检索结果-内蒙古大学图书馆

conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yao Huang Yinpeng Dong Shouwei Ruan Xiao Yang Hang Su Xingxing Wei Institute of Artificial Intelligence Beihang University Beijing China RealAI Dept. of Comp. Sci. and Tech. Institute for AI Tsinghua-Bosch Joint ML Center THBI Lab BNRist Center Tsinghua University Beijing China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Compared with transferable untargeted attacks, transferable targeted adversarial attacks could specify the mis-classification categories of adversarial samples, posing a greater threat to security-critical tasks. In the meanwhile, 3D adversarial samples, due to their potential of multi-view robustness, can more comprehensively identify weak-nesses in existing deep learning systems, possessing great application value. However, the field of transferable targeted 3D adversarial attacks remains vacant. The goal of this work is to develop a more effective technique that could generate transferable targeted 3D adversarial examples, filling the gap in this field. To achieve this goal, we design a novel framework named TT3D that could rapidly reconstruct from few multi-view images into Transferable Targeted 3D textured meshes. While existing mesh-based texture optimization methods compute gradients in the high-dimensional mesh space and easily fall into local optima, leading to unsatisfactory transferability and distinct distortions, TT3D innovatively performs dual optimization towards both feature grid and Multi-layer Perceptron (MLP) parameters in the grid-based NeRF space, which significantly enhances black-box transferability while enjoying naturalness. Experimental results show that TT3D not only exhibits superior cross-model transferability but also maintains considerable adaptability across different renders and vision tasks. More importantly, we produce 3D adversarial examples with 3D printing techniques in the real world and verify their robust performance under various scenarios.

关键词： visualization Three-dimensional displays Closed box optimization methods Three-dimensional printing Neural radiance field Filling

来源：评论

学校读者我要写书评

暂无评论

Optical Frequency Domain visualization of Electron Beam Driven Plasma Wakefields

引用

AIP conference Proceedings 2010年第1期1299卷 505-509页

作者： Rafal Zgadzaj Michael C. Downer Patric Muggli Vitaly Yakimenko Karl Kusche Michhail Fedurin Marcus Babzien aUniversity of Texas Austin TX 78712 USA bUnivesity of Southern California Los Angeles CA 90089 USA cBrookhaven National Laboratory Upton NY 11973 USA

Bunch driven plasma wakefield accelerators (PWFA), such as the “plasma afterburner,” are a promising emerging method for significantly increasing the energy output of conventional particle accelerators [1]. The study and optimization of this method would benefit from an experimental correlation of the drive bunch parameters and the accelerated particle parameters with the corresponding plasma wave structure. However, the plasma wave structure has not been observed directly so far. We will report ongoing development of a noninvasive optical Frequency Domain Interferometric (FDI) [2] and Holographic (FDH) [3] diagnostics of bunch driven plasma wakes. Both FDI and FDH have been previously demonstrated in the case of laser driven wakes. These techniques employ two laser pulses co‐propagating with the drive particle bunch and the trailing plasma wave. One pulse propagates ahead of the drive bunch and serves as a reference, while the second is overlapped with the plasma wave and probes its structure. The multi‐shot FDI and single‐shot FDH diagnostics permit direct noninvasive observation of longitudinal and transverse structure of the plasma wakes. The experiment is being developed at the 70 MeV Linac in the Accelerator Test Facility at Brookhaven National Laboratory to visualize wakes generated by two [4] and multi‐bunch [5] drive beams.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Genetic Algorithm optimization of Teams for Heterogeneity

Genetic Algorithm Optimization of Teams for Heterogeneity

引用

Frontiers in Education (FIE) conference

作者： P. K. Imbrie Jutshi Agarwal Gibin Raju University of Cincinnati Cincinnati USA School of Education University of Cincinnati Cincinnati USA

ISBN: (数字)9781728189611

ISBN: (纸本)9781728189628

This work in progress study aims at developing a system to designate teams to relatively large groups of students in a classroom setting. It is motivated by recent changes in the ABET Criterion 3 accreditation guideline that requires students to demonstrate "an ability to function effectively on a team whose members together provide leadership, create a collaborative and inclusive environment, establish goals, plan tasks, and meet objectives." Outside of accreditation guidelines, team-based learning is becoming the prescribed pedagogical tool to enhance student collaboration and prepare them for professional work environments upon graduation. One important factor in effective team-based learning is to ensure teams are balanced in their abilities and characteristics across team members. Demographical memberships of students can also play an important role in team dynamics and impact the overall success in content learning. Instructors usually assign teams to students by manually looking into their abilities from previous grades and other performance factors. This can then become tedious when aiming to maintain uniform heterogeneity in classrooms of students coming from diverse backgrounds of knowledge, skills, ethnicity, and gender. While some studies have presented the use of computer-aided tools, visualization categorization, and other Artificial Intelligence techniques, this work proposes the use of the Genetic Algorithm (GA) to form teams optimized for heterogeneity. The Genetic Algorithm presented uses a discrete integer-based chromosome representation and groups alleles to represent each team. Standard GA operators enable the algorithm to be adapted to any optimizing criteria deemed fit by the instructor. The algorithm presented in this work uses self-reported competency data on 3 different computational skills for 1300 students enrolled in a firstyear engineering design thinking course divided into over 20course sections of strength 40-60 each. Net team scores

关键词： Genetic algorithms Tools Biological cells Genetics optimization Collaboration Statistics

来源：评论

学校读者我要写书评

暂无评论

SLAM and Map Learning using Hybrid Semantic Graph optimization *

SLAM and Map Learning using Hybrid Semantic Graph Optimizati...

引用

Mediterranean conference on Control and Automation (MED)

作者： Ambuj Agrawal Dhruv Agarwal Mehul Arora Ritik Mahajan Shivansh Beohar Lhilo Kenye Rahul Kala Centre of Intelligent Robotics Indian Institute of Information Technology Allahabad India NavAjna technologies Pvt. Ltd Hyderabad India

ISBN: (数字)9781665406734

ISBN: (纸本)9781665406741

Visual Simultaneous Localization and Mapping using budget-grade cameras only faces the challenges of continuous drifts that accumulate with time. While loop closure techniques mitigate the effects, they are applicable only when the robot completes a loop, which is a rarity in everyday navigation. The motion blur and smaller resolution of budget cameras further reduce the accuracy of SLAM. In this paper, we aim to solve the problem of active drift correction for a low-cost robot to solve autonomous navigation using the semantic map. Semantic maps have been used previously for re-localization but are useful only when the semantic maps themselves are highly accurate which is not realizable for budget robots. The semantic maps also face problems of correspondence matching in areas rich with recurrent semantics. To alleviate the same effects, the robot performs SLAM using a hybrid graph optimization consisting of semantic points whose pose is obtained from the semantic map database, and the non-semantic point features. The semantic map corrects for the drift, while the non-semantic features apply local smoothing that helps in mitigating the errors of the semantic map. They also apply robustness against errors in correspondence matching. The semantic graph may itself have errors, which are hence learned with time as the robot navigates. The robot adds new semantic objects into the database if it observes them, while the robot also mends the position based on the new observations. The initial semantic map is made using images captured by a camera on a few known poses, based on which it adds the observed semantics.

关键词： visualization Simultaneous localization and mapping Navigation Databases Semantics Robot vision systems Cameras

来源：评论

学校读者我要写书评

暂无评论

Design and Research on Visual Recognition System for Fruit Sorting Collaborative Robot

Design and Research on Visual Recognition System for Fruit S...

引用

Networking Systems of AI (INSAI), International conference on

作者： Yingchen Ma Hanan Zhu Hongli Jia Chunlai Guo Jiaqi Li Zhe Li College of Intelligent Engineering Harbin Institute of Petroleum Harbin China College of Intelligent Engineering Heilongjiang Agricultural Engineering Vocational College Harbin China IE Technology Research Center Harbin Cambridge University Harbin China

ISBN: (数字)9798350344660

ISBN: (纸本)9798350344677

This study aimed to enhance the efficiency and accuracy of fruit sorting through the development of a collaborative robotic vision recognition system based on neural networks. Leveraging convolutional neural networks (CNNs), a substantial dataset of fruit images was collected, preprocessed, and utilized for training. The core algorithm employed was the neural network, particularly effective in pattern recognition and feature extraction. Integration with the control system of collaborative robots allowed real-time fruit identification and analysis using visual sensors during sorting. The system's design considered optimization and acceleration of neural networks, incorporating advanced deep learning techniques like CNNs and recurrent neural networks. This fusion of collaborative robots, neural networks, and visual recognition technologies significantly improved fruit sorting efficiency and accuracy. The automated sorting process achieved through thoughtful system design and optimization reduces labor costs and enhances productivity. Despite notable progress in the design and research of collaborative robotic and neural network-based vision recognition systems, challenges and areas for improvement persist. Future work may involve further optimizing neural network models for increased precision and robustness and refining collaborative robot control strategies for more complex task collaboration. The collaborative robotic and neural network-based vision recognition system opens new possibilities in the field of fruit sorting, propelling the industry towards intelligent and efficient practices, thereby creating greater economic and societal value.

关键词： visualization Accuracy Image recognition Service robots Machine vision Neural networks Collaborative robots Real-time systems Convolutional neural networks Sorting

来源：评论

学校读者我要写书评

暂无评论

Visualizing Test Diversity to Support Test Optimisation

Visualizing Test Diversity to Support Test Optimisation

引用

Asia-Pacific conference on Software Engineering

作者： Francisco Gomes De Oliveira Neto Robert Feldt Linda Erlenhov José Benardi De Souza Nunes Dept. of Computer Science and Engineering Chalmers University of Gothenburg Gothenburg Sweden Department of Computing Systems Federal University of Campina Grande Campina Grande Brazil

ISBN: (纸本)9781728119717;9781728119700

Diversity has been used as an effective criteria to optimise test suites for cost-effective testing. Particularly, diversity-based (alternatively referred to as similarity-based) techniques have the benefit of being generic and applicable across different Systems Under Test (SUT), and have been used to automatically select or prioritise large sets of test cases. However, there is a challenge in how to present diversity information to developers and testers since results are typically many-dimensional. Furthermore, the generality of diversity-based approaches makes it harder to choose when and where to apply them. In this paper we address these challenges by investigating: i) what are the trade-offs in using different sources of diversity (e.g., diversity of test requirements or test scripts) to optimise large test suites, and ii) how visualisation of test diversity data can assist testers for test optimisation and improvement. We perform a case study on three industrial projects and present quantitative results on the fault detection capabilities and redundancy levels of different sets of test cases. Our key result is that test similarity maps, based on pair-wise diversity calculations, helped industrial practitioners identify issues with their test repositories and decide on actions to improve. We conclude that the visualisation of diversity information can assist testers in their maintenance and optimisation activities.

关键词： optimization Testing Indexes Data visualization Fault detection Maintenance engineering Subspace constraints

来源：评论

学校读者我要写书评

暂无评论

Monocular Visual Odometry for Robot Localization in LNG Pipes

Monocular Visual Odometry for Robot Localization in LNG Pipe...

引用

2011 IEEE International conference on Robotics and Automation(2011年IEEE世界机器人与自动化大会 ICRA 2011)

作者： Peter Hansen Brett Browning Hatem Alismail Peter Rander Qri8 lab Carnegie Mellon UniversityDohaQatar Robotics Institute/NREC Carnegie Mellon UniversityPittsburgh PAUSA

Regular inspection for corrosion of the pipes used in Liquified Natural Gas (LNG) processing facilities is critical for safety. We argue that a visual perception system equipped on a pipe crawling robot can improve on existing techniques (Magnetic Flux Leakage, radiography, ultrasound) by producing high resolution registered appearance maps of the internal surface. To achieve this capability, it is necessary to estimate the pose of sensors as the robot traverses the pipes. We have explored two monocular visual odometry algorithms (dense and sparse) that can be used to estimate sensor pose. Both algorithms use a single easily made measurement of the scene structure to resolve the monocular scale ambiguity in their visual odometry estimates. We have obtained pose estimates using these algorithms with image sequences captured from cameras mounted on different robots as they moved through two pipes having diameters of 152mm (6”) and 406mm (16”), and lengths of 6 and 4 meters respectively. Accurate pose estimates were obtained whose errors were consistently less than 1 percent for distance traveled down the pipe.

关键词： Cameras visualization optimization Measurement Robot vision systems Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Visual Alignment with Similarity Graphs

Unsupervised Visual Alignment with Similarity Graphs

引用

IEEE conference on Computer Vision and Pattern Recognition

作者： Fatemeh Shokrollahi Yancheshmeh Ke Chen Joni-Kristian Kamarainen Department of Signal Processing Tampere University of Technology

ISBN: (纸本)9781467369657

Alignment of semantically meaningful visual patterns, such as object classes, is an important pre-processing step for a number of applications such as object detection and image categorization. Considering the expensive manpower spent on the annotation for supervised alignment methods, unsupervised alignment techniques are more favorable especially for large-scale problems. Fine adjustment can be effectively and efficiently achieved with image congealing methods, but they require moderately good initialization which is largely invalid in practice. Alignment of visual class examples with large viewpoint changes remains as an open problem. Feature-based methods can solve the problem to some degree, but require manual selection of a good seed image and omit the fact that examples of a semantic class can be visually very different (e.g., Harley-Davidsons and Scooters in "motorbikes"). In this work, we overcome the aforementioned drawbacks by defining visual similarity under the generalized assignment problem which is solved by fast approximation and non-linear optimization. From pair-wise image similarities we construct an image graph which is used to step-wise align, "morph", an image to another by graph traveling. We automatically find a suitable seed by novel centrality measure which identifies "similarity hubs" in the graph. The proposed approach in the unsupervised manner outperforms the state-of-the-art methods with classes from the popular benchmark datasets.

关键词： images Imagery (Psychotherapy) Alignment Image Mopeds Object detection visualization ANNOTATIONS Line graph

来源：评论

学校读者我要写书评

暂无评论

On the performance of ConvNet features for place recognition

On the performance of ConvNet features for place recognition

引用

IEEE/RSJ International conference on Intelligent Robots and Systems

作者： N. Sunderhauf S. Shirazi F. Dayoub B. Upcroft M. Milford ARC Centre of Excellence for Robotic Vision Queensland University of Technology (QUT)

After the incredible success of deep learning in the computer vision domain, there has been much interest in applying Convolutional Network (ConvNet) features in robotic fields such as visual navigation and SLAM. Unfortunately, there are fundamental differences and challenges involved. Computer vision datasets are very different in character to robotic camera data, real-time performance is essential, and performance priorities can be different. This paper comprehensively evaluates and compares the utility of three state-of-the-art ConvNets on the problems of particular relevance to navigation for robots;viewpoint-invariance and condition-invariance, and for the first time enables real-time place recognition performance using ConvNets with large maps by integrating a variety of existing (locality-sensitive hashing) and novel (semantic search space partitioning) optimization techniques. We present extensive experiments on four real world datasets cultivated to evaluate each of the specific challenges in place recognition. The results demonstrate that speed-ups of two orders of magnitude can be achieved with minimal accuracy degradation, enabling real-time performance. We confirm that networks trained for semantic place categorization also perform better at (specific) place recognition when faced with severe appearance changes and provide a reference for which networks and layers are optimal for different aspects of the place recognition problem.

关键词： Feature extraction Robustness visualization Real-time systems Semantics Computer vision

来源：评论

学校读者我要写书评

暂无评论

Innovative Deep Learning techniques for Solving Complex Computer Vision Challenges and Enhancing Pattern Recognition Accuracy

Innovative Deep Learning Techniques for Solving Complex Comp...

引用

Distributed Systems, Computer Networks and Cybersecurity (ICDSCNC), International conference on

作者： T. Jayachitra S. Sathya Ramesh P S Jothikumar R Gouri M. S Mohammed Waheeduddin Hussain Department of Electrical Electronics and Communication Engineering Sharda University Greater Noida India Department of Artificial Intelligence and Data Science GRT Institute of Engineering and Technology Tiruttani India Department of Smart Computing Vellore Institute of Technology Vellore India Department of Computer Science and Engineering Shadan College of Engineering and Technology Hyderabad India Department of Computer Science and Engineering Baselios Mathews - II College of Engineering Sasthamcotta Kollam India Department of Information Technology Shadan College of Engineering and Technology Peerancheru Hyderabad India

ISBN: (数字)9798350375442

ISBN: (纸本)9798350375459

The proposed work provides an in-depth analysis of DL techniques to enhance pattern recognition accuracy in difficult computer vision applications. This background explains the present status of the problems in the area and motivates the development of a complex framework that blends innovative neural network topologies, state-of-the-art optimization approaches, and inventive data augmentation strategies. Among the methods are CNNs enhanced with residual blocks and attention mechanisms, which are implemented using the TensorFlow deep learning framework. The results demonstrate significant improvements over baseline models on a number of measures. Using the CIFAR-10 dataset, the proposed system achieves an impressive 92.5% accuracy and 92.1% F1-score for classification tasks. With an IoU of 78.2% and a mAP of 81.4% in object identification tasks, the system shows its robustness in accurately localizing and recognizing things within photos. These findings have practical ramifications for industries needing accurate visual identification, such autonomous driving and medical imaging, in addition to advancing theoretical knowledge. The efficacy of the architecture highlights its potential to serve as a benchmark for next deep learning studies and applications.

关键词： Deep learning Computer vision visualization Accuracy Network topology Neural networks Data augmentation Topology Pattern recognition Object recognition

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：