检索结果-内蒙古大学图书馆

IEEE International Conference on Robotics and Biomimetics

作者： Beijia Tai Yangjie Wei Guangyu Zhang Yuqing He Siyao Cui Key Laboratory of Intelligent Computing in Medical Image Ministry of Education College of Computer Science and Engineering Northeastern University Shenyang China Shenyang Institute of Automation Chinese Academy of Science Shenyang China

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

Accurate tracking of unmanned devices is essen-tial for higher-level decision-making in collaborative confrontation scenarios. However, the robustness of current positioning methods based on Ultra-Wideband (UWB) is limit, and the positioning error is unstable. This paper presents a collabo-rative localization algorithm specifically designed for indoor unmanned systems, which leverages UWB technology combined with Least Squares (LS) and Extended Kalman Filter (EKF) models to achieve anchor calibration, as well as precise and stable positioning of unmanned devices. First, the positions of anchors is estimated using fixed-point ranging information; Second, the positions of anchors are simultaneously corrected while locating the tags on unmanned devices. The experimental results show that our algorithm achieves positioning accuracy within 10 cm in the three-dimensional space, even with a ranging error of 5 cm.

关键词： Location awareness Accuracy Three-dimensional displays Autonomous systems Collaboration Distance measurement Robustness Calibration Robots Ultra wideband technology

来源：评论

学校读者我要写书评

暂无评论

REMOTE: Real-time Ego-motion Tracking for Various Endoscopes via Multimodal Visual Feature Learning

arXiv

引用

arXiv 2025年

作者： Shao, Liangjing Chen, Benshuang Zhao, Shuting Chen, Xinrong Academy for Engineering & Technology Fudan University China Shanghai Key Laboratory of Medical Image Computing and Computer-Assisted Intervention Fudan University China

Real-time ego-motion tracking for endoscope is a significant task for efficient navigation and robotic automation of endoscopy. In this paper, a novel framework is proposed to perform real-time ego-motion tracking for endoscope. Firstly, a multi-modal visual feature learning network is proposed to perform relative pose prediction, in which the motion feature from the optical flow, the scene features and the joint feature from two adjacent observations are all extracted for prediction. Due to more correlation information in the channel dimension of the concatenated image, a novel feature extractor is designed based on an attention mechanism to integrate multi-dimensional information from the concatenation of two continuous frames. To extract more complete feature representation from the fused features, a novel pose decoder is proposed to predict the pose transformation from the concatenated feature map at the end of the framework. At last, the absolute pose of endoscope is calculated based on relative poses. The experiment is conducted on three datasets of various endoscopic scenes and the results demonstrate that the proposed method outperforms state-of-the-art methods. Besides, the inference speed of the proposed method is over 30 frames per second, which meets the real-time requirement. The project page is here: *** © 2025, CC BY.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Retinopathy Classification with OCT images via Disentangling Representation and Adaptation Networks

Cross-Domain Retinopathy Classification with OCT Images via ...

引用

Optoelectronics Global Conference (OGC)

作者： Wickramaarachchi Minidu Thiranjaya Yuan Li Lei Tao Yuemei Luo Jiangsu Provincial Key Laboratory of Intelligent Medical Image Computing (iMIC) School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing China Jiangsu Provincial Key Laboratory of Intelligent Medical Image Computing (iMIC) School of Computer Science Nanjing University of Information Science and Technology Nanjing China Jiangsu Provincial Key Laboratory of Intelligent Medical Image Computing (iMIC) School of Future Technology Nanjing University of Information Science and Technology Nanjing China

ISBN: (数字)9798350391466

ISBN: (纸本)9798350391473

Deep learning methods have shown significant potential in retinopathy classification using optical coherence tomography (OCT) images. However, substantial challenges arise due to domain shift issues, which are attributable to heterogeneity in data collection devices, variations in subject populations, and discrepancies in imaging protocols and parameters. To address these, we propose a novel approach leveraging Disentangling Representation and Adaptation Networks (DRANet) to enhance the robustness and generalization of retinopathy classification models across different OCT datasets. Our methodology involves developing DRANet, a specialized network architecture designed to disentangle representations of data and facilitate domain adaptation. DRANet includes components for learning invariant representations across domains through adversarial training, ensuring robustness against domain shifts. DRANet encodes individual representations of content and style from both source and target images. Then, it adapts the domain by incorporating the transferred style factor into the content factor, along with learnable weights specified for each domain. This learning framework allows bidirectional domain. After conducting extensive experiments conducted on three public datasets achieved accuracies of $\mathrm{8 8 \%, ~} \mathrm{9 0 \%}$, and $\mathrm{9 2 \%}$ under three cross-domain scenarios, demonstrating the efficacy of our approach in mitigating domain shift effects and improving retinopathy classification performance.

关键词： Training Deep learning Protocols Retinopathy Optical coherence tomography Imaging Coherence Network architecture Data collection Robustness

来源：评论

学校读者我要写书评

暂无评论

Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentation

Both Style and Distortion Matter: Dual-Path Unsupervised Dom...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Xu Zheng Jinjing Zhu Yexin Liu Zidong Cao Chong Fu Lin Wang Northeastern University AI Thrust HKUST(GZ) Key Laboratory of Intelligent Computing in Medical Image Ministry of Education NEU China Dept. of CSE HKUST

The ability of scene understanding has sparked active research for panoramic image semantic segmentation. However, the performance is hampered by distortion of the equirectangular projection (ERP) and a lack of pixel-wise annotations. For this reason, some works treat the ERP and pinhole images equally and transfer knowledge from the pinhole to ERP images via unsupervised domain adaptation (UDA). However, they fail to handle the domain gaps caused by: 1) the inherent differences between camera sensors and captured scenes; 2) the distinct image formats (e.g., ERP and pinhole images). In this paper, we propose a novel yet flexible dual-path UDA framework, DPPASS, taking ERP and tangent projection (TP) images as inputs. To reduce the domain gaps, we propose cross-projection and intra-projection training. The cross-projection training includes tangent-wise feature contrastive training and prediction consistency training. That is, the former formulates the features with the same projection locations as positive examples and vice versa, for the models' awareness of distortion, while the latter ensures the consistency of cross-model predictions between the ERP and TP. Moreover, adversarial intra-projection training is proposed to reduce the inherent gap, between the features of the pinhole images and those of the ERP and TP images, respectively. Importantly, the TP path can be freely removed after training, leading to no additional inference cost. Extensive experiments on two benchmarks show that our DPPASS achieves + 1.06% mIoU increment than the state-of-the-art approaches. https://***/cvpr23/DPPASS

关键词：

来源：评论

学校读者我要写书评

暂无评论

GALOPA: graph transport learning with optimal plan alignment 23

GALOPA: graph transport learning with optimal plan alignment

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Yejiang Wang Yuhai Zhao Zhengkui Wang Ling Li School of Computer Science and Engineering Northeastern University China and Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University China InfoComm Technology Cluster Singapore Institute of Technology Singapore

Self-supervised learning on graphs aims to learn graph representations in an unsupervised manner. While graph contrastive learning (GCL - relying on graph augmentation for creating perturbation views of anchor graphs and maximizing/minimizing similarity for positive/negative pairs) is a popular self-supervised method, it faces challenges in finding label-invariant augmented graphs and determining the exact extent of similarity between sample pairs to be achieved. In this work, we propose an alternative self-supervised solution that (i) goes beyond the label invariance assumption without distinguishing between positive/negative samples, (ii) can calibrate the encoder for preserving not only the structural information inside the graph, but the matching information between different graphs, (iii) learns isometric embeddings that preserve the distance between graphs, a by-product of our objective. Motivated by optimal transport theory, this scheme relies on an observation that the optimal transport plans between node representations at the output space, which measure the matching probability between two distributions, should be consistent with the plans between the corresponding graphs at the input space. The experimental findings include: (i) The plan alignment strategy significantly outperforms the counterpart using the transport distance; (ii) The proposed model shows superior performance using only node attributes as calibration signals, without relying on edge information; (iii) Our model maintains robust results even under high perturbation rates; (iv) Extensive experiments on various benchmarks validate the effectiveness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

3D Clothed Human Reconstruction From One In-the-Wild RGB image

3D Clothed Human Reconstruction From One In-the-Wild RGB Ima...

引用

IEEE International Conference on image Processing

作者： Liangjing Shao Benshuang Chen Xinrong Chen Academy for Engineering & Technology Fudan University Shanghai China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

In recent years, much achievement have been made in the field of 3D clothed human reconstruction. However, most of researches performed not well for reconstruction from in-the-wild images due to the domain gap between the synthetic images of training datasets and the in-the-wild images. In this study, a modular model, including clothes encoder, body encoder and cloth generator, is proposed to perform 3D clothed human reconstruction from one single-view in-the-wild RGB image. In particular, we introduce the adaptive aggregation of convolution and multi-head attention into the cloth encoder and apply the adjustment of the segmentation at the preprocessing stage. According to experiments on MSCOCO and 3DPW datasets, the proposed method achieves state-of-the-art performance on 3D clothed human reconstruction from in-the-wild images compared with previous works.

关键词： Training Solid modeling image segmentation Adaptation models Three-dimensional displays Convolution Data preprocessing

来源：评论

学校读者我要写书评

暂无评论

Source-Free Unsupervised Domain Adaptation Fundus image Segmentation via Entropy Optimization and Anatomical Priors

引用

Procedia Computer Science 2024年 250卷 182-187页

作者： Yijia Chen Jiapeng Li Haoze Yu Lin Qi Yongchun Li College of Medicine and Biological Information Engineering Northeastern University Shenyang 110169 China Engineering Research Center of Medical Imaging and Intelligent Analysis Ministry of Education Shenyang 110169 China Key Laboratory of Medical Image Computing Ministry of Education Northeastern University Shenyang 110169 China Shenyang Contain Electronic Technology Co. Ltd. Shenyang 110167 China

This research focuses on fundus image segmentation within a source-free domain adaptation framework, where the availability of source images during the adaptation phase is limited due to privacy concerns. Although Source-Free Unsupervised Domain Adaptation (SFUDA) methods have seen significant innovative developments in recent years, they still face several challenges which include suboptimal performance due to substantial domain discrepancies, reliance on potentially noisy or inaccurate pseudo-labels during the adaptation process, and a lack of integration with domain-specific prior knowledge. To address these issues, this paper proposes a SFUDA framework via Entropy Optimization and Anatomical Priors (EOAPNet). To alleviate the influence of the divergence between the source and target domains, EOAPNet primarily evaluates the uncertainty (i.e., entropy) of predictions on target domain data and improves the model by focusing on high-entropy pixels or regions. Additionally, a weak-strong augmentation mean-teacher scheme is introduced in EOAPNet, which can enhance the accuracy of pseudo-labels and reduce error propagation. Thirdly, by integrating an anatomical knowledge-based class ratio prior into the overall loss function in the form of a Kullback–Leibler (KL) divergence, EOAPNet also incorporates expert domain knowledge. EOAPNet yields comparable results to several state-of-the-art adaptation techniques in experiments on two retinal image segmentation datasets involving the RIM-ONE-r3 and Drishti-GS datasets.

关键词： Source-Free unsupervised domain adaptation Entropy Anatomical priors Mean teacher

来源：评论

学校读者我要写书评

暂无评论

Multi-residual 2D network integrating spatial correlation for whole heart segmentation

引用

Computers in Biology and Medicine 2024年 172卷 108261-108261页

作者： Huang, Yan Yang, Jinzhu Sun, Qi Yuan, Yuliang Li, Honghe Hou, Yang Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Liaoning Shenyang China School of Computer Science and Engineering Northeastern University Liaoning Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Liaoning Shenyang China Department of Radiology Shengjing Hospital of China Medical University Liaoning Shenyang China

Whole heart segmentation (WHS) has significant clinical value for cardiac anatomy, modeling, and analysis of cardiac function. This study aims to address the WHS accuracy on cardiac CT images, as well as the fast inference speed and low graphics processing unit (GPU) memory consumption required by practical clinical applications. Thus, we propose a multi-residual two-dimensional (2D) network integrating spatial correlation for WHS. The network performs slice-by-slice segmentation on three-dimensional cardiac CT images in a 2D encoder–decoder manner. In the network, a convolutional long short-term memory skip connection module is designed to perform spatial correlation feature extraction on the feature maps at different resolutions extracted by the sub-modules of the pre-trained ResNet-based encoder. Moreover, a decoder based on the multi-residual module is designed to analyze the extracted features from the perspectives of multi-scale and channel attention, thereby accurately delineating the various substructures of the heart. The proposed method is verified on a dataset of the multi-modality WHS challenge, an in-house WHS dataset, and a dataset of the abdominal organ segmentation challenge. The dice, Jaccard, average symmetric surface distance, Hausdorff distance, inference time, and maximum GPU memory of the WHS are 0.914, 0.843, 1.066 mm, 15.778 mm, 9.535 s, and 1905 MB, respectively. The proposed network has high accuracy, fast inference speed, minimal GPU memory consumption, strong robustness, and good generalization. It can be deployed to clinical practical applications for WHS and can be effectively extended and applied to other multi-organ segmentation fields. The source code is publicly available at https://***/nancy1984yan/MultiResNet-SC. © 2024 Elsevier Ltd

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Joint Secure and Covert Communications for Active STAR-RIS Assisted ISAC Systems

引用

IEEE Transactions on Wireless Communications 2025年

作者： Guo, Liang Jia, Jie Mu, Xidong Liu, Yuanwei Chen, Jian Wang, Xingwei Northeastern University School of Computer Science and Engineering China Northeastern University Engineering Research Center of Security Technology of Complex Network System Ministry of Education China Northeastern University Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Shenyang110819 China BelfastBT3 9DT United Kingdom Department of Electrical and Electronic Engineering China

This paper investigates the design of jointly supporting physical layer security (PLS) and covert communications (CCs) in an active simultaneously transmitting and reflecting reconfigurable intelligent surface (a-STAR-RIS) assisted integrated sensing and communication (ISAC) system. Due to the unified waveform design of ISAC signals, we consider a challenging scenario with two targets being suspicious attackers, where one warden target potentially detects the confidential transmission behavior of covert users and another eavesdropper target attempts to intercept the broadcasted confidential information of security users. We investigate the joint beamforming design at the base station (BS) and the a-STAR-RIS to achieve a high-quality sensing beampattern while meeting covertness and security communication requirements. (1) For the ideal scenario with perfect channel state information (CSI) and precise target locations, we propose an alternative optimization (AO) method to address the optimization problem involving highly coupled variables. Specifically, the optimal beamforming design at the BS is handled using the semi-definite relaxation (SDR) technique, while the beamforming design at the a-STAR-RIS is addressed through a penalty-based iterative algorithm. (2) A more practical case with uncertain target locations and imperfect CSI is considered to achieve a robust beamforming design, where the non-deterministic outage probability constraints are effectively transformed by employing the Bernstein-type inequality. Numerical results demonstrate the superiority of the a-STAR-RIS over the baseline cases and certify that the proposed algorithms can effectively balance the tradeoff among the sensing quality, covert and secure communication requirements. Besides, results also show that the proposed robust beamforming scheme can construct adequate sensing beampattern, even with imperfect CSI and uncertain target locations. © 2002-2012 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Layph: Making Change Propagation Constraint in Incremental Graph Processing by Layering Graph

arXiv

引用

arXiv 2023年

作者： Yu, Song Gong, Shufeng Zhang, Yanfeng Yu, Wenyuan Yin, Qiang Tian, Chao Tao, Qian Yan, Yongze Yu, Ge Zhou, Jingren Northeastern University United States Alibaba Group China Shanghai Jiao Tong University China Chinese Academy of Sciences China Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University China

Real-world graphs are constantly evolving, which demands updates of the previous analysis results to accommodate graph changes. By using the memoized previous computation state, incremental graph computation can reduce unnecessary recomputation. However, a small change may propagate over the whole graph and lead to large-scale iterative computations. To address this problem, we propose Layph, a two-layered graph framework. The upper layer is a skeleton of the graph which is much smaller than the original graph, and the lower layer has some disjoint subgraphs. Layph limits costly global iterative computations on the original graph to the small graph skeleton and a few subgraphs updated with the input graph changes. In this way, many vertices and edges are not involved in iterative computations, which significantly reduces the computation overhead and improves the performance of incremental graph processing. Our experimental results show that Layph outperforms current state-of-the-art incremental graph systems by 9.08× on average (up to 36.66×) in response time. Copyright © 2023, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：