检索结果-内蒙古大学图书馆

2020 International Symposium on Automation, Information and Computing, ISAIC 2020

作者： Zhang, Hu Hu, Dong Qiu, Yingcan Jiangsu Province’s Key Lab of Image Procession and Image Communications Nanjing210003 China Education Ministry’s Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing210003 China Education Ministry’s Engineering Research Center of Ubiquitous Network and Heath Service Nanjing210003 China Nanjing University of Posts and Telecommunications Nanjing210003 China

A siamese network tracking algorithm based on hierarchical attention mechanism is proposed in this paper. In order to obtain more robust target tracking results, different layer features are fused effectively. In the process of extracting features, attention mechanism is used to recalibrate the feature map, and AdaBoost algorithm is used to weight the target feature map, which improves the reliability of the response map. Besides, the Inception module is also introduced which not only increases the width of the network and the adaptability of the siamese network to the scale, but also reduces the parameters and improves the speed of network training. Experimental results show that this method can effectively solve the impact of background clutter and improve the accuracy of tracking. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Experimental Evaluation of a Novel sensor-Based Sorting Approach Featuring Predictive Real-Time Multiobject Tracking

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2021年第2期68卷 1548-1559页

作者： Maier, Georg Pfaff, Florian Pieper, Christoph Gruna, Robin Noack, Benjamin Kruggel-Emden, Harald Langle, Thomas Hanebeck, Uwe D. Wirtz, Siegmar Scherer, Viktor Beyerer, Jurgen Fraunhofer IOSB D-76131 Karlsruhe Germany Inst Optron Syst Technol & Image Exploitat D-76131 Karlsruhe Germany Karlsruhe Inst Technol Intelligent Sensor Actuator Syst Lab D-76131 Karlsruhe Germany Ruhr Univ Bochum Dept Energy Plant Technol D-44801 Bochum Germany TU Berlin Mech Proc Engn & Solids Proc D-10623 Berlin Germany

sensor-based sorting is a machine vision application that has found industrial application in various fields. An accept-or-reject task is executed by separating a material stream into two fractions. Current systems use line-scanning sensors, which is convenient as the material is perceived during transportation. However, line-scanning sensors yield a single observation of each object and no information about their movement. Due to a delay between localization and separation, assumptions regarding the location and point in time for separation need to be made based on the prior localization. Hence, it is necessary to ensure that all objects are transported at uniform velocities. This is often a complex and costly solution. In this article, we propose a new method for reliably separating particles at nonuniform velocities. The problem is transferred from a mechanical to an algorithmic level. Our novel advanced image processing approach includes equipping the sorter with an area-scan camera in combination with a real-time multiobject tracking system, which enables predictions of the location of individual objects for separation. For the experimental validation of our approach, we present a modular sorting system, which allows comparing sorting results using a line-scan and area-scan camera. Results show that our approach performs reliable separation and hence increases sorting efficiency.

关键词： Automated visual inspection machine vision real-time multiobject tracking sensor-based sorting

来源：评论

学校读者我要写书评

暂无评论

Keys to accurate feature extraction using residual spiking neural networks

引用

NEUROMORPHIC COMPUTING AND ENGINEERING 2022年第4期2卷 044001-044001页

作者： Vicente-Sola, Alex Manna, Davide L. Kirkland, Paul Di Caterina, Gaetano Bihl, Trevor Univ Strathclyde Ctr Image & Signal Proc Elect & Elect Engn Neuromorph Sensor Signal Proc Lab Glasgow Scotland Air Force Res Lab Wright Patterson AFB OH USA

Spiking neural networks (SNNs) have become an interesting alternative to conventional artificial neural networks (ANN) thanks to their temporal processing capabilities and energy efficient implementations in neuromorphic hardware. However, the challenges involved in training SNNs have limited their performance in terms of accuracy and thus their applications. Improving learning algorithms and neural architectures for a more accurate feature extraction is therefore one of the current priorities in SNN research. In this paper we present a study on the key components of modern spiking architectures. We design a spiking version of the successful residual network architecture and provide an in-depth study on the possible implementations of spiking residual connections. This study shows how, depending on the use case, the optimal residual connection implementation may vary. Additionally, we empirically compare different techniques in image classification datasets taken from the best performing networks. Our results provide a state of the art guide to SNN design, which allows to make informed choices when trying to build the optimal visual feature extractor. Finally, our network outperforms previous SNN architectures in CIFAR-10 (94.14%) and CIFAR-100 (74.65%) datasets and matches the state of the art in DVS-CIFAR10 (72.98%), with less parameters than the previous state of the art and without the need for ANN-SNN conversion. Code available at: https://***/VicenteAlex/Spiking_ResNet.

关键词： feature extraction image classification neural networks neuromorphic residual network spiking

来源：评论

学校读者我要写书评

暂无评论

Spiking Neural Networks for event-based action recognition: A new task to understand their advantage

arXiv

引用

arXiv 2022年

作者： Vicente-Sola, Alex Manna, Davide L. Kirkland, Paul Di Caterina, Gaetano Bihl, Trevor Neuromorphic Sensor Signal Processing Lab Centre for Image and Signal Processing Electrical and Electronic Engineering University of Strathclyde Glasgow United Kingdom Air Force Research Laboratory Wright Patterson AFBOH United States

Spiking Neural Networks (SNN) are characterised by their unique temporal dynamics, but the properties and advantages of such computations are still not well understood. In order to provide answers, in this work we demonstrate how Spiking neurons can enable temporal feature extraction in feed-forward neural networks without the need for recurrent synapses, and how recurrent SNNs can achieve comparable results to LSTM with a smaller number of parameters. This shows how their bio-inspired computing principles can be successfully exploited beyond energy efficiency gains and evidences their differences with respect to conventional artificial neural networks. These results are obtained through a new task, DVS-Gesture-Chain (DVS-GC), which allows, for the first time, to evaluate the perception of temporal dependencies in a real event-based action recognition dataset. Our study proves how the widely used DVS Gesture benchmark can be solved by networks without temporal feature extraction when its events are accumulated in frames, unlike the new DVS-GC which demands an understanding of the order in which events happen. Furthermore, this setup allowed us to reveal the role of the leakage rate in spiking neurons for temporal processing tasks and demonstrated the benefits of"hard reset" mechanisms. Additionally, we also show how time-dependent weights and normalization can lead to understanding order by means of temporal attention. © 2022, CC BY-SA.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Simple and complex spiking neurons: perspectives and analysis in a simple STDP scenario

引用

NEUROMORPHIC COMPUTING AND ENGINEERING 2022年第4期2卷 044009-044009页

作者： Manna, Davide L. Vicente-Sola, Alex Kirkland, Paul Bihl, Trevor J. Di Caterina, Gaetano Univ Strathclyde Ctr Image & Signal Proc Elect & Elect Engn Neuromorph Sensor Signal Proc Lab Glasgow Scotland US Air Force Res Lab Wright Patterson AFB OH USA

Spiking neural networks (SNNs) are largely inspired by biology and neuroscience and leverage ideas and theories to create fast and efficient learning systems. Spiking neuron models are adopted as core processing units in neuromorphic systems because they enable event-based processing. Among many neuron models, the integrate-and-fire (I&F) models are often adopted, with the simple leaky I&F (LIF) being the most used. The reason for adopting such models is their efficiency and/or biological plausibility. Nevertheless, rigorous justification for adopting LIF over other neuron models for use in artificial learning systems has not yet been studied. This work considers various neuron models in the literature and then selects computational neuron models that are single-variable, efficient, and display different types of complexities. From this selection, we make a comparative study of three simple I&F neuron models, namely the LIF, the quadratic I&F (QIF) and the exponential I&F (EIF), to understand whether the use of more complex models increases the performance of the system and whether the choice of a neuron model can be directed by the task to be completed. Neuron models are tested within an SNN trained with spike-timing dependent plasticity (STDP) on a classification task on the N-MNIST and DVS gestures datasets. Experimental results reveal that more complex neurons manifest the same ability as simpler ones to achieve high levels of accuracy on a simple dataset (N-MNIST), albeit requiring comparably more hyper-parameter tuning. However, when the data possess richer spatio-temporal features, the QIF and EIF neuron models steadily achieve better results. This suggests that accurately selecting the model based on the richness of the feature spectrum of the data could improve the whole system's performance. Finally, the code implementing the spiking neurons in the SpykeTorch framework is made publicly available.

关键词： spiking neural networks STDP spiking neurons unsupervised learning temporal features

来源：评论

学校读者我要写书评

暂无评论

SIMPLE AND COMPLEX SPIKING NEURONS: PERSPECTIVES AND ANALYSIS IN A SIMPLE STDP SCENARIO

arXiv

引用

arXiv 2022年

作者： Manna, Davide Liberato Sola, Alex Vicente Kirkland, Paul Di Caterina, Gaetano Bihl, Trevor Neuromorphic Sensor Signal Processing Lab Centre for Image and Signal Processing Electrical and Electronic Engineering University of Strathclyde Glasgow United Kingdom Air Force Research Laboratory Wright Patterson AFB OH United States

Spiking neural networks (SNNs) are largely inspired by biology and neuroscience and leverage ideas and theories to create fast and efficient learning systems. Spiking neuron models are adopted as core processing units in neuromorphic systems because they enable event-based processing. Among many neuron models, the integrate-and-fire (I&F) models are often adopted, with the simple Leaky I&F (LIF) being the most used. The reason for adopting such models is their efficiency and/or biological plausibility. Nevertheless, rigorous justification for adopting LIF over other neuron models for use in artificial learning systems has not yet been studied. This work considers various neuron models in the literature and then selects computational neuron models that are single-variable, efficient, and display different types of complexities. From this selection, we make a comparative study of three simple I&F neuron models, namely the LIF, the Quadratic I&F (QIF) and the Exponential I&F (EIF), to understand whether the use of more complex models increases the performance of the system and whether the choice of a neuron model can be directed by the task to be completed. Neuron models are tested within an SNN trained with Spike-Timing Dependent Plasticity (STDP) on a classification task on the N-MNIST and DVS Gestures datasets. Experimental results reveal that more complex neurons manifest the same ability as simpler ones to achieve high levels of accuracy on a simple dataset (N-MNIST), albeit requiring comparably more hyper-parameter tuning. However, when the data possess richer Spatio-temporal features, the QIF and EIF neuron models steadily achieve better results. This suggests that accurately selecting the model based on the richness of the feature spectrum of the data could improve the whole system's performance. Finally, the code implementing the spiking neurons in the SpykeTorch framework is made publicly available. © 2022, CC BY-SA.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Earth System Data Cubes: Avenues for advancing Earth system research

引用

ENVIRONMENTAL DATA SCIENCE 2025年 3卷 e27-e27页

作者： Montero, David Kraemer, Guido Anghelea, Anca Aybar, Cesar Brandt, Gunnar Camps-Valls, Gustau Cremer, Felix Flik, Ida Gans, Fabian Habershon, Sarah Ji, Chaonan Kattenborn, Teja Martinez-Ferrer, Laura Martinuzzi, Francesco Reinhardt, Martin Soechting, Maximilian Teber, Khalil Mahecha, Miguel D. Univ Leipzig Remote Sensing Ctr Earth Syst Res RSC4Earth D-04103 Leipzig Germany Univ Leipzig Inst Earth Syst Sci & Remote Sensing D-04103 Leipzig Germany German Ctr Integrat Biodivers Res iDiv D-04103 Leipzig Germany European Space Agcy ESA European Space Res Inst ESRIN I-00044 Frascati Italy Univ Valencia Image Proc Lab Valencia 46980 Spain Water Competence Ctr CCA Lima 15086 Peru Brockmann Consult GmbH D-21029 Hamburg Germany Max Planck Inst Biogeochem Jena Germany Univ Freiburg Sensor Based Geoinformat D-79106 Freiburg Germany Univ Freiburg Ctr Scalable Data Analyt & Artificial Intelligence D-79106 Freiburg Germany Univ Leipzig Image & Signal Proc Grp D-04109 Leipzig Germany UFZ Helmholtz Ctr Environm Res Helmholtz Ctr Environm Res Magdeburg Germany

Recent advancements in Earth system science have been marked by the exponential increase in the availability of diverse, multivariate datasets characterised by moderate to high spatio-temporal resolutions. Earth System Data Cubes (ESDCs) have emerged as one suitable solution for transforming this flood of data into a simple yet robust data structure. ESDCs achieve this by organising data into an analysis-ready format aligned with a spatio-temporal grid, facilitating user-friendly analysis and diminishing the need for extensive technical data processing knowledge. Despite these significant benefits, the completion of the entire ESDC life cycle remains a challenging task. Obstacles are not only of a technical nature but also relate to domain-specific problems in Earth system research. There exist barriers to realising the full potential of data collections in light of novel cloud-based technologies, particularly in curating data tailored for specific application domains. These include transforming data to conform to a spatio-temporal grid with minimum distortions and managing complexities such as spatio-temporal autocorrelation issues. Addressing these challenges is pivotal for the effective application of Artificial Intelligence (AI) approaches. Furthermore, adhering to open science principles for data dissemination, reproducibility, visualisation, and reuse is crucial for fostering sustainable research. Overcoming these challenges offers a substantial opportunity to advance data-driven Earth system research, unlocking the full potential of an integrated, multidimensional view of Earth system processes. This is particularly true when such research is coupled with innovative research paradigms and technological progress.

关键词： Earth System Science Data Cubes Artificial Intelligence Data Life Cycle

来源：评论

学校读者我要写书评

暂无评论

Unsupervised spiking instance segmentation on event data using STDP: A preprint

arXiv

引用

arXiv 2021年

作者： Kirkland, Paul Manna, Davide L. Vicente-Sola, Alex Di Caterina, Gaetano Neuromorphic Sensor Signal Processing Lab Centre for Image and Signal Processing Electrical and Electronic Engineering University of Strathclyde Glasgow United Kingdom

Spiking Neural Networks (SNN) and the field of Neuromorphic Engineering has brought about a paradigm shift in how to approach Machine Learning (ML) and Computer Vision (CV) problem. This paradigm shift comes from the adaption of event-based sensing and processing. An event-based vision sensor allows for sparse and asynchronous events to be produced that are dynamically related to the scene. Allowing not only the spatial information but a high-fidelity of temporal information to be captured. Meanwhile avoiding the extra overhead and redundancy of conventional high frame rate approaches. However, with this change in paradigm, many techniques from traditional CV and ML are not applicable to these event-based spatial-temporal visual streams. As such a limited number of recognition, detection and segmentation approaches exist. In this paper, we present a novel approach that can perform instance segmentation using just the weights of a Spike Time Dependent Plasticity trained Spiking Convolutional Neural Network that was trained for object recognition. This exploits the spatial and temporal aspects of the network’s internal feature representations adding this new discriminative capability. We highlight the new capability by successfully transforming a single class unsupervised network for face detection into a multi-person face recognition and instance segmentation network. © 2021, CC BY.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Sentiment Recognition for Short Annotated GIFs Using Visual-Textual Fusion

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2020年第4期22卷 1098-1110页

作者： Liu, Tianliang Wan, Junwei Dai, Xiubin Liu, Feng You, Quanzeng Luo, Jiebo Nanjing Univ Posts & Telecommun Key Lab Broadband Wireless Commun & Sensor Networ Jiangsu Prov Key Lab Image Proc & Image CommunNa Minist EducJiangsu Prov Engn Res Ctr High Perfor Nanjing 210003 Peoples R China Microsoft Cloud A1 Comp Vis Team Redmond WA 98052 USA Univ Rochester Dept Comp Sci Rochester NY 14627 USA

With the rapid development of social media, visual sentiment analysis from image or video has become a hot spot in visual understanding researches. In this work, we propose an effective approach using visual and textual fusion for sentiment analysis of short GIF videos with textual descriptions. We extract both sequence-level and frame-level visual features for each given GIF video. Next, we build a visual sentiment classifier by using the extracted features. We also define a mapping function, which converts the sentiment probability from the classifier to a sentiment score used in our fusion function. At the same time, for the accompanied textual annotations, we employ the Synset forest to extract the sets of the meaningful sentiment words and utilize the SentiWordNet3.0 model to obtain the textual sentiment score. Then, we design a joint visual-textual sentiment score function weighted with visual sentiment component and textual sentiment one. To make the function more robust, we introduce a noticeable difference threshold to further process the fused sentiment score. Finally, we adopt a grid search technique to obtain relevant model hyper-parameters by optimizing a sentiment aware score function. Experimental results and analysis extensively demonstrate the effectiveness of the proposed sentiment recognition scheme on three benchmark datasets including T-GIF dataset, GSO-2016 dataset and Adjusted-GIFGIF dataset.

关键词： Sentiment analysis Visualization Feature extraction Streaming media Semantics Twitter GIFs Sentiment 3-D Convolution Convolutional Long-Short-Term-Memory SentiWordNet3 0 Grid Searching

来源：评论

学校读者我要写书评

暂无评论

Optimal feature subset deduction based on possibilistic feature quality classification and feature complementarity

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年 249卷

作者： Medhioub, Mouna Bouhamed, Sonda Ammar Kallel, Imene Khanfir Derbel, Nabil Kanoun, Olfa CRNS Lab Signals Syst aRtificial Intelligence NeTworkS Sfax Tunisia Univ Sfax Natl Sch Elect & Telecommun Sfax Sfax Technopole Sakiet Ezzit Sfax Tunisia Univ Sfax Natl Sch Engineers Sfax Control & Energy Management CEM Lab Sfax Tunisia IMT Atlantique Image & Informat Proc Dept iTi Technopole Brest Iroise F-83818 Nantes France Tech Univ Chemnitz Measurement & Sensor Technol Chemnitz Germany Natl Sch Elect & Telecommun Sfax Rd TunisTechnopole Sfax Sfax Tunisia

Data quality estimation has become an important research axis in applications when defining useful information is required. Determining useful information is an essential task in the learning process. One important aspect thereby is to find optimal and sufficient information that has a good quality and which is complimentary to improve the performance of the decision-making system. In this paper, a survey of data quality is operated in the possibilistic framework. The main objective of this work is the development of a possibilistic approach that aims to extract useful information from imperfect knowledge. The new method consists of two main steps, the classification of feature quality and the determination of the optimal feature subset. The optimal feature subset is deduced according to the feature classification technique and the feature complementarity. To show the performance of the proposed approach, the new method has been evaluated, firstly, on a synthetic dataset, and then on different benchmark databases. Later, the new method is evaluated on two real databases to gain a better insight into the performance of this method. Experiments showed the effectiveness of the proposed method in extracting useful information using the optimal feature subset. Experimental results illustrate significant accuracy rates compared with different earlier methods, especially when the system complexity increases.

关键词： Possibility distribution Useful data Feature classification Data quality Feature complementarity Optimal feature subset

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：