检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Hu, Anning Li, Ang Jin, Xirui Zou, Danping Shanghai Key Laboratory of Navigation and Location-based Service Shanghai Jiao Tong University China

We introduce ThermoStereoRT, a real-time thermal stereo matching method designed for all-weather conditions that recovers disparity from two rectified thermal stereo images, envisioning applications such as night-time drone surveillance or under-bed cleaning robots. Leveraging a lightweight yet powerful backbone, ThermoStereoRT constructs a 3D cost volume from thermal images and employs multi-scale attention mechanisms to produce an initial disparity map. To refine this map, we design a novel channel and spatial attention module. Addressing the challenge of sparse ground truth data in thermal imagery, we utilize knowledge distillation to boost performance without increasing computational demands. Comprehensive evaluations on multiple datasets demonstrate that ThermoStereoRT delivers both real-time capacity and robust accuracy, making it a promising solution for real-world deployment in various challenging environments. Our code will be released on https: //***/SJTU-ViSYS-team/ThermoStereoRT. Copyright © 2025, The Authors. All rights reserved.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Stereo-LiDAR Depth Estimation with Deformable Propagation and Learned Disparity-Depth Conversion

Stereo-LiDAR Depth Estimation with Deformable Propagation an...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Ang Li Anning Hu Wei Xi Wenxian Yu Danping Zou Shanghai Key Laboratory of Navigation and Location-Based Service Shanghai Jiao Tong University Intelligent Perception Institute Midea Corporate Research Center Blue-Orange Lab Midea Group

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Accurate and dense depth estimation with stereo cameras and LiDAR is an important task for automatic driving and robotic perception. While sparse hints from LiDAR points have improved cost aggregation in stereo matching, their effectiveness is limited by the low density and non-uniform distribution. To address this issue, we propose a novel stereo-LiDAR depth estimation network with Semi-Dense hint Guidance, named SDG-Depth. Our network includes a deformable propagation module for generating a semi-dense hint map and a confidence map by propagating sparse hints using a learned deformable window. These maps then guide cost aggregation in stereo matching. To reduce the triangulation error in depth recovery from disparity, especially in distant regions, we introduce a disparity-depth conversion module. Our method is both accurate and efficient. The experimental results on benchmark tests show its superior performance. Our code is available at https://***/SJTU-ViSYS/SDG-Depth.

关键词： Laser radar Costs Accuracy Three-dimensional displays Robot vision systems Estimation Reliability

来源：评论

学校读者我要写书评

暂无评论

Stereo-LiDAR Depth Estimation with Deformable Propagation and Learned Disparity-Depth Conversion

arXiv

引用

arXiv 2024年

作者： Li, Ang Hu, Anning Xi, Wei Yu, Wenxian Zou, Danping Shanghai Key Laboratory of Navigation and Location-based Service Shanghai Jiao Tong University China Intelligent Perception Institute Midea Corporate Research Center China Blue-Orange Lab Midea Group China

Accurate and dense depth estimation with stereo cameras and LiDAR is an important task for automatic driving and robotic perception. While sparse hints from LiDAR points have improved cost aggregation in stereo matching, their effectiveness is limited by the low density and nonuniform distribution. To address this issue, we propose a novel stereo-LiDAR depth estimation network with Semi-Dense hint Guidance, named SDG-Depth. Our network includes a deformable propagation module for generating a semi-dense hint map and a confidence map by propagating sparse hints using a learned deformable window. These maps then guide cost aggregation in stereo matching. To reduce the triangulation error in depth recovery from disparity, especially in distant regions, we introduce a disparity-depth conversion module. Our method is both accurate and efficient. The experimental results on benchmark tests show its superior performance. Our code is available at https://***/SJTU-ViSYS/SDG-Depth. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

An Immediate Update Strategy of Multi-State Constraint Kalman Filter

arXiv

引用

arXiv 2024年

作者： Zhang, Qingchao Ouyang, Wei Han, Jiale Cai, Qi Zhu, Maoran Wu, Yuanxin Shanghai Key Lab of Navigation and Location Service School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai200240 China

The lightweight Multi-state Constraint Kalman Filter (MSCKF) has been well-known for its high efficiency, in which the delayed update has been usually adopted since its proposal. This work investigates the immediate update strategy of MSCKF based on timely reconstructed 3D feature points and measurement constraints. The differences between the delayed update and the immediate update are theoretically analyzed in detail. It is found that the immediate update helps construct more observation constraints and employ more filtering updates than the delayed update, which improves the linearization point of the measurement model and therefore enhances the estimation accuracy. Numerical simulations and experiments show that the immediate update strategy significantly enhances MSCKF even with a small amount of feature observations. Copyright © 2024, The Authors. All rights reserved.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Efficient Semantic-Aware TSDF Mapping with Adaptive Resolutions

Efficient Semantic-Aware TSDF Mapping with Adaptive Resoluti...

引用

Robotics, Automation and Artificial Intelligence (RAAI), IEEE International Conference on

作者： Weidong Wang Yu Hu Wei Xi Danping Zou Wenxian Yu Shanghai Key Laboratory of Navigation and Location-based Service Shanghai Jiao Tong University Shanghai China Intelligent Perception Institute Midea Corporate Research Center Foshan China

ISBN: (数字)9798350307566

ISBN: (纸本)9798350307573

Mapping unknown environments based on vision sensors is a key step for robot planning. Existing methods usually adopt a fixed resolution to store the occupancy information. A high resolution consumes excessive computational resources while a low one results in unbearable information loss of specific user-interested regions that require precise representation. To address these challenges, we develop an efficient semantic-aware Truncated Signed Distance Function (TSDF) mapping system with adaptive resolutions. Our map representation consists of multiple layers with different voxel sizes. Meanwhile, with the assistance of semantic segmentation or object detection models, we identify key objects in the scene and use higher resolutions for their reconstruction. Semantic information can guide the selection of map resolution and also potentially provide valuable insights for more complex user-defined navigation tasks. By leveraging our lightweight implementation, our system achieves real-time computation and less memory consumption than existing frameworks.

关键词： Adaptation models Adaptive systems Three-dimensional displays Semantic segmentation Computational modeling Semantics Object detection

来源：评论

学校读者我要写书评

暂无评论

BDS B1I multipath channel statistical model comparison between static and dynamic scenarios in dense urban canyon environment

引用

Satellite navigation 2020年第1期1卷 287-302页

作者： Xin Chen Di He Ling Pei Shanghai Key Laboratory of Navigation and Location-based Service School of Electronic Information and Electrical EngineeringShanghai Jiao Tong UniversityDongchuan Road 800Shanghai 200240China

Global navigation Satellite System(GNSS)multipath channel models are fundamental and critical for signal simulation and receiver performance *** also aid the designing of suitable multipath error mitigation algorithms when the properties of multipath channel are ***,there is insufficient existing research on BeiDou navigation Satellite System(BDS)signal multipath channel *** this study,multipath channel statistical models are established on the basis of extensive datasets of the BDS B1I signal.A multipath parameter estimation algorithm is designed to extract information of multipath rays from the intermediate frequency *** delay,power loss,Doppler fading frequency,and lifetime distribution models for static and dynamic vehicle platforms are established and compared,and the effects of the satellite orbit type and platform speed on the models are *** results reveal the detailed distribution and variation characteristics of the multipath parameters and are valuable for the development of accurate urban navigation systems.

关键词： Multipath channel statistical model Multipath delay Multipath power loss Multipath Doppler fading frequency Multipath lifetime

来源：评论

学校读者我要写书评

暂无评论

Attitude Control based on Reinforcement Learning for Quadrotor

Attitude Control Based on Reinforcement Learning for Quadrot...

引用

International Conference on Autonomous Unmanned Systems, ICAUS 2021

作者： Wang, Yao Zhang, Weiping Mou, Jiawang Zheng, Kexin National Key Laboratory of Science and Technology on Micro/Nano Fabrication Laboratory Laboratory for Thin Film and Micro Fabrication of the Ministry of Education Shanghai Key Lab of Navigation and Location-Based Services Department of Micro-nano Electronics School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai200240 China

ISBN: (纸本)9789811694912

To design a good control system for a 6 degree-of-freedom aircraft is not an easy work. The classic linear method such as PID can’t provide a good performance for complex nonlinear systems in some cases. In this paper, an end-to-end policy using Reinforcement Learning (RL) based on Proximal Policy Optimization (PPO) is proposed. This mothed is used to established a mapping from the observed states to the motor signals to control the attitude of quadrotor. In order to evaluate the performance of the end-to-end controller based on PPO, a RL-PID controller is designed to compare with the end-to-end controller in this paper. The result shows that the performance of the end-to-end controller based on PPO is better. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Sparse-to-Dense Hint Guided Stereo-LiDAR Fusion

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Li, Ang Zuo, Dexin Hu, Anning Yu, Wenxian Zou, Danping Shanghai Jiao Tong University Shanghai Key Laboratory of Navigation and Location-based Service Shanghai China

One challenge in stereo-LiDAR fusion arises from the sparsity and non-uniform distribution of LiDAR data. Existing methods expand sparse LiDAR data to produce semi-dense hints as guidance for fusion. However, the absence of depth cues beyond the expanded areas may still limit performance. To address this challenge, we propose a novel sparse-to-dense hint guided stereo-LiDAR fusion method. The key idea is to use a dense hint map generated by a lightweight network as guidance, with sparse LiDAR points and a monocular image as inputs. The dense hints are then employed to construct and explicitly regularize a multi-modal cost volume via integrating the geometric cues from the hints and the visual information from the images to produce better stereo prediction. The construction and aggregation of cost volume follow a well-designed coarse-to-fine strategy along with a pixel-wise search range adjustment module, facilitating fast computation while preserving fine details. Finally, a confidence-based fusion module is performed to adaptively produce the ultimate prediction based on the monocular and stereo estimations. The experimental results show that our method significantly outperforms existing methods with high inference efficiency across multiple benchmark datasets. © 1991-2012 IEEE.

关键词： Stereo vision

来源：评论

学校读者我要写书评

暂无评论

Classification of Schizophrenia Patients According to DNA Methylation Data based on Meta-learning

Classification of Schizophrenia Patients According to DNA Me...

引用

2022 IEEE Conference on Telecommunications, Optics and Computer Science, TOCS 2022

作者： Li, Qi Liu, Haichun Li, Lanzhen Chen, Tao Zhang, Qinting Li, Haozhe Pan, Changchun Dept. of Automation Shanghai Jiao Tong University Shanghai200240 China Dept. of Automation Ningbo Artificial Intelligent Institute Shanghai Jiao Tong University Ningbo315016 China Department of Economics University of Waterloo Waterloo Canada Academy of Forensic Science Shanghai Forensic Service Platform Shanghai China Shanghai Key Laboratory of Navigation and Location Based Services Shanghai Jiao Tong University Shanghai200240 China

ISBN: (纸本)9781665470537

The question for understanding the correlation between genetic expression and diagnosis of schizophrenia patients has always been challenging. The DNA methylation can provide an effective approach to solve the problem. However, limited by the size of datasets and the high dimensionality, conventional feature selection and pattern recognition methods cause a severe overfitting phenomenon. In this paper, the DNA methylation data are analyzed to filter out the most important gene points for classification. To alleviate the negative overfitting impacts the optimization-based meta-learning i.e., the MAML algorithm, is developed to solve the multi-classification and feature selection problems. The proposed method combining MAML with attention-based mechanism is capable of conducting feature selection with fast generalization and quick adaptation for small samples. The major work lies in that the proposed model is pretrained with TCGA which can be tailored to our circumstance with priori information. To test the efficiency of the proposed algorithm, the DNA methylation data are used including homicidal schizophrenics and violent schizophrenics from some authoritative institute. Our method achieves a recognition accuracy of 91.89% (homicidal schizophrenics, schizophrenics without violent behaviors, and normal people) and 67.96% (schizophrenics with violent behaviors, schizophrenics without violent behaviors, and normal people}) respectively, which is a great improvement compared to the best-known results based on the traditional method with 82.52% and 63.76%. Furthermore, 1000 significant feature gene points are selected from more than 400 thousand feature points. © 2022 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

TextSLAM: Visual SLAM with Planar Text Features

TextSLAM: Visual SLAM with Planar Text Features

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Boying Li Danping Zou Daniele Sartori Ling Pei Wenxian Yu Shanghai Key Laboratory of Navigation and Location-based Service Shanghai Jiao Tong University

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

We propose to integrate text objects in man-made scenes tightly into the visual SLAM pipeline. The key idea of our novel text-based visual SLAM is to treat each detected text as a planar feature which is rich of textures and semantic meanings. The text feature is compactly represented by three parameters and integrated into visual SLAM by adopting the illumination-invariant photometric error. We also describe important details involved in implementing a full pipeline of text-based visual SLAM. To our best knowledge, this is the first visual SLAM method tightly coupled with the text features. We tested our method in both indoor and outdoor environments. The results show that with text features, the visual SLAM system becomes more robust and produces much more accurate 3D text maps that could be useful for navigation and scene understanding in robotic or augmented reality applications.

关键词： Simultaneous localization and mapping Three-dimensional displays Visualization Feature extraction navigation Cameras Robustness

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：