Filters








549 Hits in 7.0 sec

Real-time Classification from Short Event-Camera Streams using Input-filtering Neural ODEs [article]

Giorgio Giannone, Asha Anoosheh, Alessio Quaglino, Pierluca D'Oro, Marco Gallieri, Jonathan Masci
2020 arXiv   pre-print
This sequence is used as the input for a novel asynchronous RNN-like architecture, the Input-filtering Neural ODEs (INODE). This is inspired by the dynamical systems and filtering literature.  ...  In this work, we instead propose to directly use events from a DVS camera, a stream of intensity changes and their spatial coordinates.  ...  Acknoledgements The authors are grateful to Christian Osendorfer for his valuable input and feedback and to everyone at NNAISENSE for contributing to an inspiring R&D environment.  ... 
arXiv:2004.03156v1 fatcat:spus7jl5wbhjxkfwio3ce723eq

Deep Sensing of Urban Waterlogging [article]

Shi-Wei Lo, Jyh-Horng Wu, Jo-Yu Chang, Chien-Hao Tseng, Meng-Wei Lin, Fang-Pang Lin
2021 arXiv   pre-print
The use of an efficient large-scale waterlogging sensing and information system can provide valuable real-time disaster information to facilitate disaster management and enhance awareness of the general  ...  The use of a deep sensing system in the monsoon season in Taiwan was demonstrated, and waterlogging events were predicted on the island-wide scale.  ...  ACKNOWLEDGMENT We are indebted to Water Resources Agency (WRA) and Directorate General of Highways (DGH) in Taiwan for their video streaming.  ... 
arXiv:2103.05927v3 fatcat:7y7l2lxnxjez7jtozitvdxxlpu

Deep Sensing of Urban Waterlogging

Shi-Wei Lo, Jyh-Horng Wu, Jo-Yu Chang, Chien-Hao Tseng, Meng-Wei Lin, Fang-Pang Lin
2021 IEEE Access  
The use of an efficient large-scale waterlogging sensing and information system can provide valuable near real-time disaster information to facilitate disaster management and enhance awareness of the general  ...  The use of a deep sensing system in the monsoon season in Taiwan was demonstrated, and waterlogging events were predicted on the island-wide scale.  ...  ACKNOWLEDGMENT The authors are indebted to Water Resources Agency (WRA) and Directorate General of Highways (DGH) in Taiwan for their video streaming.  ... 
doi:10.1109/access.2021.3111623 fatcat:vrh3cwtwujcr5pkrsiccqk5sry

Anomaly Detection in Residential Video Surveillance on Edge Devices in IoT Framework [article]

Mayur R. Parate, Kishor M. Bhurchandi, Ashwin G. Kothari
2021 arXiv   pre-print
The experimental results indicate the proposed method is feasible and achieves satisfactory results in real-life scenarios.  ...  Therefore, we propose anomaly detection for intelligent surveillance using CPU-only edge devices. A modular framework to capture object-level inferences and tracking is developed.  ...  Hardware accelerators like, Movidius Neural Compute Stick (MNCS) are very useful to achieve higher processing speed for real-time applications.  ... 
arXiv:2107.04767v2 fatcat:xnwbgcxd7zfq7epjx362t7mewi

ReActNet: Temporal Localization of Repetitive Activities in Real-World Videos [article]

Giorgos Karvounas, Iason Oikonomidis, Antonis Argyros
2019 arXiv   pre-print
These distances are computed on frame representations obtained with a convolutional neural network.  ...  On top of this representation, we design, implement and evaluate ReActNet, a lightweight convolutional neural network that classifies a given frame as belonging (or not) to a repetitive video segment.  ...  From a prac- pose the use of Short Term Fourier Transform (STFT) on tical point of view, many real-world applications such as the volume of the input video.  ... 
arXiv:1910.06096v1 fatcat:vkp43gxzpzhyxjiuzfhzbbfyoe

Automated Event Detection and Classification in Soccer: The Potential of Using Multiple Modalities

Olav Andre Nergård Rongved, Markus Stige, Steven Alexander Hicks, Vajira Lasantha Thambawita, Cise Midoglu, Evi Zouganeli, Dag Johansen, Michael Alexander Riegler, Pål Halvorsen
2021 Machine Learning and Knowledge Extraction  
We also analyze how the tolerance for delays in classification and spotting time, and the tolerance for prediction accuracy, influence the results.  ...  Our experiments show that using multiple modalities improves event detection performance for certain types of events.  ...  We also acknowledge the use of video data from Norsk Toppfotball (NTF). Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/make3040051 fatcat:zbsxxlp525dfheubyzprpfhyte

A Novel Approach for Robust Multi Human Action Recognition and Summarization based on 3D Convolutional Neural Networks [article]

Noor Almaadeed, Omar Elharrouss, Somaya Al-Maadeed, Ahmed Bouridane, Azeddine Beghdadi
2021 arXiv   pre-print
This is followed by an analysis of each sequence to detect and recognize the corresponding actions using 3D convolutional neural networks (3DCNNs).  ...  Action-based video summarization is performed by saving each person's action at each time of the video.  ...  In addition, the proposed approach can be improved to be used to recognize multiple human actions in real-time.  ... 
arXiv:1907.11272v4 fatcat:gxg77wheffdqdguo52zhwvkppi

Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review [article]

Abolfazl Razi, Xiwen Chen, Huayu Li, Brendan Russo, Yan Chen, Hongbin Yu
2022 arXiv   pre-print
estimation, event analysis, modeling and anomaly detection.  ...  This paper explores Deep Learning (DL) methods that are used or have the potential to be used for traffic video analysis, emphasizing driving safety for both Autonomous Vehicles (AVs) and human-operated  ...  Jason Pacheco, Larry Head, and Junsuo Qu from their thoughtful comments on this paper. Special thanks go to Greg Leeming from Intel for his insightful comments and continued support of this project.  ... 
arXiv:2203.10939v1 fatcat:h4o5zghhhfezncn7luy56yjusm

Exploiting Neuron and Synapse Filter Dynamics in Spatial Temporal Learning of Deep Spiking Neural Network [article]

Haowen Fang, Amar Shrestha, Ziyi Zhao, Qinru Qiu
2020 arXiv   pre-print
The recent discovered spatial-temporal information processing capability of bio-inspired Spiking neural networks (SNN) has enabled some interesting models and applications.  ...  Furthermore, spike timing plays an important role in information representation, but conventional rate-based spike coding models only consider spike trains statistically, and discard information carried  ...  Time Series Classification Our work also shows advantages in time series classification.  ... 
arXiv:2003.02944v2 fatcat:shl4cvgwjreqzpv3uwbbm3yvna

Communicative Representation Learning on Attributed Molecular Graphs

Ying Song, Shuangjia Zheng, Zhangming Niu, Zhang-hua Fu, Yutong Lu, Yuedong Yang
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
Graph neural networks, especially message passing neural network (MPNN) and its variants, have recently made remarkable achievements in molecular graph modeling.  ...  Herein, we propose a Communicative Message Passing Neural Network (CMPNN) to improve the molecular embedding by strengthening the message interactions between nodes and edges through a communicative kernel  ...  Time Series Classification Our work also shows advantages in time series classification.  ... 
doi:10.24963/ijcai.2020/388 dblp:conf/ijcai/FangSZQ20 fatcat:bqzmhpw3wfhejaw7ufycm4fatu

Enhanced Accuracy for Multiclass Mental Workload Detection Using Long Short-Term Memory for Brain–Computer Interface

Umer Asgher, Khurram Khalil, Muhammad Jawad Khan, Riaz Ahmad, Shahid Ikramullah Butt, Yasar Ayaz, Noman Naseer, Salman Nazir
2020 Frontiers in Neuroscience  
Real-time four-level MWL states are assessed using fNIRS system, and initial classification is performed using three strong machine learning (ML) techniques, support vector machine (SVM), k-nearest neighbor  ...  The brain activity signals are acquired using functional near-infrared spectroscopy (fNIRS) from the prefrontal cortex (PFC) region of the brain.  ...  It is a supervised experiment; participants are observed with a live stream video camera placed in front of them from an adjacent room.  ... 
doi:10.3389/fnins.2020.00584 pmid:32655353 pmcid:PMC7324788 fatcat:3vfdh5qjmfbx3hlo6a3n3i6pfa

Review on Vehicle Detection Technology for Unmanned Ground Vehicles

Qi Liu, Zirui Li, Shihua Yuan, Yuzheng Zhu, Xueyuan Li
2021 Sensors  
This article firstly introduces commonly used sensors for vehicle detection, lists their application scenarios and compares the strengths and weakness of different sensors.  ...  The advantages of the event camera are its high dynamic measurement range, sparse spatio-temporal data flow, short information transmission and processing time [48] , but its image pixel size is small  ...  Event Camera An overview of event camera technology can be found in [44] .  ... 
doi:10.3390/s21041354 pmid:33672976 fatcat:ammlsccxbbhgpkx6r5vod7ciuy

A Review of Object Visual Detection for Intelligent Vehicles

Sirin Kumar Singh, Department of Computer Science & Engineering, School of Engineering, Babu Banarasi Das University, Uttar Pradesh, India
2021 Journal of Informatics Electrical and Electronics Engineering (JIEEE)  
Our survey starts with a short presentation on the historical backdrop of profound learning and its agent device, in particular, Convolutional Neural Network (CNN) and region-based convolutional neural  ...  Post handling is the real commitment of the review paper for moving item identification issues.  ...  The proposed calculation at first takes the video outlines as info individually gauges the normal stream vectors from them which brings about Optical stream vectors.  ... 
doi:10.54060/jieee/002.02.008 fatcat:lajgh5n76vdavieakskubfczgy

AI and Deep Learning for Urban Computing [chapter]

Senzhang Wang, Jiannong Cao
2021 The Urban Book Series  
We first introduce the background, followed by listing key challenges from the perspective of computer science when AI techniques are applied.  ...  Thus, we briefly introduce the deep-learning models that are widely used in various urban-computing tasks.  ...  As the data are usually generated in real-time and new data keep on coming, the characteristic of velocity requires that the new streaming data can be processed in near real time.  ... 
doi:10.1007/978-981-15-8983-6_43 fatcat:uq7j3hvsvzfl5lq33omx64un3i

Machine and deep learning for sport-specific movement recognition: a systematic review of model development and performance

Emily E Cust, Alice J Sweeting, Kevin Ball, Sam Robertson
2018 Journal of Sports Sciences  
Twelve studies used a deep learning method as a form of Convolutional Neural Network algorithm and one study also adopted a Long Short Term Memory architecture in their model.  ...  inputs.  ...  Analysis of vision based systems to detect real time goal events in soccer videos. Applied Artificial Intelligence, 27(7),656-667.  ... 
doi:10.1080/02640414.2018.1521769 pmid:30307362 fatcat:h3flbavuivbilbo6ekwvmnjg6i
« Previous Showing results 1 — 15 out of 549 results