检索结果-内蒙古大学图书馆

Causal reasoning in typical computer vision tasks

science China(Technological sciences) 2024年第1期67卷 105-120页

作者： ZHANG KeXuan SUN QiYu ZHAO ChaoQiang TANG Yang Key Laboratory of Advanced Control and Optimization for Chemical Process Ministry of EducationEast China University of Science and TechnologyShanghai 200237China National Key Laboratory of Air based Information Perception and Fusion Luoyang 471000China Luoyang Institute of Electro Optical Equipment of Avic Luoyang 471000China

Deep learning has revolutionized the field of artificial *** on the statistical correlations uncovered by deep learning-based methods,computer vision tasks,such as autonomous driving and robotics,are growing *** being the basis of deep learning,such correlation strongly depends on the distribution of the original data and is susceptible to uncontrolled *** the guidance of prior knowledge,statistical correlations alone cannot correctly reflect the essential causal relations and may even introduce spurious *** a result,researchers are now trying to enhance deep learningbased methods with causal *** theory can model the intrinsic causal structure unaffected by data bias and effectively avoids spurious *** paper aims to comprehensively review the existing causal methods in typical vision and visionlanguage tasks such as semantic segmentation,object detection,and image *** advantages of causality and the approaches for building causal paradigms will be *** roadmaps are also proposed,including facilitating the development of causal theory and its application in other complex scenarios and systems.

关键词： causal reasoning computer vision tasks vision-language tasks semantic segmentation object detection

来源：评论

学校读者我要写书评

暂无评论

Scene image recognition with knowledge transfer for drone navigation

引用

Journal of Systems Engineering and Electronics 2023年第5期34卷 1309-1318页

作者： DU Hao WANG Wei WANG Xuerao ZUO Jingqiu WANG Yuanda School of Automation Southeast UniversityNanjing 210096China Autonomous Control Robot Laboratory Jiangsu Zhongke Institute of Applied Research on Intelligent Science and TechnologyChangzhou 213164China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science and TechnologyNanjing 210044China

In this paper,we study scene image recognition with knowledge transfer for drone *** divide navigation scenes into three macro-classes,namely outdoor special scenes(OSSs),the space from indoors to outdoors or from outdoors to indoors transitional scenes(TSs),and ***,there are difficulties in how to recognize the TSs,to this end,we employ deep convolutional neural network(CNN)based on knowledge transfer,techniques for image augmentation,and fine tuning to solve the ***,there is still a novelty detection prob-lem in the classifier,and we use global navigation satellite sys-tems(GNSS)to solve it in the prediction *** results show our method,with a pre-trained model and fine tun-ing,can achieve 91.3196%top-1 accuracy on Scenes21 dataset,paving the way for drones to learn to understand the scenes around them autonomously.

关键词： scene recognition convolutional neural network knowledge transfer global navigation satellite systems(GNSS)-aided

来源：评论

学校读者我要写书评

暂无评论

Simulation and Spatial-Temporal Characteristics Analysis of underwater Bubble Screen Echo 7

Simulation and Spatial-Temporal Characteristics Analysis of ...

引用

7th International Conference on Communication, Image and Signal Processing, CCISP 2022

作者： Lv, Wei Sun, Naiwei Ni, Wenxi Shen, Shen Science and Technology on Underwater Information and Control Laborator Xi'An Precision Machiney Research Institude Xi'an China

ISBN: (数字)9781665459594

ISBN: (纸本)9781665459594

In order to research the underwater bubble screen echo, a modeling and simulation method is proposed in this paper. First, the mathematical model of underwater bubble shell is modeled. Second, the simulation experiments are carried out in different working conditions. Finally, the presented model is validated by comparing the spatial-temporal characteristics of the simulation data and the trial data using the space-time adaptive process. © 2022 IEEE.

关键词： underwater acoustics

来源：评论

学校读者我要写书评

暂无评论

COMBINING ADJACENT SELF-SIMILARITY FEATURE AND ENHANCED MATCHING METHOD FOR SENTINEL IMAGE REGISTRATION 10

COMBINING ADJACENT SELF-SIMILARITY FEATURE AND ENHANCED MATC...

引用

10th International Symposium on Test Automation and Instrumentation, ISTAI 2024

作者： Zhang, Hui Song, Yu Hu, Jingfang Li, Yansheng Li, Yang Gao, Guowei Beijing Key Laboratory of Sensor Beijing Information Science & Technology University Beijing100101 China Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science and Technology University Beijing100192 China State Key Laboratory of Transducer Technology Aerospace Information Research Institute Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9781837242672

The accurate registration of Sentinel-2 optical images with Sentinel-1 synthetic aperture radar (SAR) images plays a critical role in remote sensing applications such as disaster management, environmental monitoring and military target identification. The distinct imaging mechanisms of the two images result in non-negligible radiometric and geometric differences, which make traditional image registration techniques suffer from insufficient correct matching points or even registration failures. To solve this problem, an optimised image registration algorithm is proposed. Firstly, First, the structural features are obtained by computing the adjacent self-similarity (ASS) features, and effectively suppress the interference of radiometric differences and speckle noise on the registration process through constructing index map and minimum self-similarity map (SSM). Subsequently, a new key-point detector is designed to restrain the local non-maximum of the minimum SSM, and a descriptor for the distribution histogram is built by log-polar grids. Finally, we employ a cascaded sample consensus (CSC) matching method that refines the search region for correct matches, leading to high accurate correspondences. In summary, our algorithm offers a comprehensive solution for image registration that improving both the number of correctly matched key-points and the overall registration accuracy, and is applicable to any complex scenario. © The Institution of Engineering & technology 2024.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Autonomous landing scene recognition based on transfer learning for drones

引用

Journal of Systems Engineering and Electronics 2023年第1期34卷 28-35页

作者： DU Hao WANG Wei WANG Xuerao WANG Yuanda School of Automation Southeast UniversityNanjing 210096China Autonomous Control Robot Laboratory Jiangsu Zhongke Institute of Applied Research on Intelligent Science and TechnologyChangzhou 213164China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science and TechnologyNanjing 210044China

In this paper, we study autonomous landing scene recognition with knowledge transfer for drones. Considering the difficulties in aerial remote sensing, especially that some scenes are extremely similar, or the same scene has different representations in different altitudes, we employ a deep convolutional neural network(CNN) based on knowledge transfer and fine-tuning to solve the problem. Then, LandingScenes-7 dataset is established and divided into seven classes. Moreover, there is still a novelty detection problem in the classifier, and we address this by excluding other landing scenes using the approach of thresholding in the prediction stage. We employ the transfer learning method based on ResNeXt-50 backbone with the adaptive momentum(ADAM) optimization algorithm. We also compare ResNet-50 backbone and the momentum stochastic gradient descent(SGD) optimizer. Experiment results show that ResNeXt-50 based on the ADAM optimization algorithm has better performance. With a pre-trained model and fine-tuning, it can achieve 97.845 0% top-1 accuracy on the LandingScenes-7dataset, paving the way for drones to autonomously learn landing scenes.

关键词： landing scene recognition convolutional neural network(CNN) transfer learning remote sensing image

来源：评论

学校读者我要写书评

暂无评论

A Novel Trajectory Planning Method Based on Trust Region Policy Optimization

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-15页

作者： Ye, Bao-Lin Zhang, Jiajie Li, Lingxi Wu, Weimin Jiaxing Key Laboratory of Smart Transportations the School of Information Science and Engineering Jiaxing University China Elmore Family School of Electrical and Computer Engineering Purdue University Indianapolis USA State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China

Trajectory planning method is a research hotspot in autonomous driving. Existing reinforcement learning-based trajectory planning methods suffer from unstable performance due to the strong randomness of network weight parameter updates during the training process. Therefore, this paper proposes a novel trajectory planning method based on deep reinforcement learning trust region policy optimization (TRPO). Firstly, in order to enhance the robustness of the trajectory planning method based on deep reinforcement learning TRPO, a TRPO-LSTM based decision model was proposed. More specifically, a long short term memory (LSTM) based state feature extraction network was designed and embeded into a TRPO-based decision model to enhance the ability of TRPO to extract information from the environmental state space. Secondly, in order to make the planned trajectory adaptive to the dynamic changes of traffic environment, we presented a novel TRPO-LSTM trajectory fitting algorithm. To the best of our knowledge, this is the first work aiming at applying the TRPO-LSTM based decision model in the trajectory fitting process to search the optimal longitudinal trajectory speed. Finally, the proposed trajectory planning method was implemented and simulated on the CARLA simulator. The experimental results show that, compared with existing trajectory planning methods based on deep reinforcement learning algorithms, our proposed method achieves a cumulative reward improvement of over 28.9% in the scenario of four lane highway, and has better robustness. Meanwhile, the proposed method can achieve a lower collision rate of 0.93% while improving the average speed and comfort of vehicle driving. IEEE

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

On Joint Active-Passive Sonar Detection Performance of underwater Long-Range Low-Speed Small Target 6

On Joint Active-Passive Sonar Detection Performance of Under...

引用

6th International Conference on information Communication and Signal Processing, ICICSP 2023

作者： Lai, Kai Liu, Xionghou Yang, Yixin Sun, Chao School of Marine Science and Technology Northwestern Polytechnical University Xi'an710072 China Xi'an China Shaanxi Key Laboratory of Underwater Information Technology 710072 China

ISBN: (纸本)9798350339994

We discuss the feasibility of the joint active-passive sonar detection method of underwater low-speed small targets located at long ranges. Specifically, the transmission loss, the reverberation level, and the noise level related to the joint active-passive detection method are modeled and calculated. The relationship between the figure of merit and the transmission loss is used to analyze the performance of the joint active-passive detection method of underwater low-speed small targets. For obtaining a long detection range, we mainly consider the working frequency of both the active and passive sonars to be much lower than traditional small target detection sonars. The active sonar is set to be worked at a frequency band not higher than 40kHz. Meanwhile, the passive sonar is supposed to work at a frequency band not higher than 1 kHz. The factors that affect the performance of the joint active-passive detection method are analyzed in detail. The results indicate that the considered joint active-passive detection method may have a detection range of more than 2000m in a relatively good underwater acoustic environment, which provides a potential way to significantly increase the working range of the underwater detection sonar system. © 2023 IEEE.

关键词： detection performance figure of merit joint active-passive detection underwater low-speed small targets

来源：评论

学校读者我要写书评

暂无评论

Design and Test of Missile-Borne Acquisition and Storage System for Magnetoelectric Sensor 3

Design and Test of Missile-Borne Acquisition and Storage Sys...

引用

3rd International Symposium on Semiconductor and Electronic technology, ISSET 2024

作者： Li, Jiale Zeng, Tao Sui, Li Beijing Institute of Technology Science and Technology on Eletromechanical Dynamic Control Laboratory Beijing100081 China Xi'an Institute of Electromechanical Information Technology Xi'an710065 China

ISBN: (纸本)9798350390285

The magnetoelectric sensor can solve the problem of acceleration sensor signal adhesion when a large aspect ratio warhead penetrates a multi-layer protective structure at high speed to certain extent, but no missile-borne acquisition and storage system suitable for this sensor has been found. Therefore, this paper designed a magnetoelectric sensor missile-borne acquisition and storage system, which used GD32E230K8T6 as the main control chip, used the on-chip SAR-ADC to realize the analog-to-digital conversion, and used a resistor network to realize the in-phase attenuation linear transformation for the signal. The data was stored in a 256Kbit FRAM with a sampling rate of more than 100kHz and a sampling accuracy of 12bit. The test result showed that the prototype accomplished the acquisition task and the storage task, and had power-off protection with 330ms working time after power-off. The prototype can meet the requirements of missile-borne acquisition and storage. © 2024 IEEE.

关键词： Linear transformations

来源：评论

学校读者我要写书评

暂无评论

Pyrometallurgical recycling of spent lithium-ion batteries from conventional roasting to synergistic pyrolysis with organic wastes

引用

Journal of Energy Chemistry 2023年第10期85卷 547-561,I0014页

作者： Chao Pan Yafei Shen China Energy Science and Technology Research Institute Co.Ltd. Nanjing 210023JiangsuChina Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control(AEMPC) Collaborative Innovation Center of Atmospheric Environment and Equipment TechnologySchool of Environmental Science and EngineeringNanjing University of Information Science and TechnologyNanjing 210044JiangsuChina

The synergistic pyrolysis has been increasingly used for recycling spent lithium-ion batteries(LIBs)and organic wastes(hydrogen and carbon sources),which are in-situ transformed into various reducing agents such as H_(2),CO,and char via carbothermal and/or gas thermal *** with the conventional roasting methods,this“killing two birds with one stone”strategy can not only reduce the cost and energy consumption,but also realize the valorization of organic *** paper concluded the research progress in synergistic pyrolysis recycling of spent LIBs and organic *** the one hand,valued metals such as Li,Co,Ni,and Mn can be recovered through the pyrolysis of the cathode materials with inherent organic materials(e.g.,separator,electrolyte)or graphite *** the pyrolysis process,the organic materials are decomposed into char and gases(e.g.,CO,H_(2),and CH_(4))as reducing agents,while the cathode material is decomposed and then converted into Li_(2)CO_(3) and low-valent transition metals or their oxides via in-situ thermal *** formed Li_(2)CO_(3) can be easily recovered by the water leaching process,while the formed transition metals or their oxides(e.g.,Co,CoO,Ni,MnO,etc.)can be recovered by the reductant-free acid leaching or magnetic separation *** the other hand,organic wastes(e.g.,biomass,plastics,etc.)as abundant hydrogen and carbon sources can be converted into gas(e.g.,H_(2),CO,etc.)and char via *** cathode materials are decomposed and subsequently reduced by the pyrolysis gas and *** addition,the pyrolysis oil and gas can be upgraded by catalytic reforming with the active metals derived from cathode ***,great challenges are proposed to promote this promising technology in the industrial applications.

关键词： Synergistic pyrolysis Spent LIBs Biomass Recycling Reduction roasting

来源：评论

学校读者我要写书评

暂无评论

Scale Normalization and Lightweight FPN for Small Object Detection in Aerial Images 3

Scale Normalization and Lightweight FPN for Small Object Det...

引用

3rd International Conference on Computer Graphics, Image, and Virtualization, ICCGIV 2023

作者： Wei, Haokun Liu, Jingyi Chen, Jinyong Sun, Yuxin Chu, Boce Zhu, Jin Key Laboratory of Aerospace Information Applications of CETC Shijiazhaung China Science and Technology on Electro-Optical Information Security Control Laboratory Tianjin China

ISBN: (纸本)9781510671720

The detection of small objects by oriented bounding box in aerial images is a recent hot topic. However, since the aerial images are not collected at the same height, the Ground Sample Distance (GSD) is different for each image, so that small objects are easily overlooked. Existing algorithms are designed for multi-scale object detection, and feature fusion is time-consuming, resulting in a large amount of model parameters that is not easy to deploy on embedded devices. We propose three methods to address the above problems. First, we scale the collected aerial images to the same scale according to the GSD value. Second, we change the structure of Feature Pyramid Network (FPN) and only keep the necessary low-level feature maps. Finally, we rescale the anchor for the specific scene. We validate our proposed method on the DOTA dataset. The results show that the modified model using our method can identify more small-scale objects, and the maximum number of model parameters can be reduced by 2.7%, the inference speed can be increased by 13.24%, and the model size was reduced by up to 28% when the detection accuracy is the same as the original algorithm. © 2023 SPIE.

关键词： Object detection

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：