检索结果-内蒙古大学图书馆

Learning Probabilistic Coordinate Fields for Robust Correspondences

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhao, Weiyue Lu, Hao Ye, Xinyi Cao, Zhiguo Li, Xin Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China The Lane Department of Computer Science and Electrical Engineering West Virginia University MorgantownWV26506-6109 United States

We introduce Probabilistic Coordinate Fields (PCFs), a novel geometric-invariant coordinate representation for image correspondence problems. In contrast to standard Cartesian coordinates, PCFs encode coordinates in correspondence-specific barycentric coordinate systems (BCS) with affine invariance. To know when and where to trust the encoded coordinates, we implement PCFs in a probabilistic network termed PCF-Net, which parameterizes the distribution of coordinate fields as Gaussian mixture models. By jointly optimizing coordinate fields and their confidence conditioned on dense flows, PCF-Net can work with various feature descriptors when quantifying the reliability of PCFs by confidence maps. An interesting observation of this work is that the learned confidence map converges to geometrically coherent and semantically consistent regions, which facilitates robust coordinate representation. By delivering the confident coordinates to keypoint/feature descriptors, we show that PCF-Net can be used as a plug-in to existing correspondence-dependent approaches. Extensive experiments on both indoor and outdoor datasets suggest that accurate geometric invariant coordinates help to achieve the state of the art in several correspondence problems, such as sparse feature matching, dense image registration, camera pose estimation, and consistency filtering. Further, the interpretable confidence map predicted by PCF-Net can also be leveraged to other novel applications from texture transfer to multi-homography classification. Copyright © 2023, The Authors. All rights reserved.

关键词： Textures

Data-Driven Discovery of Stochastic Differential Equations

学校读者我要写书评

暂无评论

Engineering 2022年第10期17卷 244-252页

作者： Yasen Wang Huazhen Fang Junyang Jin Guijun Ma Xin He Xing Dai Zuogong Yue Cheng Cheng Hai-Tao Zhang Donglin Pu Dongrui Wu Ye Yuan Jorge Gonçalves Jürgen Kurths Han Ding School of Mechanical Science and Engineering Huazhong University of Science and TechnologyWuhan 430074China State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and TechnologyWuhan 430074China Department of Mechanical Engineering University of KansasLawrenceKS 66045USA HUST-Wuxi Research Institute Wuxi 214174China Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhan 430074China Department of Plant Sciences University of CambridgeCambridge CB23EAUK Luxembourg Centre for Systems Biomedicine University of LuxembourgBelvaux 4367Luxembourg Department of Physics Humboldt University of BerlinBerlin 12489Germany Department of Complexity Science Potsdam Institute for Climate Impact ResearchPotsdam 14473Germany

Stochastic differential equations(SDEs)are mathematical models that are widely used to describe complex processes or phenomena perturbed by random noise from different *** identification of SDEs governing a system is often a challenge because of the inherent strong stochasticity of data and the complexity of the system’s *** practical utility of existing parametric approaches for identifying SDEs is usually limited by insufficient data *** study presents a novel framework for identifying SDEs by leveraging the sparse Bayesian learning(SBL)technique to search for a parsimonious,yet physically necessary representation from the space of candidate basis *** importantly,we use the analytical tractability of SBL to develop an efficient way to formulate the linear regression problem for the discovery of SDEs that requires considerably less time-series *** effectiveness of the proposed framework is demonstrated using real data on stock and oil prices,bearing variation,and wind speed,as well as simulated data on well-known stochastic dynamical systems,including the generalized Wiener process and Langevin *** framework aims to assist specialists in extracting stochastic mathematical models from random phenomena in the natural sciences,economics,and engineering fields for analysis,prediction,and decision making.

关键词： Data-driven method System identification Sparse Bayesian learning Stochastic differential equations Random phenomena

A2B: Anchor to Barycentric Coordinate for Robust Correspondence

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhao, Weiyue Lu, Hao Cao, Zhiguo Li, Xin The Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Lane Department of Computer Science and Electrical Engineering West Virginia University Commonwealth of Virginia Morgantown 15461 United States

There is a long-standing problem of repeated patterns in correspondence problems, where mismatches frequently occur because of inherent ambiguity. The unique position information associated with repeated patterns makes coordinate representations a useful supplement to appearance representations for improving feature correspondences. However, the issue of appropriate coordinate representation has remained unresolved. In this study, we demonstrate that geometric-invariant coordinate representations, such as barycentric coordinates, can significantly reduce mismatches between features. The first step is to establish a theoretical foundation for geometrically invariant coordinates. We present a seed matching and filtering network (SMFNet) that combines feature matching and consistency filtering with a coarse-to-fine matching strategy in order to acquire reliable sparse correspondences. We then introduce DEGREE, a novel anchor-to-barycentric (A2B) coordinate encoding approach, which generates multiple affine-invariant correspondence coordinates from paired images. DEGREE can be used as a plug-in with standard descriptors, feature matchers, and consistency filters to improve the matching quality. Extensive experiments in synthesized indoor and outdoor datasets demonstrate that DEGREE alleviates the problem of repeated patterns and helps achieve state-of-the-art performance. Furthermore, DEGREE also reports competitive performance in the third image Matching Challenge at CVPR 2021. This approach offers a new perspective to alleviate the problem of repeated patterns and emphasizes the importance of choosing coordinate representations for feature correspondences. Copyright © 2023, The Authors. All rights reserved.

关键词：

Relative-Posture-Fixed Model Predictive Human-Following control with Visibility Constraints in Obstacle Environments

学校读者我要写书评

暂无评论

Relative-Posture-Fixed Model Predictive Human-Following Cont...

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Yikun Zhang Jian Huang Jinqi Yu Yaonan Zhu Yasuhisa Hasegawa Key Laboratory for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Shenzhen Huazhong University of Science and Technology Research Institute ShenZhen China Department of Micronano Mechanical Science and Engineering Nagoya University Nagoya Japan

The relative-posture-fixed human following is critical for the human-robot interaction and cooperation in daily scenes such as domestic service and healthcare. However, few of previous researches have discussed the difficulties faced by mobile robots in the real world, including the limitation of sensing range and hindrance from obstacles. For practicality, in this paper we investigate the relative-posture-fixed following control with collision avoidance and visibility constraints. The control task is formulated as a receding-horizon optimization problem and solved under the Nonlinear Model Predictive control (NMPC) framework, while an Extended Kalman Filter (EKF) based human trajectory predict algorithm is integrated into the robot controller. The effectiveness of the proposed algorithm is verified in a simulation, and the results demonstrate a promising performance of our controller for the human-following task in complicated environments.

关键词：

CPTNet: Cascade Pose Transform Network for Single image Talking Head Animation 15th

学校读者我要写书评

暂无评论

CPTNet: Cascade Pose Transform Network for Single Image Talk...

15th Asian Conference on Computer Vision, ACCV 2020

作者： Zhang, Jiale Xian, Ke Liu, Chengxin Chen, Yinpeng Cao, Zhiguo Zhong, Weicai Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Huawei CBG Consumer Cloud Service Search Product and Big Data Platform Department Xi’an China

ISBN: (纸本)9783030695378

We study the problem of talking head animation from a single image. Most of the existing methods focus on generating talking heads for human. However, little attention has been paid to the creation of talking head anime. In this paper, our goal is to synthesize vivid talking heads from a single anime image. To this end, we propose cascade pose transform network, termed CPTNet, that consists of a face pose transform network and a head pose transform network. Specifically, we introduce a mask generator to animate facial expression (e.g., close eyes and open mouth) and a grid generator for head movement animation, followed by a fusion module to generate talking heads. In order to handle large motion and obtain more accurate results, we design a pose vector decomposition and cascaded refinement strategy. In addition, we create an anime talking head dataset, that includes various anime characters and poses, to train our model. Extensive experiments on our dataset demonstrate that our model outperforms other methods, generating more accurate and vivid talking heads from a single anime image. © 2021, Springer Nature Switzerland AG.

关键词： Animation

Lite-HRNet: A lightweight high-resolution network

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yu, Changqian Xiao, Bin Gao, Changxin Yuan, Lu Zhang, Lei Sang, Nong Wang, Jingdong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Microsoft

We present an efficient high-resolution network, Lite-HRNet, for human pose estimation. We start by simply applying the efficient shuffle block in ShuffleNet to HRNet (high-resolution network), yielding stronger performance over popular lightweight networks, such as MobileNet, ShuffleNet, and Small HRNet. We find that the heavily-used pointwise (1 × 1) convolutions in shuffle blocks become the computational bottleneck. We introduce a lightweight unit, conditional channel weighting, to replace costly pointwise (1 × 1) convolutions in shuffle blocks. The complexity of channel weighting is linear w.r.t the number of channels and lower than the quadratic time complexity for pointwise convolutions. Our solution learns the weights from all the channels and over multiple resolutions that are readily available in the parallel branches in HRNet. It uses the weights as the bridge to exchange information across channels and resolutions, compensating the role played by the pointwise (1 × 1) convolution. Lite-HRNet demonstrates superior results on human pose estimation over popular lightweight networks. Moreover, Lite-HRNet can be easily applied to semantic segmentation task in the same lightweight manner. The code and models have been publicly available at https://***/HRNet/Lite-HRNet. © 2021, CC BY.

关键词： Convolution

Forget less,count better:a domain-incremental self-distillation learning benchmark for lifelong crowd counting

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2023年第2期24卷 187-202页

作者： Jiaqi GAO Jingqi LI Hongming SHAN Yanyun QU James ZWANG Fei-Yue WANG Junping ZHANG Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China Institute of Science and Technology for Brain-inspired Intelligence Fudan UniversityShanghai 200433China Shanghai Center for Brain Science and Brain-inspired Technology Shanghai 201210China School of Information Science and Technology Xiamen UniversityXiamen 361005China College of Information Sciences and Technology the Pennsylvania State UniversityUniversity ParkPA 16802USA State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Crowd counting has important applications in public safety and pandemic control.A robust and practical crowd counting system has to be capable of continuously learning with the newly incoming domain data in real-world scenarios instead of fitting one domain ***-the-shelf methods have some drawbacks when handling multiple domains:(1)the models will achieve limited performance(even drop dramatically)among old domains after training images from new domains due to the discrepancies in intrinsic data distributions from various domains,which is called catastrophic forgetting;(2)the well-trained model in a specific domain achieves imperfect performance among other unseen domains because of domain shift;(3)it leads to linearly increasing storage overhead,either mixing all the data for training or simply training dozens of separate models for different domains when new ones are *** overcome these issues,we investigate a new crowd counting task in incremental domain training setting called lifelong crowd *** goal is to alleviate catastrophic forgetting and improve the generalization ability using a single model updated by the incremental ***,we propose a self-distillation learning framework as a benchmark(forget less,count better,or FLCB)for lifelong crowd counting,which helps the model leverage previous meaningful knowledge in a sustainable manner for better crowd counting to mitigate the forgetting when new data arrive.A new quantitative metric,normalized Backward Transfer(nBwT),is developed to evaluate the forgetting degree of the model in the lifelong learning *** experimental results demonstrate the superiority of our proposed benchmark in achieving a low catastrophic forgetting degree and strong generalization ability.

关键词： Crowd counting Knowledge distillation Lifelong learning

Implicit Ray-Transformers for Multi-view Remote Sensing image Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Qi, Zipeng Chen, Hao Liu, Chenyang Shi, Zhenwei Zou, Zhengxia The Image Processing Center School of Astronautics The Beijing Key Laboratory of Digital Media The State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China The Shanghai Artificial Intelligence Laboratory Shanghai200232 China The Department of Guidance Navigation and Control School of Astronautics Beihang University Beijing100191 China

The mainstream CNN-based remote sensing (RS) image semantic segmentation approaches typically rely on massive labeled training data. Such a paradigm struggles with the problem of RS multi-view scene segmentation with limited labeled views due to the lack of considering 3D information within the scene. In this paper, we propose "Implicit Ray-Transformer (IRT)" based on Implicit Neural Representation (INR), for RS scene semantic segmentation with sparse labels (such as 4-6 labels per 100 images). We explore a new way of introducing multi-view 3D structure priors to the task for accurate and view-consistent semantic segmentation. The proposed method includes a two-stage learning process. In the first stage, we optimize a neural field to encode the color and 3D structure of the remote sensing scene based on multi-view images. In the second stage, we design a Ray Transformer to leverage the relations between the neural field 3D features and 2D texture features for learning better semantic representations. Different from previous methods that only consider 3D prior or 2D features, we incorporate additional 2D texture information and 3D prior by broadcasting CNN features to different point features along the sampled ray. To verify the effectiveness of the proposed method, we construct a challenging dataset containing six synthetic sub-datasets collected from the Carla platform and three real sub-datasets from Google Maps. Experiments show that the proposed method outperforms the CNN-based methods and the state-of-the-art INR-based segmentation methods in quantitative and qualitative metrics. Ablation study shows that under limited label conditions, the combination of the 3D structure prior and 2D texture can significantly improve the performance and effectively complete missing semantic information in novel views. Experiments also demonstrate the proposed method could yield geometry-consistent segmentation results against illumination changes and viewpoint changes. Our dat

关键词： Remote sensing

A Late-Stage Bitemporal Feature Fusion Network for Semantic Change Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Chenyao Zhang, Haotian Guo, Han Zou, Zhengxia Shi, Zhenwei The Image Processing Center School of Astronautics Beihang University Beijing100191 China The State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China The Shanghai Artificial Intelligence Laboratory Shanghai200232 China The Department of Guidance Navigation and Control School of Astronautics Beihang University Beijing100191 China

Semantic change detection is an important task in geoscience and earth observation. By producing a semantic change map for each temporal phase, both the land use land cover categories and change information can be interpreted. Recently some multi-task learning based semantic change detection methods have been proposed to decompose the task into semantic segmentation and binary change detection subtasks. However, previous works comprise triple branches in an entangled manner, which may not be optimal and hard to adopt foundation models. Besides, lacking explicit refinement of bitemporal features during fusion may cause low accuracy. In this letter, we propose a novel late-stage bitemporal feature fusion network to address the issue. Specifically, we propose local global attentional aggregation module to strengthen feature fusion, and propose local global context enhancement module to highlight pivotal semantics. Comprehensive experiments are conducted on two public datasets, including SECOND and Landsat-SCD. Quantitative and qualitative results show that our proposed model achieves new state-of-the-art performance on both datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics