检索结果-内蒙古大学图书馆

IEEE Annual International Computer Software and applications conference (COMPSAC)

作者： Yihan Zhang Qian Zhang Dave Towey School of Computer Science University of Nottingham Ningbo China Ningbo China

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

Visible-infrared image fusion is a technique that extracts information from different sensors. It could be used to enhance human visual perception of video surveillance under low-light conditions, and provide rich information for subsequent tasks. Vision Transformer (ViT) based fusion algorithms require standardizing input images to a specific height and width that could be divided into a series of blocks of fixed size. Consequently, a scaling operation must be performed on the original image, which frequently decreases the quality of fusion results. This paper proposes a visible-infrared image fusion neural network that is insensitive to input size, by first utilizing a fixed-size image pre-fusion framework to generate lossless instructive fusion results (IFRs), followed by a size-insensitive enhancing framework that refines these preliminary fused images under the guidance of IFRs. It also has potential applicability to other image fusion algorithms, like multi-focus image fusion.

关键词： Software algorithms Neural networks sensor fusion Video surveillance Transformers Software sensors

来源：评论

学校读者我要写书评

暂无评论

A low-cost, open-source, and distributed ocean profiling sensor node 17

A low-cost, open-source, and distributed ocean profiling sen...

引用

17th IEEE sensors applications Symposium (SAS)

作者： Rico, Andres Prasad, Suparnamaaya Larson, Kent MIT Media Lab Cambridge MA 02139 USA MIT 77 Massachusetts Ave Cambridge MA 02139 USA

ISBN: (数字)9781665409810

ISBN: (纸本)9781665409810

Ocean exploration is emerging as a critical field of research for understanding and combating climate change. While coastal waters house vital marine ecosystems, such as coral reefs, they are still vastly unexplored. sensor nodes in coastal waters can give local communities and researchers relevant data for understanding the relationship between climate change, blue-economy activities, and ecosystem degradation. We present and validate a sensor node that can be opportunistically used by non-industrial fishing boats in order to collectively source ocean profiles containing temperature, light, and acidity levels at multiple depths. We describe the complete system architecture and validate our design with deployments in three different types of water bodies. First, we validate the device's temperature, light, and depth sensors in a submersion within a controlled pool environment. We then evaluate the software-based power cycling for intermittent data acquisition algorithms through a river deployment. Finally, we demonstrate the complete system's functionality and possible ways to incorporate acidity sensing with an open ocean deployment. In addition to field testing, we describe and test possible architectures for adding networking capabilities through a WiFi-based system. We conclude that the device's electrical and mechanical characteristics significantly contribute towards enabling low-cost, community-sourced data acquisition for ocean coastal water profiling.

关键词： Ocean IoT Opportunistic Sensing sensor fusion

来源：评论

学校读者我要写书评

暂无评论

ICRAI 2023 - 2023 9th International conference on Robotics and Artificial Intelligence

ICRAI 2023 - 2023 9th International Conference on Robotics a...

引用

9th International conference on Robotics and Artificial Intelligence, ICRAI 2023

ISBN: (纸本)9798400708282

The proceedings contain 10 papers. The topics discuss include: a mirror-hand rehabilitation system based on virtual reality interaction;enhancing few-shot 3D point cloud semantic segmentation through bidirectional prototype learning;complex skill learning using modified transformers with automatic chunking and forgetting;mapping and optimizing communication in ROS 2-based applications on configurable system-on-chip;wrench feasibility workspace analysis and adaptive rotation algorithm of cable-driven upper limb rehabilitation robot;design and development of medical co-bot to assist surgeon;grammatical evolution based controller design for vehicle robot action learning;enhancing value co-creation in Wenzhou’s elderly care networks: mathematical fusion algorithms for multi-sensor integration in social robotics;and kinematic solution of coupled deformation flexible cable.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-View fusion of sensor Data for Improved Perception and Prediction in Autonomous Driving 22

Multi-View Fusion of Sensor Data for Improved Perception and...

引用

22nd IEEE/CVF Winter conference on applications of Computer Vision (WACV)

作者： Fadadu, Sudeep Pandey, Shreyash Hegde, Darshan Shi, Yi Chou, Fang-Chieh Djuric, Nemanja Vallespi-Gonzalez, Carlos Aurora Innovat Pittsburgh PA 15222 USA Uber ATG Pittsburgh PA USA

ISBN: (纸本)9781665409155

We present an end-to-end method for object detection and trajectory prediction utilizing multi-view representations of LiDAR returns and camera images. In this work, we recognize the strengths and weaknesses of different view representations, and we propose an efficient and generic fusing method that aggregates benefits from all views. Our model builds on a state-of-the-art Bird's-Eye View (BEV) network that fuses voxelized features from a sequence of historical LiDAR data as well as rasterized high-definition map to perform detection and prediction tasks. We extend this model with additional LiDAR Range-View (RV) features that use the raw LiDAR information in its native, non-quantized representation. The RV feature map is projected into BEV and fused with the BEV features computed from LiDAR and high-definition map. The fused features are then further processed to output the final detections and trajectories, within a single end-to-end trainable network. In addition, the RV fusion of LiDAR and camera is performed in a straightforward and computationally efficient manner using this framework. The proposed multi-view fusion approach improves the state-of-the-art on proprietary large-scale real-world data collected by a fleet of self-driving vehicles, as well as on the public nuScenes data set with minimal increases on the computational cost.

关键词： Laser radar Object detection Predictive models Feature extraction Cameras Prediction algorithms Trajectory

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

Resource-Efficient Sensor Fusion via System-Wide Dynamic Gat...

引用

IEEE Communications Society conference on sensor and Ad Hoc Communications and Networks (SECON)

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

ISBN: (数字)9798331519186

ISBN: (纸本)9798331519193

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%.

关键词： Wireless communication Wireless sensor networks Costs Soft sensors Heuristic algorithms Neural networks Logic gates sensor fusion Dynamic scheduling Time measurement

来源：评论

学校读者我要写书评

暂无评论

Advances in multi-sensor fusion for body sensor networks: algorithms, architectures, and applications

引用

INFORMATION fusion 2019年 45卷 150-152页

作者： Fortino, Giancarlo Gravina, Raffaele Ghasemzadeh, Hassan Liu, Peter X. Poon, Carmen C. Y. Wang, Zhelong Univ Calabria Commenda Di Rende Italy Washington State Univ Pullman WA 99164 USA Carleton Univ Ottawa ON Canada Chinese Univ Hong Kong Hong Kong Hong Kong Peoples R China Dalian Univ Technol Dalian Peoples R China

来源：评论

学校读者我要写书评

暂无评论

Distributed MHT with Passive sensors 24

Distributed MHT with Passive Sensors

引用

24th IEEE International conference on Information fusion (fusion)

作者： Coraluppi, Stefano Rago, Constantino Carthel, Craig Bale, Brandon Syst & Technol Res 600 West Cummings Pk Woburn MA 01801 USA

ISBN: (纸本)9781737749714

This paper focuses on two challenges in multi-target tracking with passive sensors. The first is the well-known observability problem whereby individual sensor measurements are insufficient to localize targets. The second is the need to relax the usual small-target assumption of at most one measurement per target per scan. Indeed, in some applications such as passive sonar, there are repeated measurements, i.e. multiple detections per target per scan of one sensor. We examine these challenges in a multi-sensor setting and describe the advantages of a distributed MHT solution architecture, with measurement-space tracking following by multi-sensor Cartesian tracking using a robust Cartesian initialization scheme. In the presence of repeated measurements, there are (at least) two viable processing architectures. In both cases we leverage a recently developed generalization to the MHT recursion. We study the relative merits of the two alternative solutions.

关键词： multi-target tracking (MTT) multiple-hypothesis tracking (MHT) observability repeated measurements fusion architectures

来源：评论

学校读者我要写书评

暂无评论

The Information fusion on Person Recognition Using Hip Joint Angles

The Information Fusion on Person Recognition Using Hip Joint...

引用

IEEE conference on Industrial Electronics and applications (ICIEA)

作者： Rabé Andersson T. Sunil Kumar José Chilo Department of Electrical Engineering Mathematics and Science University of Gävle Gävle Sweden

ISBN: (数字)9798350360868

ISBN: (纸本)9798350360875

In this research, we investigate the efficacy of information fusion techniques for the purpose of gait pattern recognition using hip joint angle data captured by smartphone sensors. The classifiers tested were the Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Naive Bayes (NB) algorithms, which gave the highest classification accuracy. But, to further enhance the classification accuracy, we integrated score-level fusion (SLF) and decision-level fusion (DLF), leveraging multiple classifier algorithms. Our experiment results reveal that information fusion techniques improve the overall accuracy with 90.5% for the score-level fusion and 91% for the decision-level fusion (voting scheme), indicating the effectiveness of ensemble methods in hip joint angle-based recognition systems. Lastly, some Limitations of the study, such as the use of treadmills and the focus on healthy adult gait patterns are recognized, highlighting areas for future research, including the application to individuals with gait-affecting conditions.

关键词： Support vector machines Training Accuracy Nearest neighbor methods sensor fusion Classification algorithms Bayes methods

来源：评论

学校读者我要写书评

暂无评论

Enhancing Agricultural Productivity: A sensor fusion, Spectroscopic Near Infrared, and AI-Based Framework for Monitoring Fruit Ripeness

Enhancing Agricultural Productivity: A Sensor Fusion, Spectr...

引用

International Bhurban conference on Applied Sciences & Technology, IBCAST

作者： Hira Ambreen Muhammad Imran Tang Diyin Chongsheng Zhang Sir Syed CASE Institute of Technology Islamabad Pakistan School of Automation Science and Electrical Engineering Beihang University Aeronautics and Astronautics China Department of EE Military College of Signals National University of Sciences & Technology (NUST) Henan Univerity Kaifeng China Department of Detection and Automation Engineering School of Automation Science and Electrical Engineering Beihang University Aeronautics and Astronautics China School of Computer & Information Engineering Henan University Kaifeng China

ISBN: (数字)9798331516680

ISBN: (纸本)9798331516697

Fruit ripeness evaluation is essential for harvest optimization and post-harvest loss prevention. Traditional visual inspection is inefficient. This study employs sensor fusion and AI algorithms to evaluate fruit maturity in real-time using gas sensors (i.e., MQ-3, MQ-6, MQ-8, MQ-135) and Near-Infrared spectral sensors (i.e., GY-AS7263). Primarily, data pro-cessing-sensor fusion, data preparation, and AI model application-is crucial to the proposed framework. Subsequently, sensor fusion approaches improve data accuracy by combining signals from various sensors. Secondly, data pretreatment techniques including noise reduction, normalization, and feature extraction prepare data for analysis. Thirdly, we use powerful machine learning algorithms such as Random Forest to judge maturity more accurately and reliably than conventional techniques. Lastly, integrating NIR spectroscopy with gas sensor data resolves cost and model transferability issues, enhancing accuracy and acces-sibility for agricultural use. Static image processing techniques provide challenges for real-time applications, including expensive computer costs and lower reliability. The proposed framework based on multi-sensor fusion system enhances agricultural applications' versatility, scalability, and reactivity, surpassing existing methodologies.

关键词： Productivity Accuracy Machine learning algorithms Noise reduction sensor fusion Feature extraction Real-time systems Reliability Monitoring Gas detectors

来源：评论

学校读者我要写书评

暂无评论

UAV Target Tracking with Bandit-Based Data fusion 17th

UAV Target Tracking with Bandit-Based Data Fusion

引用

17th International conference on Combinatorial Optimization and applications, COCOA 2024

作者： Lv, Yang Fan, Guochao Li, Mengzhen Liu, Xiongjun Liu, Pengqing Zhang, Yapu Beijing Jinghang Computation and Communication Research Institute Beijing100074 China Institute of Operations Research and Information Engineering Beijing University of Technology Beijing100124 China

ISBN: (纸本)9789819644445

Unmanned Aerial Vehicles have emerged as the optimal solution for target tracking due to their low cost and high maneuverability. We study the problem of target tracking in partially observable adversarial environments. Building on previous research, we develop a data fusion algorithm to optimize target tracking. To enable a single UAV to track a hard-to-observe target with limited sensor capabilities, we construct a target environment tracking model along with its corresponding reward function. In the algorithm design, we incorporate the Exp4-IX algorithm from the framework of an adversarial multi-armed bandit with advice, and we prove that the regret bound of this algorithm exhibits sub-linear growth. In numerical experiments, the Exp4-IX algorithm integrates the Previous Position algorithm, Particle Filtering algorithm, and Trajectory Fitting algorithm, and is benchmarked against the Average fusion algorithm. The results demonstrate its effectiveness in online fusion for smooth trajectory scenarios. This integration allows the UAV to predict the target’s position with greater accuracy compared to other algorithms. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Aircraft 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：