检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Gallagher, James E. Oughton, Edward J. Department of Geography Geoinformation Science Department George Mason University FairfaxVA22030 United States

Multispectral imaging and deep learning have emerged as powerful tools supporting diverse use cases from autonomous vehicles, to agriculture, infrastructure monitoring and environmental assessment. The combination of these technologies has led to significant advancements in object detection, classification, and segmentation tasks in the non-visible light spectrum. This paper considers 400 total papers, reviewing 200 in detail to provide an authoritative meta-review of multispectral imaging technologies, deep learning models, and their applications, considering the evolution and adaptation of You Only Look Once (YOLO) methods. Ground-based collection is the most prevalent approach, totaling 63% of the papers reviewed, although uncrewed aerial systems (UAS) for YOLO-multispectral applications have doubled since 2020. The most prevalent sensor fusion is Red-Green-Blue (RGB) with Long-Wave Infrared (LWIR), comprising 39% of the literature. YOLOv5 remains the most used variant for adaption to multispectral applications, consisting of 33% of all modified YOLO models reviewed. 58% of multispectral-YOLO research is being conducted in China, with broadly similar research quality to other countries (with a mean journal impact factor of 4.45 versus 4.36 for papers not originating from Chinese institutions). Future research needs to focus on (i) developing adaptive YOLO architectures capable of handling diverse spectral inputs that do not require extensive architectural modifications, (ii) exploring methods to generate large synthetic multispectral datasets, (iii) advancing multispectral YOLO transfer learning techniques to address dataset scarcity, and (iv) innovating fusion research with other sensor types beyond RGB and LWIR. © 2024, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Advancements in Object Detection for Unmanned Aerial Vehicles: applications, Challenges, and Future Perspectives

Advancements in Object Detection for Unmanned Aerial Vehicle...

引用

International Symposium on Digital Forensic and Security (ISDFS)

作者： Anıl Sezgin Aytuğ Boyacı Siemens Corporate Technology Istanbul Turkey Department of Computer Engineering National Defence University Air Force Academy Istanbul Turkey

ISBN: (数字)9798350330366

ISBN: (纸本)9798350330373

Unmanned Aerial Vehicles (UAVs) are used in different fields ranging from recreational vehicles to agriculture, environmental monitoring, infrastructure inspection, disaster management, security, surveillance and logistics. This paper provides an overview of UAV applications and highlights the importance of object detection in improving drone autonomy. Object detection facilitates tasks such as precision agriculture, disaster response, environmental protection, infrastructure inspection and autonomous navigation. The paper reviews recent advances in UAV-specific object detection algorithms and methodologies and highlights challenges such as varying altitudes, motion blur, real-time processing constraints and limited computational resources. Solutions and adaptations are discussed to overcome these challenges, including lightweight neural network architectures, transfer learning, data augmentation, edge computing, multi-sensor fusion, attention mechanisms and adaptive algorithms. The study highlights the importance of integrating object detection systems into UAVs to improve their use in various sectors and contribute to improvements in surveillance missions.

关键词： Reviews Surveillance Transfer learning Object detection Inspection Autonomous aerial vehicles Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Multi-sensor aided deep pose tracking 2nd

Multi-sensor aided deep pose tracking

引用

2nd Modeling, Estimation and Control Conference (MECC)

作者： Lee, Hojun Toner, Tyler Tilbury, Dawn Barton, Kira Univ Michigan Dept Robot Ann Arbor MI 48109 USA Univ Michigan Dept Mech Engn Ann Arbor MI 48109 USA

Accurate pose estimation of nearby objects is critical for robots to dynamically interact with their surroundings. The complexity of this task has led researchers to explore deep learning methods. Nowadays, many works have solely focused on developing complicated neural network architectures to estimate pose from a simple monocular camera. However, most of these methods struggle with inherent limitations of a single sensor system, like occlusion, which are commonly encountered in mobile robotics applications. Online, occlusion-robust pose estimation is extremely important in such cases, as mobility of a robot introduces major uncertainty that complicates manipulation. Hence, we present Multi-sensor aided Deep Pose Tracking (MS-DPT), a framework for online object pose estimation to enable robust mobile manipulation. A Convolutional Neural Network (CNN) identifies key objects in an RGB-D image, from which object pose estimates are generated using a variant of the Iterative Closest Point (ICP) algorithm. An extended Kalman filter is used to fuse this pose estimate with onboard motion sensors to compensate for occlusion and robot motion during manipulation. This three stage method focuses on cohering different modalities and algorithms to improve the pose tracking stability and continuity in cases where the target object becomes heavily occluded by an obstacle or a mobile robot itself. The proposed approach accurately tracks textureless objects with high symmetries while operating at 10 FPS during experiments. Copyright (c) 2022 The Authors. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0)

关键词： Object pose estimation Neural-network model Robot vision Data fusion Tracking

来源：评论

学校读者我要写书评

暂无评论

Field Experiments with an Automated Utility Platform for Transportation and Work Processes

Field Experiments with an Automated Utility Platform for Tra...

引用

IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)

作者： Edlinger, Raimund Dumberger, Stefan Froschauer, Roman Pointner, Wolfgang Zeilinger, Marcel Nuechter, Andreas Univ Appl Sci Upper Austria Smart Automat & Robot Wels Austria AIT Austrian Inst Technol Assist & Autonomous Syst Vienna Austria Julius Maximilians Univ Wurzburg Informat Robot & Telemat 7 Wurzburg Germany

ISBN: (纸本)9781665482172

The automation of transport and work tasks in various application domains continues to be a major challenge. The proposed paper presents key technologies within a process from sensing to reasoning and includes: (i) understanding the scene and its relations through new approaches in object classification and pose estimation based on machine learning, as well as methods for reliable detection of objects and object features;(ii) reliable and safe outdoor localization and mapping based on multi-modal approaches and innovative camera-based methods. The fusion of different sensor data is used for reliable obstacle detection and collision avoidance. The investigation of suitable system architectures, data processing platforms and communication mechanisms taking into account safety requirements is a prerequisite for the operation in a safety-critical environment. The paper provides a proof of concept for an automated platform to demonstrate and evaluate application scenario provided by the Linz Airport in the form of an automated transport process for air freight between a terminal and the aircraft.

关键词： Localization Mapping and Navigation applications of Autonomous Intelligent Robots Autonomous Robotic Systems Robotic Simulation sensors and sensor Integration

来源：评论

学校读者我要写书评

暂无评论

PreSim: A 3D Photo-Realistic Environment Simulator for Visual AI

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第2期6卷 2501-2508页

作者： Yuan, Honglin Veltkamp, Remco C. Univ Utrecht Dept Informat & Comp Sci NL-3584 CC Utrecht Netherlands

Recent years have witnessed great advancement in visual artificial intelligence (AI) research based on deep learning. To take advantage of deep learning, we need to collect a large amount of data in various environments and conditions. However, collecting such data is time-consuming and labor-intensive. Apart from that, developing and testing visual AI algorithms for multisensory models is expensive and in some cases dangerous processes in the real world. We present PreSim, a 3D environment simulator which provides photo-realistic simulations using a view synthesis module and supports flexible configuration of multimodal sensors to address both of these issues. For our view synthesis module we introduce novel depth refinement, adaptive view selection and layered rendering, to provide realistic imagery. We demonstrate that PreSim has several advantages: (i) it provides a photo-realistic 3D environment which allows seamlessly integrating multisensory models in the virtual world and enables them to perceive and navigate scenes, (ii) it has an internal view synthesis module which allows transforming algorithms developed and tested in simulation to physical platforms without domain adaption, (iii) it can generate a large amount of data for vision-based applications, such as depth estimation and object pose estimation.

关键词： Simulation and animation sensor fusion RGB-D Perception

来源：评论

学校读者我要写书评

暂无评论

Research on the System Design and Application of Mobile Manipulator Hybrid Robot for Transporting in Intelligent Factory

Research on the System Design and Application of Mobile Mani...

引用

Intelligent Control, Measurement and Signal Processing and Intelligent Oil Field (ICMSP), International Conference on

作者： Xiaohong Qin Lianhao Zhang Bin Zhao Shenyang Institute of Science and Technology Shenyang China Northeastern University Shenyang China SIASUN Robot & Automation Co. Shenyang China

ISBN: (数字)9798331516550

ISBN: (纸本)9798331516567

Based on the development and application status of mobile manipulator hybrid robot, this paper takes the handling process requirements of intelligent factories in China as the research objective to design and develop a composite robot platform system. The hardware system mainly includes mobile platforms, manipulators, and sensors. The software system mainly consists of control systems, software architectures, algorithm libraries and corresponding communication protocols. This platform system has the key technologies of scene information perception, mobile path planning and self-collision detection of the manipulator during the grasping process, which are necessary in engineering project applications. The corresponding innovative algorithms are embedded in it, and scene tests and effect analysis are carried out in a memory module production factory. Test results show that, compared with mainstream products and application technologies in the field, this mobile manipulator hybrid robot can use multiple sensors to obtain scene information and conduct high-precision data fusion, simultaneously meet multiple measurement indicators of mobile path planning, and quickly achieve pre-collision warning without the application of sensors, verifying the effectiveness and advancement of the independently developed platform system.

关键词： Software architecture Service robots Software algorithms Memory modules sensor fusion Manipulators Robot sensing systems Production facilities Path planning Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

Resource-Efficient sensor fusion via System-Wide Dynamic Gated Neural Networks

arXiv

引用

arXiv 2024年

作者： Singhal, C. Wu, Y. Malandrino, F. de Guevara Contreras, S. Ladron Levorato, M. Chiasserini, C.F. INRIA France UC Irvine United States CNR-IEIIT Italy CNIT Italy Politecnico di Torino Italy Chalmers University of Technology Sweden

Mobile systems will have to support multiple AI-based applications, each leveraging heterogeneous data sources through DNN architectures collaboratively executed within the network. To minimize the cost of the AI inference task subject to requirements on latency, quality, and - crucially - reliability of the inference process, it is vital to optimize (i) the set of sensors/data sources and (ii) the DNN architecture, (iii) the network nodes executing sections of the DNN, and (iv) the resources to use. To this end, we leverage dynamic gated neural networks with branches, and propose a novel algorithmic strategy called Quantile-constrained Inference (QIC), based upon quantile-Constrained policy optimization. QIC makes joint, high-quality, swift decisions on all the above aspects of the system, with the aim to minimize inference energy cost. We remark that this is the first contribution connecting gated dynamic DNNs with infrastructure-level decision making. We evaluate QIC using a dynamic gated DNN with stems and branches for optimal sensor fusion and inference, trained on the RADIATE dataset offering Radar, LiDAR, and Camera data, and real-world wireless measurements. Our results confirm that QIC matches the optimum and outperforms its alternatives by over 80%. Copyright © 2024, The Authors. All rights reserved.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Grayscale and Event-Based sensor fusion for Robust Steering Prediction for Self-Driving Cars

Grayscale and Event-Based Sensor Fusion for Robust Steering ...

引用

IEEE sensors applications Symposium, SAS

作者： Luca Pascarella Michele Magno ETH Zurich Zurich Switzerland

Event-based vision, led by a dynamic vision sensor (DVS), is a bio-inspired vision model that leverages timestamped pixel-level brightness changes of non-static scenes. Thus, DVS's architecture captures the dynamics of a scene and filters static information out. Although machine learning algorithms based on DVS inputs overcome active pixel sensors (APS), they still struggle in challenging conditions. For example, DVS-based models outperform APS-based ones in high-dynamic scenes but suffer in static landscapes. In this paper, we present GEFU (Grayscale and Event-based FUsor), an approach that opens to sensor fusion by combining grayscale and event-based inputs. In particular, we evaluate GEFU's performance on a practical task: predicting a vehicle's steering angle in a realistic driving condition. GEFU is built on top of a consolidated convolutional neural network and trained with realistic driving conditions. Our approach outperforms solo DVS- or APS-based models on nontrivial driving cases, such as the static scenes for the former and the suboptimal light exposure for the latter approach. Our results show that GEFU (i) reduces the root-mean-squared error to ~2° and (ii) although the magnitude of the steering angle does not always match the ground truth, the steering direction left/right is always predicted correctly.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural Network Image fusion with PCA Preprocessing 3

Neural Network Image Fusion with PCA Preprocessing

引用

Conference on Big Data iiI - Learning, Analytics, and applications

作者： Depoian, Arthur C., ii Jaques, Lorenzo E. Xie, Dong Bailey, Colleen P. Guturu, Parthasarathy Univ North Texas Dept Elect Engn Denton TX 76207 USA

ISBN: (数字)9781510642980

ISBN: (纸本)9781510642980

The techniques for fusion of multi-spectral sensor datasets containing complementary information about the subject of observation facilitate visualization of the data into a form more easily interpreted by both humans and algorithms. Many applications of feature-level fusion seek to combine edges and textures, across the bandwidth of the sensory spectrum. Visualization techniques can be skewed by the introduction of corruption and redundancies induced by harmonics. A majority of image fusion techniques rely on intensity hue saturation (IHS) transforms, principal component analysis (PCA), and Gram Schmidt process. PCA's ability to remove the redundancy from a set of correlated data while preserving the variance and its resistance to color distortion lends itself to this data-fusion application. PCA also has a lower spectral distortion as compared to IHS and has been found to create superior image fusion. The application of neural network control techniques has been shown to more accurately recreate results similar to those found by human inference. Over the years, increased computation power has given rise to the spread of neural networks into roles previously carried out by humans. Select advanced image processing techniques have benefited greatly from their implementation. We propose a novel method of utilizing PCA in conjunction with a neural network to achieve a higher quality of image fusion. Implementation of an autoencoder neural network to fuse this information creates a higher level of data visualization when compared to traditional weighted fusion techniques.

关键词： Image fusion Principal Component Analysis Autoencoder

来源：评论

学校读者我要写书评

暂无评论

Dynamic Buffer Sizing for Out-of-order Event Compensation for Time-sensitive applications

引用

ACM TRANSACTIONS ON sensor NETWORKS 2020年第1期17卷 1–23页

作者： Weiss, Wolfgang Jimenez, Victor J. Exposito Zeiner, Herwig JOANNEUM RES Forsch Gesell MbH DIGITAL Inst Informat & Commun Technol Steyrergasse 17 A-8010 Graz Austria VIRTUAL VEHICLE Res GmbH Inffeldgasse 21a A-8010 Graz Austria

Today's sensor network implementations often comprise various types of nodes connected with different types of networks. These and various other aspects influence the delay of transmitting data and therefore of out-of-order data occurrences. This turns into a crucial problem in time-sensitive applications where data must be processed promptly and decisions must be reliable. In this article, we research dynamic buffer sizing algorithms for multiple, distributed, and independent sources, which reorder event streams, thus enabling subsequent time-sensitive applications to work correctly. To be able to evaluate such algorithms, we had to record datasets first. Five novel dynamic buffer sizing algorithms were implemented and compared to state-of-the-art approaches in this domain. The evaluation has shown that the use of a dynamic time-out buffering method is preferable over a static buffer. The higher the variation of the network or other influences in the environment, the more necessary it becomes to use an algorithm that dynamically adapts its buffer size. These algorithms are universally applicable, easy to integrate in existing architectures, and particularly interesting for time-sensitive applications. Dynamic time-out buffering is still a trade-off between reaction time and out-of-order event compensation.

关键词： Out-of-order event compensation time-sensitive applications distributed systems event processing multi-source event data fusion

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：