datasets demonstrate the superior performance of the proposed HIPA over previous methods quantitatively and qualitatively. We will share our code and models when the paper is accepted. Copyright © 2022, The Authors. All rights reserved.

关键词： Image reconstruction

Robot-To-robot relative pose estimation using humans as markers

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Islam, Md Jahidul Mo, Jiawei Sattar, Junaed Interactive Robotics and Vision Laboratory Department of Computer Science and Engineering University of Minnesota Twin Cities United States

In this paper, we propose a method to determine the 3D relative pose of pairs of communicating robots by using human pose-based key-points as correspondences. We adopt a -leader-follower' framework, where at first, the leader robot visually detects and triangulates the key-points using the state-of-The-Art pose detector named OpenPose. Afterward, the follower robots match the corresponding 2D projections on their respective calibrated cameras and find their relative poses by solving the perspective-n-point (PnP) problem. In the proposed method, we design an efficient person re-identification technique for associating the mutually visible humans in the scene. Additionally, we present an iterative optimization algorithm to refine the associated key-points based on their local structural properties in the image space. We demonstrate that these refinement processes are essential to establish accurate key-point correspondences across viewpoints. Furthermore, we evaluate the performance of the proposed relative pose estimation method through several experiments conducted in terrestrial and underwater environments. Finally, we discuss the relevant operational challenges of this approach and analyze its feasibility for multi-robot cooperative systems in humandominated social settings and feature-deprived environments such as underwater. Copyright © 2019, The Authors. All rights reserved.

关键词： Iterative methods

Global semantic description of objects based on prototype theory

学校读者我要写书评

暂无评论

arXiv 2019年

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

In this paper, we introduce a novel semantic description approach based on Prototype Theory foundations. Inspired by the human approach used for representing categories, we propose a Computational Prototype Model (CPM) that encodes and stores the central semantic meaning of the object’s category: the semantic prototype. Also, we introduce a Prototype-based Description Model that encodes the semantic of an object while describing its features using our CPM model. Our description method uses semantic prototypes computed by convolutional neural network (CNN) classification models to create discriminative signatures that describe an object highlighting its most distinctive features within the category. Our experiments show that: i) the proposed CPM model (semantic prototype + distance metric) successfully describes the internal semantic structure of objects categories;ii) our semantic distance metric can be understood as object visual typicality score within a category;and iii) our descriptor encoding is semantically interpretable and significantly outperforms other image global encodings in clustering and classification tasks. Copyright © 2019, The Authors. All rights reserved.

关键词： Encoding (symbols)

Minimal 3D Dubins Path with Bounded Curvature and Pitch Angle

学校读者我要写书评

暂无评论

Minimal 3D Dubins Path with Bounded Curvature and Pitch Angl...

IEEE International Conference on robotics and Automation (ICRA)

作者： Petr Váňa Armando Alves Neto Jan Faigl Douglas G. Macharet Faculty of Electrical Engineering Czech Technical University Prague Czech Republic Department of Electronic Engineering Universidade Federal de Minas Gerais MG Brazil Computer Vision and Robotics Laboratory (VeRLab) Universidade Federal de Minas Gerais MG Brazil

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

In this paper, we address the problem of finding cost-efficient three-dimensional paths that satisfy the maximum allowed curvature and the pitch angle of the vehicle. For any given initial and final configurations, the problem is decoupled into finding the horizontal and vertical parts of the path separately. Although the individual paths are modeled as two-dimensional Dubins curves using closed-form solutions, the final 3D path is constructed using the proposed local optimization to find a cost-efficient solution. Moreover, based on the decoupled approach, we provide a lower bound estimation of the optimal path that enables us to determine the quality of the found heuristic solution. The proposed solution has been evaluated using existing benchmark instances and compared with state-of-the-art approaches. Based on the reported results and lower bounds, the proposed approach provides paths close to the optimal solution while the computational requirements are in hundreds of microseconds. Besides, the proposed method provides paths with fewer turns than others, which make them easier to be followed by the vehicle's controller.

关键词： Three-dimensional displays Two dimensional displays Turning Path planning Atmospheric modeling Space vehicles Optimization

Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Quande Dou, Qi Heng, Pheng Ann Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong T Stone Robotics Institute Chinese University of Hong Kong Hong Kong Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

Model generalization capacity at domain shift (e.g., various imaging protocols and scanners) is crucial for deep learning methods in real-world clinical deployment. This paper tackles the challenging problem of domain generalization, i.e., learning a model from multi-domain source data such that it can directly generalize to an unseen target domain. We present a novel shape-aware meta-learning scheme to improve the model generalization in prostate MRI segmentation. Our learning scheme roots in the gradient-based meta-learning, by explicitly simulating domain shift with virtual meta-train and meta-test during training. Importantly, considering the deficiencies encountered when applying a segmentation model to unseen domains (i.e., incomplete shape and ambiguous boundary of the prediction masks), we further introduce two complementary loss objectives to enhance the meta-optimization, by particularly encouraging the shape compactness and shape smoothness of the segmentations under simulated domain shift. We evaluate our method on prostate MRI data from six different institutions with distribution shifts acquired from public datasets. Experimental results show that our approach outperforms many state-of-the-art generalization methods consistently across all six settings of unseen domains4 Copyright © 2020, The Authors. All rights reserved.

关键词： Urology

P1AC: Revisiting Absolute Pose From a Single Affine Correspondence

学校读者我要写书评

暂无评论

arXiv 2020年

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

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/. © 2020, CC BY.

关键词：

Fast perception, planning, and execution for a robotic butler: Wheeled humanoid m-hubo

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Lee, Moonyoung Heo, Yujin Park, Jinyong Yang, Hyun-Dae Jang, Ho-Deok Benz, Philipp Park, Hyunsub Kweon, In So Oh, Jun-Ho Humanoid Robot Research Center Department of Mechanical Engineering Korea Advanced Institute of Science and Technology 291 Daehak-ro Yuseong-gu Daejeon34141 Korea Republic of Robotics and Computer Vision Laboratory Department of Electrical Engineering Korea Advanced Institute of Science and Technology 291 Daehak-ro Yuseong-gu Daejeon34141 Korea Republic of

As the aging population grows at a rapid rate, there is an ever growing need for service robot platforms that can provide daily assistance at practical speed with reliable performance. In order to assist with daily tasks such as fetching a beverage, a service robot must be able to perceive its environment and generate corresponding motion trajectories. This becomes a challenging and computationally complex problem when the environment is unknown and thus the path planner must sample numerous trajectories that often are sub-optimal, extending the execution time. To address this issue, we propose a unique strategy of integrating a 3D object detection pipeline with a kinematically optimal manipulation planner to significantly increase speed performance at runtime. In addition, we develop a new robotic butler system for a wheeled humanoid that is capable of fetching requested objects at 24% of the speed a human needs to fulfill the same task. The proposed system was evaluated and demonstrated in a real-world environment setup as well as in public exhibition. Copyright © 2020, The Authors. All rights reserved.

关键词： Mobile robots

MyoPS: A Benchmark of Myocardial Pathology Segmentation Combining Three-Sequence Cardiac Magnetic Resonance Images

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Lei Wu, Fuping Wang, Sihan Luo, Xinzhe Martín-Isla, Carlos Zhai, Shuwei Zhang, Jianpeng Liu, Yanfei Zhang, Zhen Ankenbrand, Markus J. Jiang, Haochuan Zhang, Xiaoran Wang, Linhong Arega, Tewodros Weldebirhan Altunok, Elif Zhao, Zhou Li, Feiyan Ma, Jun Yang, Xiaoping Puybareau, Elodie Oksuz, Ilkay Bricq, Stephanie Li, Weisheng Punithakumar, Kumaradevan Tsaftaris, Sotirios A. Schreiber, Laura M. Yang, Mingjing Liu, Guocai Xia, Yong Wang, Guotai Escalera, Sergio Zhuang, Xiahai School of Data Science Fudan University Shanghai China School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China Departament de Matemàtiques & Informàtica Universitat de Barcelona Barcelona Spain Computer Vision Center Universitat Autònoma de Barcelona Spain School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu China School of Computer Science and Engineering Northwestern Polytechnical University Xi'An China College of Electrical and Information Engineering Hunan University Changsha China National Engineering Laboratory for Robot Visual Perception and Control Technology Changsha China College of Physics and Information Engineering Fuzhou University Fuzhou China Comprehensive Heart Failure Center Wuerzburg University Hospitals Wuerzburg Germany School of Engineering University of Edinburgh Edinburgh United Kingdom School of Robotics Xi'an Jiaotong-Liverpool University Suzhou China Department of Electrical and Computer Engineering University of California Los Angeles United States Department of Radiology and Diagnostic Imaging University of Alberta Edmonton Canada Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecomm-Unications Chongqing China ImViA Laboratory Université Bourgogne Franche-Comté Dijon France Computer Engineering Department Istanbul Technical University Istanbul Turkey Le Kremlin-Bicêtre France Department of Mathematics Nanjing University of Science and Technology Nanjing China Department of Mathematics Nanjing University Nanjing China

Assessment of myocardial viability is essential in diagnosis and treatment management of patients suffering from myocardial infarction, and classification of pathology on myocardium is the key to this assessment. This work defines a new task of medical image analysis, i.e., to perform myocardial pathology segmentation (MyoPS) combining three-sequence cardiac magnetic resonance (CMR) images, which was first proposed in the MyoPS challenge, in conjunction with MICCAI 2020. The challenge provided 45 paired and pre-aligned CMR images, allowing algorithms to combine the complementary information from the three CMR sequences for pathology segmentation. In this article, we provide details of the challenge, survey the works from fifteen participants and interpret their methods according to five aspects, i.e., preprocessing, data augmentation, learning strategy, model architecture and post-processing. In addition, we analyze the results with respect to different factors, in order to examine the key obstacles and explore potential of solutions, as well as to provide a benchmark for future research. We conclude that while promising results have been reported, the research is still in the early stage, and more in-depth exploration is needed before a successful application to the clinics. Note that MyoPS data and evaluation tool continue to be publicly available upon registration via its homepage (***/zhuangxiahai/0/myops20/). © 2022, CC BY-NC-SA.

关键词： Magnetic resonance imaging

I-BALLAST: computer vision solutions for ballast degradation analysis using deep-learning and data fusion methods

学校读者我要写书评

暂无评论

Geodata and AI

Geodata and AI 2024年 1卷

作者： Kelin Ding Jiayi Luo Haohang Huang John M. Hart Issam I.A. Qamhia Erol Tutumluer Hugh Thompson Theodore R. Sussmann University of Illinois Urbana-Champaign Department of Civil and Environmental Engineering 205 North Mathews Urbana IL 61801 USA Computer Vision and Robotics Laboratory University of Illinois Urbana-Champaign Coordinated Science Laboratory 1308 West Main Street Urbana Illinois 61801 USA Federal Railroad Administration 1200 New Jersey Avenue SE Washington DC 20590 USA U.S. DOT Volpe Center Structures and Dynamics 55 Broadway Cambridge MA 02142 USA

Ballast plays a significant role in supporting tracks under repeated loading. Ballast Scanning Vehicle (BSV) is an automated platform recently developed to acquire high-quality data to assist with ballast inspection and detailed geotechnical analyses using computer vision technology. To process the image data collected by the BSV, this paper introduces an advanced image analysis software for ballast, i.e., I-BALLAST. I-BALLAST encompasses advanced data fusion techniques that integrate multiple data sources, thus producing more consistent, accurate, and comprehensive information. Field data collected by multiple image acquisition devices and other sensors like Global Positioning System (GPS) can be combined for conducting comprehensive analyses, such as segmented particle point clouds generation and varying-window-based Particle Size Distribution (PSD) and Fouling Index (FI) analyses along track sections with aligned GPS coordinates. I-BALLAST has been tested in multiple field inspections, proving it an efficient and innovative tool for ballast fouling condition evaluations.

关键词： Ballast degradation Railroad Field inspection computer vision Deep learning Data fusion