检索结果-南通市图书馆

Journal of Computer Science & Technology 2020年第4期35卷 825-842页

作者： Zachary P.Languell Qijun Gu Department of Computer Science Texas State UniversitySan MarcosTX 78666USA

The Automatic Dependent Surveillance-Broadcast(ADS-B)protocol is being adopted for use in unmanned aerial vehicles(UAVs)as the primary source of information for emerging multi-UAV collision avoidance algorithms.The lack of security features in ADS-B leaves any processes dependent upon the information vulnerable to a variety of threats from compromised and dishonest UAVs.This could result in substantial losses or damage to properties.This research proposes a new distance-bounding scheme for verifying the distance and flight trajectory in the ADS-B broadcast data from surrounding UAVs.The proposed scheme enables UAVs or ground stations to identify fraudulent UAVs and avoid collisions.The scheme was implemented and tested in the ArduPilot SITL(Software In The Loop)simulator to verify its ability to detect fraudulent UAVs.The experiments showed that the scheme achieved the desired accuracy in both flight trajectory measurement and attack detection.

关键词： automatic dependent surveillance-broadcast (ADS-B) unmanned aerial vehicle (UAV) distance bounding collision airspace safety

High accuracy object detection via bounding box regression network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Optoelectronics 2019年第3期12卷 324-331页

作者： Lipeng SUN Shihua ZHAO Gang LI Binbing LIU State Grid Hunan Electric Power Corporation Limited Research Institute Changsha 410007China State Grid Hunan Electric Power Corporation Limited Changsha 410007China School of Optical and Electronics Information Huazhong University of Science and TechnologyWuhan 430074China

As one of the primary computer vision problems, object detection aims to find and locate semantic objects in digital images. Different with object classification, which only recognizes an object to a certain class, object detection also needs to extract accurate locations of objects. In the state-of-the-art object detection algorithms, bounding box regression plays a critical role in order to achieve high localization accuracy. Almost all the popular deep learning based object detection algorithms have utilized bounding box regression for fine tuning of object locations. However, while bounding box regression is widely used, there is few study focused on the underlying rationale, performance dependencies, and performance evaluation. In this paper, we proposed a dedicated deep neural network for bounding box regression, and presented several methods to improve its performance. Some ad hoc experiments are conducted to prove the effectiveness of the network. Also, we apply the network as an auxiliary module to the faster R-CNN algorithm and test them on some real-world images. Experiment results show certain performance improvements on detection accuracy in term of mean IOU.

关键词： deep learning object detection bounding box regression IOU distribution

bounding IMMERSION CLASSES OF CODIMENSION ONE

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Science Bulletin 1991年第24期36卷 2034-2037页

作者：李邦河李贵松 Institute of Systems Science Academia Sinica Beijing 100080 PRC

Ⅰ. INTRODUCTION We are interested in the following problem of differential topology: Let W be a manifold with boundary M. When does an immersion f: M→X extend to an immersion of

关键词： bounding immersion codimension one framing bordism

bounding Inequalities for Eigenvalues of Principal Submatrices

在线全文

学校读者我要写书评

暂无评论

Advances in Linear Algebra & Matrix Theory 2019年第2期9卷 21-34页

作者： Achiya Dax Hydrological Service Jerusalem Israel

Ky Fan trace theorems and the interlacing theorems of Cauchy and Poincaré are important observations that characterize Hermitian matrices. In this note, we introduce a new type of inequalities which extend these theorems. The new inequalities are obtained from the old ones by replacing eigenvalues and diagonal entries with their moduli. This modification yields effective bounding inequalities which are valid on a larger range of matrices.

关键词： Cauchy Interlacing Theorem Poincaré Interlacing Theorem Ky Fan Trace Theorems Non-Hermitian Matrices Normal Matrices bounding Inequalities

Shortest Alternate Path Discovery through Recursive bounding Box Pruning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Transportation Technologies 2017年第2期7卷 167-180页

作者： Rajendra S. Parmar Bhushan H. Trivedi Gujarat Technology University (GTU) Ahmedabad India Gujarat Law Society Institute of Computer Technology Ahmedabad India

Congestion is a dynamic phenomenon and hence efficiently computing alternate shortest route can only help expedite decongestion. This research is aimed to efficiently compute shortest path for road traffic network so that congestion can be eased resulting in reduced CO2 emission and improved economy. Congestion detection is achieved after evaluating road capacity and road occupancy. Congestion index, a ratio of road occupancy to road capacity is computed, congestion index higher than 0.6 necessitates computation of alternate shortest route. Various algorithms offer shortest alternate route. The paper discusses minimization of graph based by removing redundant nodes which don’t play a role in computation of shortest path. The proposal is based on continuous definition of a bounding box every time a next neighboring node is considered. This reduces maximum number of contentious nodes repeatedly and optimizes the network. The algorithm is deployed from both the ends sequentially to ensure zero error and validate the shortest path discovery. While discovering shortest path, the algorithm also offers an array of shortest path in ascending order of the path length. However, vehicular traffic exhibits network duality viz. static and dynamic network graphs. Shortest route for static distance graph is pre-computed and stored for look-up, alternate shortest path based on assignment of congestion levels to edge weights is triggered by congestion index. The research also supports directed graphs to address traffic rules for lanes having unidirectional and bidirectional traffic.

关键词： bounding Box Pruning Geometric Containers Shortest Alternate Path Shortest Path Vehicular Traffic Vehicular Congestion Detection System Vehicular Congestion Detection System

基于无线传感器离散网络模型的bounding Box定位算法研究

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

计算机应用与软件 2013年第12期30卷 194-197,257页

作者：曾振东广东青年职业学院广东广州510507

bounding Box算法是一种典型的基于离散网络模型的无线传感器网络节点定位算法。针对bounding Box算法定位误差大、覆盖率低的缺点,提出一种采用虚拟锚节点策略的改进定位算法。首先未知节点利用其通信范围内的锚节点进行定位;其次,已... 详细信息

bounding Box算法是一种典型的基于离散网络模型的无线传感器网络节点定位算法。针对bounding Box算法定位误差大、覆盖率低的缺点,提出一种采用虚拟锚节点策略的改进定位算法。首先未知节点利用其通信范围内的锚节点进行定位;其次,已定位的节点根据升级策略有选择性的升级为虚拟锚节点;最后,无法定位的节点利用虚拟锚节点实现定位。另外,在离散网络模型的基础上,通过建立双半径网络节点模型从而进一步约束了未知节点的位置。理论分析及仿真结果均表明,该算法在显著提高定位覆盖率的同时,有效地提高了定位精度。

关键词：无线传感器网络定位 bounding Box算法离散网络虚拟锚节点

What and where: A context-based recommendation system for object insertion

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2020年第1期6卷 79-93页

作者： Song-Hai Zhang Zheng-Ping Zhou Bin Liu Xi Dong Peter Hall Tsinghua University Beijing 100084China Beijing National Research Center for Information Science and Technology(BNRist) Tsinghua UniversityBeijing 100084China Department of Computer Science Media Technology Research Center University of BathBath BA27AYUK

We propose a novel problem revolving around two tasks:(i)given a scene,recommend objects to insert,and(ii)given an object category,retrieve suitable background scenes.A bounding box for the inserted object is predicted in both tasks,which helps downstream applications such as semiautomated advertising and video composition.The major challenge lies in the fact that the target object is neither present nor localized in the input,and furthermore,available datasets only provide scenes with existing objects.To tackle this problem,we build an unsupervised algorithm based on object-level contexts,which explicitly models the joint probability distribution of object categories and bounding boxes using a Gaussian mixture model.Experiments on our own annotated test set demonstrate that our system outperforms existing baselines on all sub-tasks,and does so using a unified framework.Future extensions and applications are suggested.

关键词： object recommendation bounding box prediction image composition object-level context

一种基于虚拟锚节点策略改进的bounding Box定位算法

在线全文

学校读者我要写书评

暂无评论

电子器件 2014年第2期37卷 332-336页

作者：周莹重庆电子工程职业学院应用电子学院重庆401331

针对bounding Box算法定位误差大、覆盖率低的缺点,提出了一种采用虚拟锚节点策略的改进定位算法。首先未知节点利用其通信范围内的锚节点进行定位;其次,已定位的节点根据升级策略有选择性的升级为虚拟锚节点;最后,无法定位的节点利用... 详细信息

针对bounding Box算法定位误差大、覆盖率低的缺点,提出了一种采用虚拟锚节点策略的改进定位算法。首先未知节点利用其通信范围内的锚节点进行定位;其次,已定位的节点根据升级策略有选择性的升级为虚拟锚节点;最后,无法定位的节点利用虚拟锚节点实现定位。另外,在离散网络模型的基础上,通过建立双半径网络节点模型从而进一步约束了未知节点的位置。理论分析及仿真结果均表明,该算法在显著提高定位覆盖率的同时,有效地提高了定位精度。

关键词：无线传感器网络定位 bounding Box算法离散网络虚拟锚节点

RAY TRACING BEZIER SURFACE

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 1990年第1期5卷 49-57页

作者： Chai WeiyanNorthwestern Polytechnical University Northwestern Polytechnical Univ

A new algorithm for ray tracing bicubic Bezier surface intersection is presented. In order to find the intersected patches more effectively, a quadtree representation for surface patches is utilized. The introduction of the alternative binary tree subdivision of Bezier surface effectively improves the performance of the ray surface intersection, with the benefit of avoiding the problem that the binary tree subdivision would produce long narrow patches and speeding the intersection finding process. The algorithm has been programmed in FORTRAN-77 and on prime-550 II computer. The result shows that its structure is simple and it is easy to implement with good performance.

关键词： intersection patches Bezier SURFACE utilized tracing bounding FORTRAN corner polygon

A Fast Algorithm for Polygon Operations

在线全文

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 1991年第1期6卷 91-96页

作者：蔡士杰张福炎 Department of Computer Science Nanjing UniversityNanjing 210008

In this paper,a fast algorithm for polygon operations is introduced.The intersection validation testingmethod is described.

关键词： intersection polygon operations hidden vertex straight bounding sorting outside instead