检索结果-内蒙古大学图书馆

Cyber-Physical Social Intelligence (ICCSI), International Conference on

作者： Ye Chen Pengpeng Ye Yuan Liang Lin Meng Artificial Intelligence Research Institute of Industrial Technology Nanjing Institute of Technology Nanjing China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory BeijingChina School of Automotive and Rail Transit Nanjing Institute of Technology Nanjing China

ISBN: (纸本)9781665426220

In this article, we focus on the problem of the distributed nonlinear state estimation for a class of underwater cyber-physical systems with fading measurements. In this article, we propose a modified square-root cubature Kalman filter to tackle with the nonlinear system model. And the diffusion strategy is introduced in this paper to improve the system's estimation performance. To ease the internode communication cost, we propose an event-triggered mechanism to avoid the unnecessary information transmission. The corresponding esti-mation algorithm is also derived in this article. The simulation results show that the proposed algorithm can estimate the target's state accurately with less communication resources.

关键词： Fading channels Costs Simulation Information processing Cyber-physical systems Filtering algorithms Social intelligence

来源：评论

学校读者我要写书评

暂无评论

Robotic dynamic target recognition and tracking based on the monocular vision

Robotic dynamic target recognition and tracking based on the...

引用

26th Chinese control Conference, CCC 2007

作者： Lei, Liu Yongji, Wang Huazhong University of Science and Technology Intelligent and Complex System Laboratory Key Laboratory of Image Processing and Intelligent Control Ministry of Education

ISBN: (纸本)7900719229

Gather the information of the environment by the monocular vision. Using the H and S weight of the HSV color model, separate the target from the environment with a certain color, by a fast clustering algorithm for two-value image segmentation. Calculating the distance between the camera and target by the 3D reconstruction algorithm and sub-control strategy, and raise its veracity by laser information fusion. Furthermore, a vision servo system has been designed and utilized to achieve the robot's dynamic track. At last, some experiments were used to certification its availability.

关键词： Robot applications

来源：评论

学校读者我要写书评

暂无评论

Generating infrared image from visible image using Generative Adversarial Networks

Generating infrared image from visible image using Generativ...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Lei An Jiajia Zhao Huijun Di School of Computer Science & Technology Beijing Institute of Technology Beijing China Science and Technology on Complex System Control and Intelligent Agent Coorperation Laboratory Beijing Electro-Mechanical Engineering Institute Beijing China

ISBN: (纸本)9781728137933

Infrared images have properties that are unaffected by illumination compared to visible images, object can be clearly recognized at day or night. Therefore, it is a better choice to use infrared images when training deep learning algorithms in unmanned systems. However, how to obtain a large number of infrared images makes it possible to train deep learning algorithm, which is the focus of our attention. In contrast to difficulties in direct shooting, computer simulations can generate large infrared images from visible images. But models that are trained on simulated data usually do not translate well to real scenarios. To bridge the domain gap between simulated and real infrared images, we exploit recent advances in paired image-to-image translation. We extend Pixel2Pixel to generate infrared image from visible image and propose a novel way of multilayer semantic information fusion, which significantly improves the quality of generated images. Finally, the image generated by our proposed PixelPro network is almost consistent with the real image distribution, achieved the purpose of expanding the dataset.

关键词： Image translation Infrared image Generative adversarial networks Infrared imaging Visible Imagery images Infrared radiation Information fusion

来源：评论

学校读者我要写书评

暂无评论

Regularized densely-connected pyramid network for salient instance segmentation

arXiv

引用

arXiv 2020年

作者： Wu, Yu-Huan Liu, Yun Zhang, Le Gao, Wang Cheng, Ming-Ming TKLNDST College of Computer Science Nankai University Tianjin300350 China ETH Zurich Switzerland School of Information and Communication Engineering University of Electronic Science and Technology of China China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

Much of the recent efforts on salient object detection (SOD) have been devoted to producing accurate saliency maps without being aware of their instance labels. To this end, we propose a new pipeline for end-to-end salient instance segmentation (SIS) that predicts a class-agnostic mask for each detected salient instance. To better use the rich feature hierarchies in deep networks and enhance the side predictions, we propose the regularized dense connections, which attentively promote informative features and suppress non-informative ones from all feature pyramids. A novel multi-level RoIAlign based decoder is introduced to adaptively aggregate multi-level features for better mask predictions. Such strategies can be well-encapsulated into the Mask R-CNN pipeline. Extensive experiments on popular benchmarks demonstrate that our design significantly outperforms existing state-of-the-art competitors by 6.3% (58.6% vs. 52.3%) in terms of the AP metric. The code is available at https://***/yuhuan-wu/RDPNet. © 2020, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Regional Geomagnetic Map Construction based on Support Vector Machine Residual Kriging

Regional Geomagnetic Map Construction based on Support Vecto...

引用

第三十九届中国控制会议

作者： Tong Liu Xingyu Li Mengyin Fu Zhaoxiang Liang Beijing Institute of Technology Key Laboratory of Complex System Intelligent Control and Decision Nanjing University of Science and Technology

Regional geomagnetic maps are widely used in geomagnetic navigation and magnetic anomaly detection. However,the complexity of geomagnetic spatial trend changes and the spatial sparseness of the geomagnetic data affect the accuracy of regional geomagnetic map construction. In order to improve the accuracy of regional geomagnetic maps, this paper proposes the Support Vector Machine Residual Kriging method（SVMRKriging）. First, Support Vector Machine（SVM） is used to fit the geomagnetic trend changes, then the residual component is interpolated by ordinary Kriging, and finally these two parts are added to construct a regional geomagnetic map. Experiments were performed using geomagnetic grid data and aeromagnetic data. The experiment results show that SVMRKriging method can improve the accuracy of regional geomagnetic maps with geomagnetic trend changes.

关键词： Regional Geomagnetic Map Kriging Support Vector Machine

来源：评论

学校读者我要写书评

暂无评论

Aeromagnetic Compensation Based on Tikhonov Regularization with Limited L-curve Parameter-choice Algorithm

Aeromagnetic Compensation Based on Tikhonov Regularization w...

引用

第37届中国控制会议

作者： FU Mengyin LI Jie WU Tailin LIU Tong WANG Meiling WANG Kai KANG Jiapeng Beijing Institute of Technology Key Laboratory of Complex System Intelligent Control and Decision Nanjing University of Science and Technology

Magnetic anomaly detection has great application value to national economic development and national defense construction, while the presence of various interference magnetic fields on the aircraft will affect the detection of magnetic anomaly. Therefore, it is very important to compensate the aircraft interference magnetic field. In order to solve the problem that the accuracy of the parameters is poor by using ridge estimation in the process of solving the parameters of aircraft interference magnetic field model, we propose a method based on Tikhonov Regularization（TR）. Firstly, the optimal regularization parameter is obtained by the limited L-curve method in our work. Secondly, the aircraft interference magnetic field model parameters are obtained by using the TR method. Finally, we use the model parameters to calculate the aircraft interference magnetic field in the real flight, and complete the compensation. The effectiveness of this method is validated by simulation experiments. The results show that the method proposed in this paper has the advantages of high precision and convenient application, so it can be used to compensate the aircraft interference magnetic field effectively.

关键词： Aircraft Interference Magnetic Field Model Tikhonov Regularization L-curve Method Ridge Estimation

来源：评论

学校读者我要写书评

暂无评论

Simulation and analysis of far-field single-photon response model in Geiger avalanche mode 7

Simulation and analysis of far-field single-photon response ...

引用

7th Global intelligent Industry Conference, GIIC 2024

作者： Ou, Hengchang Ma, Le Jiang, Peng Wang, Pengfei Lu, Jie Zhou, Xin Sun, Jianfeng National Key Laboratory of Laser Spatial Information Institute of Opto-Electronic Harbin Institute of Technology Heilongjiang Harbin150001 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China Beijing Institute of Remote Sensing Beijing100854 China 44th Research Institute China Electronics Technology Group Corporation Chongqing400060 China Research Center for Space Optical Engineering Harbin Institute of Technology Heilongjiang Harbin150001 China Zhengzhou Research Institute of Harbin Institute of Technology Zhengzhou Henan450046 China

ISBN: (纸本)9781510682986

Poisson distribution model is the basis of data analysis for GM-APD lidar, but it is only applicable to the mirror reflected target under ideal conditions, and cannot accurately describe the photon triggering process of actual GM-APD lidar detection. For the actual target with rough surface, the negative binomial distribution with M as the parameter can describe the photon distribution model more accurately. In order to solve this problem, this paper compares and analyzes Poisson distribution triggering model and the negative binomial distribution triggering model that conforms to the triggering situation of the echo signal of the target with rough surface, considering the differences in the triggering probability under different noise and signal levels. The results show that the trigger probability curve corresponding to the trigger model based on negative binomial distribution is lower in peak value, wider in bottom value and fatter overall than that of the trigger model based on Poisson distribution, and the difference between the two is more prominent under the conditions of low noise level and high signal level. This study has guiding significance for the signal extraction research based on different surface echoes. © 2024 SPIE.

关键词： Photons

来源：评论

学校读者我要写书评

暂无评论

A dual-mode navigation algorithm based on Infrared and SAR information fusion

A dual-mode navigation algorithm based on Infrared and SAR i...

引用

IEEE International Conference on Radar

作者： Yanjiao Yang Guangzhou Qu Bo Li Meng Ma ShuaiShuai Liu Qingxi Chi Beijing Electro-Mechanical Engineering Institute Beijing China Control and Intelligent Agent Coopration Laboratory Beijing Electro-Mechanical Engineering Institute Science and Technology on Complex System Beijing China

ISBN: (纸本)9781665468893

Focused on revising the cumulative error of the SINS, a dual-mode navigation algorithm based on the infrared and SAR information fusion is studied in this paper. The SAR system can provide the SAR image and the information including the distance and the beam direction of the SAR antenna, the infrared system can provide the infrared image and the optical axis direction of the infrared lens. Under the premise of the same direction of the SAR and infrared beam, a navigation algorithm by associating the matching results of the SAR image and infrared image with the digital map is studied, which can be applied to amend the aberration of the SINS in the middle phase. At the same time, the common aperture characteristic and GPS error isolation method are used to isolate the error sub area. The simulation results reveal the validity of the algorithm.

关键词： Satellites Spaceborne radar Simulation Optical imaging Radar polarimetry Hardware Optical sensors

来源：评论

学校读者我要写书评

暂无评论

High precision test method and apparatus for photoelectric encoder

引用

Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of technology 2007年第11期27卷 977-980+1008页

作者： Deng, Fang Chen, Jie Chen, Wen-Jie Chi, Cheng Department of Automatic Control School of Information Science and Technology Beijing Institute of Technology Beijing 100081 China Key Laboratory of Complex System Intelligent Control and Decision School of Information Science and Technology Beijing Institute of Technology Beijing 100081 China

A new method and apparatus is proposed to improve the precision and reduce the cost of photoelectric encoder measurements. The method is based on highest resolution measurement and completely statistical analysis. The system includes a stepping motor, a high precision worm reduction gear, a high speed single chip microcomputer, a low cost incremental optical electric encoder and some multi interfaces of communication protocols. The single chip microcomputer as the lower system can test and collect the optical electric encoder. The PC computer as host-computer can deal with the test data. The precision of the system can reach 18 binary digits. Results of application in practice showed that the method and apparatus is efficient and effective, the cost of the apparatus is less than the some kind of system.

关键词： Photoelectric devices

来源：评论

学校读者我要写书评

暂无评论

Network Parameter Generation for One-Shot Object Detection

Network Parameter Generation for One-Shot Object Detection

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Kang Wang Jiajia Zhao Yang Wang Shuigeng Zhou Shanghai Key Lab of Intelligent Information Processing and School of Computer Science Fudan University Shanghai China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing Electro-Mechanical Engineer Institute Beijing China School of Information Engineering Nanchang University China

ISBN: (纸本)9781728137933

Recent object detection models have achieved satisfactory performance by deep learning with large-scale annotated datasets. However, these models often perform poorly when the training examples are not sufficient enough, especially for one-shot object detection where there is only one training example of each target class. In this paper, we propose a network parameter generation framework for effective one-shot object detection. By leveraging the semantic relationship between the source-domain and the target-domain (new classes), our framework can generate network parameters for the new classes directly. Furthermore, we develop two implementation schemes for this framework: weighting-based parameter generation and regression-based parameter generation. These two schemes use different information to construct the relationship and transfer knowledge from the source-domain to the target-domain. Experiments on the PASCAL-OSCD benchmark show that our methods can significantly boost the performance of one-shot object detection.

关键词： Object detection Detectors Head Training Feature extraction Task analysis Training data

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：