检索结果-内蒙古大学图书馆

A Real-time Fire Segmentation Method Based on A Deep Learning Approach

IFAC-PapersOnLine 2022年第6期55卷 145-150页

作者： Mengna Li Youmin Zhang Lingxia Mu Jing Xin Ziquan Yu Shangbin Jiao Han Liu Guo Xie Yi Yingmin Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'an Shaanxi 710048 China Department of Mechanical Industrial and Aerospace Engineering Concordia University Montreal Quebec H3G 1M8 Canada College of Automation Engineering Nanjing University of Aeronautics and Astronautics (NUAA) Nanjing Jiangsu China

As a kind of the forest “fault”, fire is highly destructive and difficult to rescue. Fire segmentation is helpful for firefighters to understand the fire scale and formulate a reasonable fire-fighting plan. Therefore, this paper proposes a real-time fire segmentation method based on deep learning. This method is an improved version of deeplbav3+, which is an encoder-decoder structure network. Encoder network is composed of deep convolutional neural network and atrous spatial pyramid pooling. Different from deeplabv3+, in order to improve the segmentation speed, this paper uses the lightweight network mobilenetv3 to build a new deep convolutional neural network and does not use atrous convolution, but it will affect the segmentation accuracy. Therefore, in order to compensate for the loss of segmentation accuracy, on the basis of the original decoder network, this paper adds two different shallow features to make the network contain rich fire feature information. Experimental results show that the comprehensive performance of this method is better than the original deeplabv3+, especially the segmentation speed of the network is greatly improved, which is about 59 FPS.

关键词： Forest fire Fire segmentation Atrous spatial pyramid pooling Mobilenetv3 Deeplabv3+

来源：评论

学校读者我要写书评

暂无评论

Early Forest Fire Segmentation Based on Deep Learning

Early Forest Fire Segmentation Based on Deep Learning

引用

2021 CAA Symposium on Fault Detection, Supervision, and Safety for Technical Processes, SAFEPROCESS 2021

作者： Li, Mengna Zhang, Youmin Xin, Jing Mu, Lingxia Yu, Ziquan Liu, Han Xie, Guo Jiao, Shangbin Yi, Yingmin Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Shaanxi Xi'an710048 China Concordia University Department of Mechanical Industrial and Aerospace Engineering MontrealQCH3G 1M8 Canada Nanjing University of Aeronautics and Astronautics College of Automation Engineering Nanjing211106 China

ISBN: (纸本)9781665401159

Fire segmentation is very important for fire rescue. It can make firefighters get the information on fire area, spread direction and so on, and then help them make quick and effective fire-fighting plan. Therefore, this paper proposes an early forest fire segmentation algorithm based on a deep learning model, named F-Unet, which mainly uses the architecture idea of Unet for reference. F-Unet consists of contraction path, feature fusion layer and expansion path. The contraction path is composed of the first 13 layers of VGG16, which is used to obtain feature maps with different scales. In order to improve the segmentation accuracy of the model, the feature fusion network proposed in this paper is added to the Unet architecture to fuse these feature maps with different scales. The expansion path is used for upsampling these feature maps to restore the size of the original input image and obtain the fire segmentation results. The experimental testing results on the FLAME dataset show that F-Unet can significantly improve the fire segmentation precision, and also prove that the proposed feature fusion network is effective to improve the performance of fire segmentation. © 2021 IEEE.

关键词： Deforestation

来源：评论

学校读者我要写书评

暂无评论

Non-Fourier Heat Conduction based on Self-Adaptive Weight Physics-Informed Neural Networks

Non-Fourier Heat Conduction based on Self-Adaptive Weight Ph...

引用

第40届中国控制会议

作者： Shuyan Shi Ding Liu Zhongdan Zhao National & Local Joint Engineering Research Center of Crystal Growth Equipment and System Integration Xi'an University of Technology Shananxi Key Laboratory of Complex System Control and Intelligent Information Processing

This paper establishes the non-Fourier heat conduction model to describe the heat transfer process of mono-crystalline silicon under the condition of unstable thermal field and thermal shock in the Czochralski method.A novel differential equations solver called Physics-Informed Neural Networks（PINN） algorithm was *** with finite element method（FEM）,this method has some advantages like no grid requirement and easily *** order to deal with the unbalance of constraint condition and speed up the convergence,we propose a novel method called Self-Adaptive Weight Physics-Informed Neural Networks（SWPINN）.The comparison of the experimental results of SWPINN and COMSOL verifies the effectiveness of *** modifying the parameter of non-Fourier heat conduction model,this paper obtains the temperature distribution under different heat relaxation ***,comparison between SWPINN and PINN shows that the proposed method has faster convergence speed and higher accuracy.

关键词： Non-Fourier Heat Conduction Physics-Informed Neural Networks Partial Differential Equation Monocrystalline Silicon Czochralski Method

来源：评论

学校读者我要写书评

暂无评论

A new semi-supervised inductive transfer learning framework: Co-transfer

arXiv

引用

arXiv 2021年

作者： Yuan, Zhe Wen, Yimin Guangxi Key Laboratory of Image and Graphic intelligent processing Guilin University of Electronic Technology Guilin541004 China School of Computer Science and Information Safety Guilin University of Electronic Technology Guilin541004 China

In many practical data mining scenarios, such as network intrusion detection, Twitter spam detection, and computer-aided diagnosis, a source domain that is different from but related to a target domain is very common. In addition, a large amount of unlabeled data is available in both source and target domains, but labeling each of them is difficult, expensive, time-consuming, and sometime unnecessary. Therefore, it is very important and worthwhile to fully explore the labeled and unlabeled data in source and target domains to settle the task in target domain. In this paper, a new semi-supervised inductive transfer learning framework, named Co-Transfer is proposed. Co-Transfer first generates three TrAdaBoost classifiers for transfer learning from the source domain to the target domain, and meanwhile another three TrAdaBoost classifiers are generated for transfer learning from the target domain to the source domain, using bootstraped samples from the original labeled data. In each round of co-transfer, each group of TrAdaBoost classifiers are refined using the carefully labeled data. Finally, the group of TrAdaBoost classifiers learned to transfer from the source domain to the target domain produce the final hypothesis. Experiments results illustrate Co-Transfer can effectively exploit and reuse the labeled and unlabeled data in source and target domains. Copyright © 2021, The Authors. All rights reserved.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

An Improved SSD for small target detection

An Improved SSD for small target detection

引用

作者： Xiang Li Haibo LuoX Key Laboratory of Opt-Electronic Information Processing Chinese Academy of Sciences Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences University of Chinese Academy of Sciences The Key Laboratory of Image Understanding and Computer Vision

SSD is one of heuristic one-stage target detection *** it has got impressive results in general target detection,it still struggles in small-size object detection and precise *** this paper,we proposed an improved SSD which forces on the small-size target *** include a shallow and high resolution feature into the hierarchical detection feature which are used for ***,we fuse the detection features(including the shallow and high resolution one) as a feature pyramid through some 1 × 1 convolution layers and unsample operations to pass information from deep features to the shallow ones,aiming to enrich the semantic information of the shallow *** make the network easier to converge,we add a L2 normalization to the bottom detection feature of the feature pyramid to make a norm balance between each pyramid *** experimental results on the VEDAI dataset show that the proposed method has obtained impressive progress than the original SSD for the small targets detection.

关键词： Convolution neural network Target detection SSD Small targets

来源：评论

学校读者我要写书评

暂无评论

Research on the detection method of alignment beacon based on the spatial structure feature of train bogies

Research on the detection method of alignment beacon based o...

引用

Chinese Automation Congress (CAC)

作者： Chong Cao Shaowei Wan Gang Peng Dingxin He Sheng Zhong Zhang Deng Wentao Guo School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan China Beijing Railway Institute of Mechanical & Electrical Engineering Group Co. Ltd. Beijing China Wuhan Lisai Technology Co. Ltd. Wuhan China

The high-speed train inspection robot needs to perform alignment parking and image acquisition at the position of the train bogie, and reliable alignment identification marks are the basis for the inspection robot to achieve highprecision alignment parking. The existing alignment method is mainly based on the way of artificial beacons, in the inspection workshop through manual laying of additional identification marks such as QR codes, magnetic stripes, RFID electronic tags, auxiliary robot alignment parking, but this type of method in beacon maintenance, laying costs and other aspects have certain limitations. Aiming at the problem, this paper proposes a vision-based bogie beacon detection method, which combines the target detection technology with the unique bogie spatial structure feature of the train, and provides reliable identification marks for the alignment and parking of the inspection robot. This method improves the alignment accuracy, reduces the cost of laying and maintaining artificial beacons, and has high application value.

关键词： Shafts Costs Wheels Object detection Inspection Maintenance engineering Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Visual Kinematics Calibration Method for Manipulator Based on Nonlinear Optimization

A Visual Kinematics Calibration Method for Manipulator Based...

引用

Chinese Automation Congress (CAC)

作者： Gang Peng Zhihao Wang Shangbin Guan Zhang Deng Wentao Guo Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Beijing Railway Institute of Mechanical & Electrical Engineering Group Co. Ltd. Beijing China Wuhan Lisai Technology Co. Ltd. Wuhan China

The traditional kinematic calibration method for manipulators requires precise three-dimensional measuring instruments to measure the end pose, which is not only expensive due to the high cost of the measuring instruments but also not applicable to all manipulators. Another calibration method uses a camera, but the system error caused by the camera’s parameters affects the calibration accuracy of the kinematics of the robot arm. In order to solve this problem, this paper reduces the dimensionality of the experimental data and redesigns the objective function to be optimized. That is, the three-dimensional positions of the feature points of the calibration plate under each manipulator attitude corresponding to the actual kinematic model and the classic D-H kinematic model are mapped into the pixel coordinate system, and the sum of Euclidean distance errors of the pixel coordinates of the two is used as the objective function to be optimized. And then, nonlinear optimization and parameter compensation are performed. The experimental results show that the pixel deviation of the end pose corresponding to the optimized D-H kinematic model proposed in this paper and the end pose corresponding to the actual kinematic model in the pixel coordinate system is 0.99 pixels. Compared with the 7.9 deviation pixels between the pixel coordinates calculated by the classic D-H kinematic model and the actual pixel coordinates, the deviation is reduced by nearly 7 pixels for an 87% reduction in error. Therefore, the proposed method can effectively avoid system errors caused by camera parameters in visual calibration, can improve the absolute positioning accuracy of the end of the robotic arm, and has good economy and universality.

关键词： Visualization Robot kinematics Instruments Robot vision systems Kinematics Manipulators Cameras

来源：评论

学校读者我要写书评

暂无评论

Surface Defect Detection Based on Deep Learning and Collaborative Cloud-edge Computation

Surface Defect Detection Based on Deep Learning and Collabor...

引用

International Conference on Computer and Communications (ICCC)

作者： Shunjie He Bo Yang Dafeng Zhu Cheng Li Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Engineering Research Center of Industrial Intelligent Control and Management Shanghai China

ISBN: (纸本)9781665409513

Surface defect detection is a fundamental step of quality management. Nowadays, surface defect detection system based on machine vision technology has made great progress which can gradually replace the human inspector. With the help of convolutional neural networks, the accuracy and stability of the surface defect detection algorithm are improving rapidly. However, it is difficult to process the images which have small defect areas and complex backgrounds. Furthermore, lacking defective samples and limited computation resources are also tough problems. To deal with these problems, a two-stage algorithm combined with object detection and classification networks is proposed. Transform learning and data augmentation are used to deal with the problem of lacking defect samples. Besides, a detection system based on collaborative cloud-edge computation is designed to improve the performance of the algorithm. The result shows that the proposed method has high performance and low requirements of computation resources.

关键词： Training Collaboration Transforms Object detection Classification algorithms Convolutional neural networks Detection algorithms

来源：评论

学校读者我要写书评

暂无评论

An Integrated Neural Unmanned System for Multi-Domain Perception and Decision-Making

An Integrated Neural Unmanned System for Multi-Domain Percep...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Qiming Liu Neng Xu Jinpeng Zhang Hesheng Wang Department of Automation Shanghai Jiao Tong University Shanghai China SJTU Paris Elite Institute of Technology Shanghai Jiao Tong University Shanghai China Second Academy of China Aerospace Science and Industry Corporation (CASIC) Beijing China 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 China

ISBN: (纸本)9781665481106

Most recent intelligent systems study the perception or policy modules independently but ignore the inter-connection between them, which results in low information efficiency and high network redundancy, in the end, leads to the incomplete utilization of network potential and poor system-level end-to-end intelligence. This paper proposes an integrated end-to-end network that adapts to multi-domain inputs and multi-function outputs. “Integration” is defined in this paper in mainly three aspects: network structure level, optimization level, and functional level. The integrated network architecture is capable of fusing multiple raw sensory inputs and outputting multiple perceptions and decisions simultaneously. We first implement the integrated system in a virtual simulation environ-ment and investigate the domain transformation methods to real world. Comprehensive experiment results in both virtual and real environments show that our proposed system can behave normally under exploration, target-driven navigation and target shooting tasks.

关键词： Training Point cloud compression Target tracking Navigation Robot kinematics Redundancy Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

3D Virtual Sand Table Display System of Industrial Park Based on Augmented Reality

3D Virtual Sand Table Display System of Industrial Park Base...

引用

Industrial Application of Artificial Intelligence (IAAI), IEEE International Conference on

作者： Hongyan Lu Jie He Caichun Cen School of Big Data and Software Engineering Wuzhou University Wuzhou China Key Laboratory of Image Processing and Intelligent Information System at Guangxi University Wuzhou University Wuzhou China School of Electronic and Information Engineering Wuzhou University Wuzhou China

ISBN: (纸本)9781665465816

To improve the interactivity of 3D virtual sand table displays, an industrial park 3D virtual sand table display system based on augmented reality is designed. The system consists of multiple modules. The design of the animation browsing module is based on the roaming walking model environment. The walking and roaming module can enable participants to experience the real visual and tactile virtual space in the process of input browsing. In the surrounding environment and traffic condition module, the surrounding environment and traffic condition display are created by means of static pictures and picture buttons. The VRML scene space module is responsible for creating objects such as VRML viewpoints. Scenario module transformation completes event transmission through routing. The virtual sand table VRML optimization modeling module is responsible for constructing the virtual sand table VRML model. The function of the multiperson collaboration module is to provide collaboration capability for plotting and discussion functions. In the multiuser detection module, yolov2 is used for multiuser detection. The augmented reality hardware module is mainly composed of computers and hololens. Through the combination of hardware and software, a three-dimensional virtual sand table display of an industrial park is realized. The test results show that the performance of the designed system is good and can meet the design requirements.

关键词： Multiuser detection Legged locomotion Visualization Three-dimensional displays Computational modeling Display systems Collaboration

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：