Filters








1,152 Hits in 10.5 sec

Anomaly Detection for Video Surveillance

Jagruti Tatiya, Riya Makhija, Mrunmay Pathe, Sarika Late, Prof. Mrunal Pathak
2021 International Journal of Scientific Research in Science and Technology  
In order to resolve the above issues, the proposed system plans to utilize neural networks.  ...  Many alternatives are there such as low-cost depth sensors, but they do have some drawbacks such as limited indoor use also with lower resolution and clamorous depth information from deep images, it becomes  ...  In 2017 , 2017 Weixin Luo, Wen Liu, recommended a Temporally coherent Sparse Coding (TSC) [7] in one of his paper, inspired by the ability to detect sparse coding-based anomaly, where the proposed system  ... 
doi:10.32628/ijsrsr21869 fatcat:bar42xi5t5dgfnqjbsupvbhf7u

Video Abnormal Event Detection Based on One-Class Neural Network

Xiangli Xia, Yang Gao, Bai Yuan Ding
2021 Computational Intelligence and Neuroscience  
As a remedy, a method based on one-class neural network (ONN) is designed for video anomaly detection.  ...  Existing methods usually design the two steps of video feature extraction and anomaly detection model establishment independently, which leads to the failure to achieve the optimal result.  ...  Inspired by the dual-stream neural network, the ONN model is trained separately on the local area blocks of the video frame and the optical flow graph to detect appearance anomalies and motion anomalies  ... 
doi:10.1155/2021/1955116 pmid:34621305 pmcid:PMC8492267 fatcat:7gbsthly6rdj7hpn3uqhxtjcza

MVIP 2020 Table of Contents

2020 2020 International Conference on Machine Vision and Image Processing (MVIP)  
A General Framework for Saliency Detection Methods 19. Removing mixture of Gaussian and Impulse noise of images using sparse coding 20.  ...  Improving Persian Digit Recognition by Combining Deep Neural Networks and SVM and Using PCA 3. Scale Equivariant CNNs with Scale Steerable Filters 4.  ... 
doi:10.1109/mvip49855.2020.9116904 fatcat:6v7rolxpkfh6jb2fg2bhd4ssuq

ABNORMAL EVENT DETECTION BY MACHINE VISION USING DEEP LEARNING

Akshara Alex, Ashi Sahu, Avni Tanwar, Nisha Rathi, Kavita Namdev
2020 International Journal of Engineering Applied Sciences and Technology  
In the proposed solution, the concept of basic deep neural network model has been widely adopted.  ...  If any one of the anomaly namely arrest, assault and abuse is occurred in a video, that anomaly is detected from specified frames of video.  ...  CNN Convolution Neural Network is a part of deep neural network to analyze and process any image.  ... 
doi:10.33564/ijeast.2020.v04i12.028 fatcat:2rvyjx65rnc2vem4cg5jjcttge

A Survey on Deep Learning Techniques for Video Anomaly Detection [article]

Jessie James P. Suarez, Prospero C. Naval Jr
2020 arXiv   pre-print
This survey, however, focuses on how Deep Learning has improved and provided more insights to the area of video anomaly detection.  ...  Anomaly detection in videos is a problem that has been studied for more than a decade. This area has piqued the interest of researchers due to its wide applicability.  ...  Scoring Sparse Coding-inspired Deep Neural Network 2019 Ionescu et. al. Classification Object-Centric Convolutional Autoencoders 2019 Xu et. al.  ... 
arXiv:2009.14146v1 fatcat:hktavfdu65gw3eek6famuirrbq

Bidirectional Retrospective Generation Adversarial Network for Anomaly Detection in Videos

Zhiwei Yang, Jing Liu, Peng Wu
2021 IEEE Access  
Sparse coding-based anomaly detection methods.  ...  Statistical models and sparse coding are common modeling methods that are used in traditional anomaly detection. Statistical model-based anomaly detection methods.  ... 
doi:10.1109/access.2021.3100678 fatcat:q6tizkldrvfmxjfx5nazxczui4

A Real-time Action Representation with Temporal Encoding and Deep Compression [article]

Kun Liu, Wu Liu, Huadong Ma, Mingkui Tan, Chuang Gan
2020 arXiv   pre-print
Deep neural networks have achieved remarkable success for video-based action recognition. However, most of existing approaches cannot be deployed in practice due to the high computational cost.  ...  Furthermore, we integrate deep compression techniques with T-C3D to further accelerate the deployment of models via reducing the size of the model.  ...  Action Recognition with Deep Neural Network.  ... 
arXiv:2006.09675v1 fatcat:pkk2n7ud4jcqniqj5idolxqn5y

Modeling Representation of Videos for Anomaly Detection using Deep Learning: A Review [article]

Yong Shean Chong, Yong Haur Tay
2015 arXiv   pre-print
Much research works have been done in finding the right representation to perform anomaly detection in video streams accurately with an acceptable false alarm rate.  ...  We address the most fundamental aspect for video anomaly detection, that is, video feature representation.  ...  Feature Extraction of Video using Deep Learning The problem of how to represent video sequences is the most fundamental problem in anomaly detection.  ... 
arXiv:1505.00523v1 fatcat:6kaxqtedwjedbajk7abs2vuita

Plug-and-Play Anomaly Detection with Expectation Maximization Filtering [article]

Muhammad Umar Karim Khan, Mishal Fatima, Chong-Min Kyung
2020 arXiv   pre-print
We propose a Core Anomaly-Detection (CAD) neural network which learns the motion behavior of objects in the scene with an unsupervised method.  ...  We believe our work is the first step towards using deep learning methods with autonomous plug-and-play smart cameras for crowd anomaly detection.  ...  [38] proposes temporallycoherent sparse coding and uses it with a recurrent neural network for anomaly detection.  ... 
arXiv:2006.08933v1 fatcat:jgrdevhvffebzgi7brasnbtsma

2020 Index IEEE Transactions on Circuits and Systems for Video Technology Vol. 30

2020 IEEE transactions on circuits and systems for video technology (Print)  
., +, TCSVT July 2020 2104-2113 Rate-Accuracy Trade-Off in Video Classification With Deep Convolutional Neural Networks.  ...  Fang, H., +, TCSVT Feb. 2020 442-456 Anomaly detection Attention-Driven Loss for Anomaly Detection in Video Surveillance.  ... 
doi:10.1109/tcsvt.2020.3043861 fatcat:s6z4wzp45vfflphgfcxh6x7npu

Deep-Anomaly: Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenes [article]

Mohammad Sabokrou, Mohsen Fayyaz, Mahmood Fathy, Zahra Moayedd, Reinhard klette
2017 arXiv   pre-print
The detection of abnormal behaviours in crowded scenes has to deal with many challenges. This paper presents an efficient method for detection and localization of anomalies in videos.  ...  Using fully convolutional neural networks (FCNs) and temporal data, a pre-trained supervised FCN is transferred into an unsupervised FCN ensuring the detection of (global) anomalies in scenes.  ...  Here we introduce and study a modified pre-trained convolutional neural network (CNN) for detecting and localizing anomalies.  ... 
arXiv:1609.00866v2 fatcat:gew3bo33gjfmhaxt36lsnqqj5q

Anomaly Detection in Moving Crowds through Spatiotemporal Autoencoding and Additional Attention

Biao Yang, Jinmeng Cao, Rongrong Ni, Ling Zou
2018 Advances in Multimedia  
We propose an anomaly detection approach by learning a generative model using deep neural network.  ...  Comparisons with state-of-the-art approaches indicate the superiority of our approach in anomaly detection.  ...  Despite the capability of deep neural network in detecting general anomaly based on a generative model, the network is easily influenced by the background.  ... 
doi:10.1155/2018/2087574 fatcat:owk64ocz5zd77nxy7rsx2sttdi

An Efficient Anomaly Detection System for Crowded Scenes Using Variational Autoencoders

Ming Xu, Xiaosheng Yu, Dongyue Chen, Chengdong Wu, Yang Jiang
2019 Applied Sciences  
As the deep neural networks make success in feature representation, the features extracted by a deep neural network represent the appearance and motion patterns in different scenes more specifically, comparing  ...  Anomaly detection in crowded scenes is an important and challenging part of the intelligent video surveillance system.  ...  [42] structured a deep convolutional neural network with the kernels trained by a sparse auto-encoder.  ... 
doi:10.3390/app9163337 fatcat:xxczp3visne6xdnwac7yhrgjlm

Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection [article]

Dong Gong, Lingqiao Liu, Vuong Le, Budhaditya Saha, Moussa Reda Mansour, Svetha Venkatesh, Anton van den Hengel
2019 arXiv   pre-print
Deep autoencoder has been extensively used for anomaly detection.  ...  It has been observed that sometimes the autoencoder "generalizes" so well that it can also reconstruct anomalies well, leading to the miss detection of anomalies.  ...  ) [10] , a 3D convolution AE method (AE-Conv3D) [45] , a temporally-coherent sparse coding method (TST) [26] , a stacked recurrent neural network (StackRNN) [26] and many video anomaly detection baselines  ... 
arXiv:1904.02639v2 fatcat:bki7ibp3fnccljokd7erhkyk44

Video Anomaly Detection for Smart Surveillance [article]

Sijie Zhu, Chen Chen, Waqas Sultani
2020 arXiv   pre-print
The goal of anomaly detection is to temporally or spatially localize the anomaly events in video sequences.  ...  Temporal localization (i.e. indicating the start and end frames of the anomaly event in a video) is referred to as frame-level detection.  ...  [17] explores the combination of sparse coding and RNN (Recurrent Neural Network).  ... 
arXiv:2004.00222v3 fatcat:bvbecuhjp5ha7a5nxdgyfz2jei
« Previous Showing results 1 — 15 out of 1,152 results