检索结果-内蒙古大学图书馆

IET International Radar Conference (IRC 2023)

作者： Mingxiao Shao Cikang Su Zhe Zhang Bingchen Zhang Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing People's Republic of China Suzhou Key Laboratory of Microwave Imaging Processing and Application Technology and Suzhou Aerospace Information Research Institute Suzhou Jiangsu People's Republic of China

ISBN: (数字)9781837240982

Compressed sensing (CS) technology has been applied to topographic synthetic aperture radar (TomoSAR) imaging due to the sparsity of elevation signals. The traditional CS algorithms discretize the elevation into many grids and assume that the scatterers are located on grids, therefore, the accuracy of the traditional CS algorithms is limited by the off-grid effect. Although there are currently methods to address the off-grid effect, such as atomic norm minimization (ANM), its application is limited by the baseline distribution form of TomoSAR, which only applies to uniformly observed scenarios. Alternating Descent Conditional Gradient (ADCG) has been applied in many fields as a gridless imaging algorithm. In this paper, we apply ADCG to TomoSAR imaging for the first time, achieving the reconstruction of non-uniform baseline observation scenes. The effectiveness of ADCG in TomoSAR imaging was verified by comparing it with iterative soft thresholding (IST) and orthogonal matching pursuit (OMP) through simulation experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Domain Knowledge Based Small Sample Ship Target Detection Method 3

Domain Knowledge Based Small Sample Ship Target Detection Me...

引用

3rd China International SAR Symposium, CISS 2022

作者： Zhou, Jianing Li, Zheng Yang, Wei Zou, Fei Wang, Hui BeiHang University School of Electronic and Information Engineering Beijing China Aerospace Information Research Institute Beijing China Chinese Academy of Sciences Key Laboratory of Technology in Geospatial Information Processing and Application System Beijing China Beijing Institute of Remote Sensing Information Beijing China Shanghai Institute of Satellite Engineering Shanghai China

ISBN: (数字)9798350398717

ISBN: (纸本)9798350398717

Synthetic Aperture Radar (SAR) is widely used in ship target detection because of its ability to operate under various weather conditions. However, some target images are difficult to obtain and label, resulting in a small sample size, which limits the development of target detection. Aiming at the problem of ship target detection in small sample SAR images, domain knowledge is used to revise and enhance the basic model in this paper. Firstly, a lightweight convolutional neural network model more suitable for small-sample SAR image ship target classification is proposed, involving target pixel and aspect ratio as domain knowledge to correct the classification results. Then, for ship target detection in SAR images, the acquisition method of scale class domain knowledge is improved. Moreover, texture-related domain knowledge based on the gray level co-occurrence matrix is extracted and used as classification features for the model to revise the model. Finally, Marine Targets Classification Dataset (MTCD) and Marine Targets Detection Dataset (MTDD) are briefly introduced and adjusted to meet the requirements of this research through screening and modification. The test results on balanced MTDD and small-sample datasets demonstrate the effectiveness of domain knowledge in improving network performance. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning based Trajectory Planning for Autonomous Vehicles

Reinforcement Learning based Trajectory Planning for Autonom...

引用

2021 China Automation Congress, CAC 2021

作者： Wang, Zhaoxu Tu, Jingzheng Chen, Cailian Department of Automation Shanghai Jiao Tong University Shanghai 200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 P. R. China

ISBN: (纸本)9781665426473

The trajectory planning of autonomous vehicles requires making safe sequential decisions instantaneously. The most significant challenge is the uncertainties brought by complex interactions with other road users in diverse driving scenarios. Previous rule-based solutions lack generalization and only suit for limited simple environments. Moreover, another approach generates feasible action sequences based on motion planning, which ignores the interactions between vehicle participants. This paper proposes a hierarchical framework based on reinforcement learning for autonomous driving. Instead of directly mapping the sensor information to the low-level control signal, we first choose a desired state and generate a target trajectory in a Frenet frame according to the desired state. Then a low-level controller is used to track the target trajectory. A reinforcement learning algorithm combining planning and learning is introduced to choose the desired state. This trajectory planning framework is evaluated on a lane switching case in a simulated environment. The simulation results demonstrate the effectiveness of the proposed method. © 2021 IEEE

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

DetFlowTrack: 3D Multi-object Tracking based on Simultaneous Optimization of Object Detection and Scene Flow Estimation

arXiv

引用

arXiv 2022年

作者： Shen, Yueling Wang, Guangming Wang, Hesheng Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai 200240 China

3D Multi-Object Tracking (MOT) is an important part of the unmanned vehicle perception module. Most methods optimize object detection and data association independently. These methods make the network structure complicated and limit the improvement of MOT accuracy. we proposed a 3D MOT framework based on simultaneous optimization of object detection and scene flow estimation. In the framework, a detection-guidance scene flow module is proposed to relieve the problem of incorrect inter-frame assocation. For more accurate scene flow label especially in the case of motion with rotation, a box-transformation-based scene flow ground truth calculation method is proposed. Experimental results on the KITTI MOT dataset show competitive results over the state-of-the-arts and the robustness under extreme motion with rotation. © 2022, CC BY-NC-SA.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Autonomous Exploration and Mapping for Mobile Robots via Cumulative Curriculum Reinforcement Learning

arXiv

引用

arXiv 2023年

作者： Li, Zhi Xin, Jinghao Li, Ning Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China

Deep reinforcement learning (DRL) has been widely applied in autonomous exploration and mapping tasks, but often struggles with the challenges of sampling efficiency, poor adaptability to unknown map sizes, and slow simulation speed. To speed up convergence, we combine curriculum learning (CL) with DRL, and first propose a Cumulative Curriculum Reinforcement Learning (CCRL) training framework to alleviate the issue of catastrophic forgetting faced by general CL. Besides, we present a novel state representation, which considers a local egocentric map and a global exploration map resized to the fixed dimension, so as to flexibly adapt to environments with various sizes and shapes. Additionally, for facilitating the fast training of DRL models, we develop a lightweight grid-based simulator, which can substantially accelerate simulation compared to popular robot simulation platforms such as Gazebo. Based on the customized simulator, comprehensive experiments have been conducted, and the results show that the CCRL framework not only mitigates the catastrophic forgetting problem, but also improves the sample efficiency and generalization of DRL models, compared to general CL as well as without a curriculum. Our code is available at https://***/BeamanLi/CCRL_Exploration. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based activity recognition and fine motor identification using 2D skeletons of cynomolgus monkeys

引用

Zoological Research 2023年第5期44卷 967-980页

作者： Chuxi Li Zifan Xiao Yerong Li Zhinan Chen Xun Ji Yiqun Liu Shufei Feng Zhen Zhang Kaiming Zhang Jianfeng Feng Trevor W.Robbins Shisheng Xiong Yongchang Chen Xiao Xiao School of Information Science and Technology Micro Nano System Center Fudan UniversityShanghai 200433China Department of Anesthesiology Huashan HospitalKey Laboratory of Computational Neuroscience and Brain-Inspired IntelligenceMinistry of EducationBehavioral and Cognitive Neuroscience CenterInstitute of Science and Technology for Brain-Inspired IntelligenceMOE Frontiers Center for Brain ScienceFudan UniversityShanghai 200433China Kuang Yaming Honors School Nanjing UniversityNanjingJiangsu 210023China Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China State Key Laboratory of Primate Biomedical Research Institute of Primate Translational MedicineKunming University of Science and TechnologyKunmingYunnan 650500China New Vision World LLC. Aliso ViejoCalifornia 92656USA Behavioural and Clinical Neuroscience Institute University of CambridgeCambridgeCB21TNUK

Video-based action recognition is becoming a vital tool in clinical research and neuroscientific study for disorder detection and ***,action recognition currently used in non-human primate(NHP)research relies heavily on intense manual labor and lacks standardized *** this work,we established two standard benchmark datasets of NHPs in the laboratory:Monkeyin Lab(Mi L),which includes 13 categories of actions and postures,and MiL2D,which includes sequences of two-dimensional(2D)skeleton ***,based on recent methodological advances in deep learning and skeleton visualization,we introduced the Monkey Monitor Kit(Mon Kit)toolbox for automatic action recognition,posture estimation,and identification of fine motor activity in *** the datasets and Mon Kit,we evaluated the daily behaviors of wild-type cynomolgus monkeys within their home cages and experimental environments and compared these observations with the behaviors exhibited by cynomolgus monkeys possessing mutations in the MECP2 gene as a disease model of Rett syndrome(RTT).Mon Kit was used to assess motor function,stereotyped behaviors,and depressive phenotypes,with the outcomes compared with human manual *** Kit established consistent criteria for identifying behavior in NHPs with high accuracy and efficiency,thus providing a novel and comprehensive tool for assessing phenotypic behavior in monkeys.

关键词： Action recognition Fine motor identification Two-stream deep model 2D skeleton Non-human primates Rett syndrome

来源：评论

学校读者我要写书评

暂无评论

Spatial Temporal Block Transformer Network for Skeleton-Based Action Recognition

Spatial Temporal Block Transformer Network for Skeleton-Base...

引用

Chinese Automation Congress (CAC)

作者： Fan Yang Dewei Li Gang Wang Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

Recently, skeleton-based action recognition has be-come very popular in areas such as autonomous driving and environmental awareness due to its small data size and high ac-curacy. Graph convolutional networks (GCN) can model skeleton data well by adapting to the graph structure of the skeleton. However, GCN lacks the ability to extract global spatial and temporal dependencies. Moreover, an action is not only formed by one single skeleton point or frame but several skeleton points and frames. In this paper, a novel spatial-temporal block transformer network based on the self-attention mechanism is proposed, which efficiently models global spatial-temporal dependencies. The model uses spatial-temporal blocks as input, and spatial-temporal feature aggregation modules are applied to enhance the information exchange between blocks. Extensive experiments on the two skeleton-based action recognition datasets show the remarkable performance of our model, which outperforms most GCN-based methods and all transformer-based methods.

关键词： Adaptation models Automation Transformers Skeleton Data models Convolutional neural networks information exchange

来源：评论

学校读者我要写书评

暂无评论

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning 22

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Lea...

引用

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： Cao, Weipeng Yao, Xuyang Xu, Zhiwu Pan, Yinghui Sun, Yixuan Li, Dachuan Qiu, Bohua Wei, Muheng Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (纸本)9798331527471

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model’s capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods. © 2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

CPR-Net: A Novel Joint Learning Network for Pulmonary Nodule Evaluation

CPR-Net: A Novel Joint Learning Network for Pulmonary Nodule...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Gong Chen Jun Liu Chen-Qian Li Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China

Lung cancer is the most common malignant tumor worldwide, with high mortality rates. Pulmonary nodule is a common manifestation of lung cancer. Accurate segmentation and detection of pulmonary nodules from CT scans are essential for proper assessment of patient prognosis. However, this task remains challenging due to various factors, such as class imbalance and the need for detailed characterization of lung nodule segmentation. To address these issues, we propose a novel network, CPR-Net (Convolutional Pyramid Residuals-Net), that combines segmentation and benign-malignant classification for CT images of lung nodules. Our approach utilizes a PBMM module to expand the perception field and enhance the representation capability of the model, allowing it to learn more detailed information. We evaluate the classification performance using accuracy, precision, recall, F1 score, AUC, and the segmentation performance using the Dice coefficient. Experiments on both publicly available datasets and self-constructed datasets demonstrate that our proposed method in this paper outperforms other methods in terms of classification and segmentation performance under limited labeled data conditions. Moreover, Our results suggest that this model has great potential for improving lung nodule diagnosis in radiology for heterogeneous intranodal images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

control Strategy of Multi-axis Serial Manipulator Based on Improved Active Disturbance Rejection control

Control Strategy of Multi-axis Serial Manipulator Based on I...

引用

第34届中国控制与决策会议

作者： Pengcheng Hu Chaochen Gu Kaijie Wu Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information ProcessingMinistry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management

Aiming at the sudden change of load torque and uncertain external disturbance that multi-axis serial manipulators may face during operation,an improved Active Disturbance Rejection controller(ADRC) assisted by a Nonlinear Disturbance Observer(NLDOB) is designed and implemented in this *** realizes the estimation and compensation of known model parameter perturbation,and NLDOB is introduced to estimate and compensate the load torque and other unmodeled dynamic factors of the ***,the lumped control object model of three-bar mechanism and permanent magnet DC motor is established,and the control response curves of improved ADRC,traditional ADRC,and PID under the same conditions are compared and analyzed through *** experimental results show that compared with the traditional ADRC and PID,the improved ADRC has faster response speed,smaller overshoot and stronger robustness.

关键词： ADRC Multi-axis serial manipulator Permanent magnet DC motor NLDOB Load estimation

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：