检索结果-内蒙古大学图书馆

S2KAN-SLAM: Elastic Neural LiDAR SLAM with SDF Submaps and Kolmogorov-Arnold Networks

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Wang, Zhong Zhang, Lin Wang, Hesheng Shanghai Jiao Tong University State Key Laboratory of Avionics Integration and Aviation System-of-Systems Synthesis Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai200240 China Tongji University School of Computer Science and Technology National Pilot Software Engineering School with Chinese Characteristics Shanghai201804 China

Traditional LiDAR SLAM approaches prioritize localization over mapping, yet high-precision dense maps are essential for numerous applications involving intelligent agents. Recent advancements have introduced methods leveraging neural fields to enhance mapping capabilities;however, these approaches still face several limitations. Firstly, concerning scene representation, they typically employ neural fields with high-dimensional features and multi-layer perceptron decoders utilizing non-continuous activation functions. This results in low learning efficiency and challenges in capturing high-frequency signals. Secondly, in terms of scene organization, these methods often treat the entire scene as a singular neural field, leading to inefficiencies, inflexibility, and difficulties in rectifying accumulated errors when mapping large-scale environments over extended periods. To tackle the first issue, we propose a lightweight continuous SDF regression approach by encoding the scene in single-valued embeddings and decoding SDF values from a Kolmogorov-Arnold Network. By minimizing discrepancies in measuring range, sampling distance, and decoded SDF values, we facilitate iterative frame-to-model tracking and bundle adjustment neural mapping. To mitigate the second challenge, we propose structuring the whole scene into multiple neural SDF submaps. By establishing node-node, node-submap, and loop closure constraints into a global pose graph, the system can create dense neural maps with global consistency across large-scale scenes. Experimental evaluations in both real-world and simulated settings indicate that our system achieves superior mapping completeness and accuracy, enhanced learning efficiency, reduced memory consumption, and greater flexibility compared to its counterparts. © 2025 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Novel passive localization algorithm based on weighted restricted total least square

引用

Journal of Systems Engineering and Electronics 2013年第4期24卷 592-599页

作者： Changwen Qu Zheng Xu Changhai Wang Department of Electronic and Information Engineering Naval Aeronautical and Astronautical University Science and Technology on Avionics Integration Laboratory

A novel multi-observer passive localization algorithm based on the weighted restricted total least square （WRTLS） is proposed to solve the bearings-only localization problem in the presence of observer position errors. Firstly, the unknown matrix perturbation information is utilized to form the WRTLS problem. Then, the corresponding constrained optimization problem is transformed into an unconstrained one, which is a generalized Rayleigh quotient minimization problem. Thus, the solution can be got through the generalized eigenvalue decomposition and requires no initial state guess process. Simulation results indicate that the proposed algorithm can approach the Cramer-Rao lower bound （CRLB）, and the localization solution is asymptotically unbiased.

关键词： passive localization bearing weighted restricted total least square (WRTLS) generalized Rayleigh quotient.

来源：评论

学校读者我要写书评

暂无评论

Novel passive localization algorithm based on double side matrix-restricted total least squares

引用

Chinese Journal of Aeronautics 2013年第4期26卷 1008-1016页

作者： Xu Zheng Qu Changwen Wang Changhai Science and Technology on Avionics Integration Laboratory Department of Electronic and Information Engineering Naval Aeronautical and Astronautical University

In order to solve the bearings-only passive localization problem in the presence of erroneous observer position, a novel algorithm based on double side matrix-restricted total least squares （DSMRTLS） is proposed. First, the aforementioned passive localization problem is transferred to the DSMRTLS problem by deriving a multiplicative structure for both the observation matrix and the observation vector. Second, the corresponding optimization problem of the DSMRTLS problem without constraint is derived, which can be approximated as the generalized Rayleigh quotient minimization problem. Then, the localization solution which is globally optimal and asymptotically unbiased can be got by generalized eigenvalue decomposition. Simulation results verify the rationality of the approximation and the good performance of the proposed algorithm compared with several typical algorithms.

关键词： Bearings Erroneous observer position Generalized eigenvalue decomposition Matrix-restricted total least squares Passive localization

来源：评论

学校读者我要写书评

暂无评论

Flight Safety Analysis with Multi-information's Dynamic Perception and Synthesis 17

Flight Safety Analysis with Multi-information's Dynamic Perc...

引用

17th IEEE/ACIS International Conference on Computer and Information science, ICIS 2018

作者： Hui, Huang Yang, Xiang Cunbao, Ma Jie, Chen Science and Technology on Avionics Integration Laboratory Shanghai China

ISBN: (纸本)9781538658925

As the flight environment becomes more and more complex, aircraft shall collect and percept multi-external information, and then complete the system hazard identification and safety analysis to avoid collision. In this paper, with Agent technology, the complex air traffic environment model is designed and built to simulate the multi-information's dynamic perception and synthesis, furthermore, the hazard identification and flight safety analysis are completed. The corresponding hazard identification method is validate by the simulation results and useful to enhance flight safety. © 2018 IEEE.

关键词： Flight simulators

来源：评论

学校读者我要写书评

暂无评论

Infrared and Visible Image Fusion based on CNN and Saliency Detection 3

Infrared and Visible Image Fusion based on CNN and Saliency ...

引用

3rd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering, ICBAIE 2022

作者： Tang, Chongwu Wu, Xinliang Dai, Changan Science and Technology on Avionics Integration Laboratory Shanghai China

ISBN: (数字)9781665451604

ISBN: (纸本)9781665451604

In this paper, a novel image fusion framework is proposed for fusing the infrared and visible images based on convolutional neural network (CNN) and saliency detection. The proposed framework overcomes the bottleneck of previous pixelbased CNN methods in that it preserves the intensity and texture homogeneity within the saliency regions. First, an initial fused image was obtained using a two-channel CNN. Then a saliency map is derived based on the difference in structural similarity between the infrared and visible source images with the initial fused image. Finally, a weighted fusion rule is applied to generate the fused image. The proposed method was validated on a combined dataset of CIFAR-10 dataset and the TNO image fusion dataset. The results show that the fused images with CNN and saliency detection present good infrared target features as well as clear visible background, and effectively preserve the visual details and infrared features of the target regions. Our method showed improved performance over the state-of-the-art image fusion methods in qualitative and quantitative evaluations. © 2022 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

A Threat Modeling Method based on Kalman Filter for UAV Path Planning 29

A Threat Modeling Method based on Kalman Filter for UAV Path...

引用

第29届中国控制与决策会议

作者： Minyang Kang Yang Liu Yijing Zhao Science and Technology on Avionics Integration Laboratory Department of Automatic Control Beihang University

ISBN: (纸本)9781509046584

For low altitude penetration task, unmanned aerial vehicles（UAVs） need to accomplish its task with collision free. However, due to the uncertainties in the flight environment, the application of UAV is undoubtedly affected in the actual complex flight environment. This paper presents a method based on Kalman filter to evaluate the risk of UAVs under the precondition of distance sensor noise, GPS sensor noise and model estimation noise, aiming to provide the security flight space. Meanwhile, experimental results verify the correctness of the algorithm.

关键词： Real-time path planning UAV Uncertainty Kalman filter

来源：评论

学校读者我要写书评

暂无评论

Fisher vector representation based on pixel-level objectness for image classification

引用

Journal of Computational Information Systems 2014年第23期10卷 10049-10058页

作者： Fang, Zheng Tuo, Hongya Qiao, Lingfeng Xu, Tao Jing, Zhongliang School of Aeronautics and Astronautics Shanghai Jiao Tong University Shanghai China Science and Technology on Avionics Integration Laboratory Shanghai China

In this paper, a discriminative image representation using Fisher Vector is proposed. Fisher Vector is popular in image classification because of its excellent performance and low demand for codebook size, but it does not carry spatial information and is computationally expensive. To address this, a Bayesian approach is used to transfer the window-level objectness to pixel-level objectness as prior knowledge of foreground layout of an image. Then, the Fisher Vector is integrated with pixel-level objectness which gives greater weight to features with high probabilities of belonging to foreground in order to make the proposed representation more discriminative. A feature selection is also adopted to eliminate features from background according to their objectness values to alleviate encoding computation as well as improve classification. The experiments on the challenging PASCAL VOC 2007 and Caltech 101 show that this method outperforms the state-of-the-art methods.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Multi-Image Restoration Method Combined with Total Generalized Variation and l_p-Norm Regularizations

引用

Journal of Shanghai Jiaotong university(science) 2019年第5期24卷 551-558页

作者： REN Xuanguang PAN Han JING Zhongliang GAO Lei School of Aeronautics and Astronautics Shanghai Jiao Tong University Science and Technology on Avionics Integration Laboratory Shanghai Jiao Tong University

Image restoration is an important part of various applications, such as computer vision, robotics and remote sensing. However, recovering the underlying structures of the latent image contained in multi-image is a challenging problem because of the need to develop robust and fast algorithms. In this paper, a novel problem formulation for multi-image restoration problem is proposed. This novel formulation is composed of multi-data fidelity terms and a composite regularizer. The proposed regularizer consists of total generalized variation(TGV)and lp-norm. This multi-regularization method can simultaneously exploit the consistence of image pixels and promote the sparsity of natural signals. To deal with the resulting problem, we derive and implement the solution using alternating direction method of multipliers(ADMM). The effectiveness of our method is illustrated through extensive experiments on multi-image denoising and inpainting. Numerical results show that the proposed method is more efficient than competing algorithms, achieving better restoration performance.

关键词： image restoration multi-regularization multi-image convex optimization

来源：评论

学校读者我要写书评

暂无评论

Robust pupil center estimation using input estimation based Gaussian significance test

Robust pupil center estimation using input estimation based ...

引用

2012 International Conference on System Simulation, ICUSS 2012

作者： Zhai, M. Wu, J.M. Liu, B.W. National Key Laboratory of Science and Technology on Avionics System Integration Shanghai China

ISBN: (纸本)9781849195386

In this paper a low cost pupil center locating system was introduced and target maneuver onset detection algorithm, input estimation based Gaussian significance test, was applied to estimate pupil center. Firstly, eye images were converted into Gaussian significance space of input estimate. In statistical significance space, pupil area was enhanced while other area was depressed. Secondly, threshold selected by input estimation based Gaussian significance test algorithm was used to binarize image in the space of statistical significance. At last pupil center was obtained by calculating mass center of the binarized image. Experiments showed that the proposed method was effective.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Research on the Method of Association Mapping Between Service Architecture Design and Service Component Development 4

Research on the Method of Association Mapping Between Servic...

引用

4th Asia-Pacific conference on Complex Systems Design and Management, CSD and M Asia 2021 and of the 12th International Conference on Complex Systems Design and Management, CSD and M 2021

作者： Xue, Bing Zhan, ZhiJuan Wang, YunHui Key Laboratory of Science and Technology on Avionics System Integration Shanghai200030 China

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：