Dynamic background modeling using deep learning autoencoder network

被引:18
作者
Gracewell, Jeffin [1 ]
John, Mala [1 ]
机构
[1] Madras Inst Technol, Dept Elect Engn, Chennai, Tamil Nadu, India
关键词
Background modeling; Background subtraction; Deep learning; Foreground extraction; Intruder detection; Unattended object detection; Visual surveillance; NEURAL-NETWORK; SUBTRACTION;
D O I
10.1007/s11042-019-7411-0
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Background modeling is a major prerequisite for a variety of multimedia applications like video surveillance, traffic monitoring, etc. Numerous approaches have been proposed for the same over the past few decades. However, the need for real time artificial intelligent based low cost approach still exists. Moreover, few recently proposed efficient approaches are not validated on the basis of some of the challenging applications in which they may fail in its efficiency when tested. In this paper, an efficient deep learning technique based on autoencoder network is used for modeling the background. The background model generated herein is obtained by training the incoming frames of the surveillance video with the deep learning network in an unsupervised manner. In order to optimize the weights of the network, greedy layer wise pre-training approach is used initially and the fine tuning of the network is done using conjugate gradient based back propagation algorithm. The performance of the algorithm is validated based on the application of unattended object detection in a dynamic environment. Comprehensive assessment of the proposed method using CDNET 2014 dataset and other datasets demonstrates the efficiency of the technique in background modeling.
引用
收藏
页码:4639 / 4659
页数:21
相关论文
共 48 条
[1]  
[Anonymous], EUR S ART NEUR NETW
[2]  
[Anonymous], IEEE INT WORKSH PETS
[3]  
[Anonymous], 2000, P 4 AS C COMP VIS SI
[4]   A deep convolutional neural network for video sequence background subtraction [J].
Babaee, Mohammadreza ;
Duc Tung Dinh ;
Rigoll, Gerhard .
PATTERN RECOGNITION, 2018, 76 :635-649
[5]   ViBe: A Universal Background Subtraction Algorithm for Video Sequences [J].
Barnich, Olivier ;
Van Droogenbroeck, Marc .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2011, 20 (06) :1709-1724
[6]   Bayesian foreground and shadow detection in uncertain frame rate surveillance videos [J].
Benedek, Csaba ;
Sziranyi, Tamas .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2008, 17 (04) :608-621
[7]   Comparative study of background subtraction algorithms [J].
Benezeth, Yannick ;
Jodoin, Pierre-Marc ;
Emile, Bruno ;
Laurent, Helene ;
Rosenberger, Christophe .
JOURNAL OF ELECTRONIC IMAGING, 2010, 19 (03)
[8]   Detection of object abandonment using temporal logic [J].
Bhargava, Medha ;
Chen, Chia-Chih ;
Ryoo, M. S. ;
Aggarwal, J. K. .
MACHINE VISION AND APPLICATIONS, 2009, 20 (05) :271-281
[9]   CONJUGATE-GRADIENT ALGORITHM FOR EFFICIENT TRAINING OF ARTIFICIAL NEURAL NETWORKS [J].
CHARALAMBOUS, C .
IEE PROCEEDINGS-G CIRCUITS DEVICES AND SYSTEMS, 1992, 139 (03) :301-310
[10]   Neural network approach to background Modeling for video object segmentation [J].
Culibrk, Dubravko ;
Marques, Oge ;
Socek, Daniel ;
Kalva, Hari ;
Furht, Borko .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2007, 18 (06) :1614-1627