Real-time background subtraction for video surveillance: From research to reality

Hedayati, M.; Zaki, Wan Mimi Diyana Wan; Hussain, Aini

doi:10.1109/cspa.2010.5545277

Cited by 16 publications

(8 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent background subtraction algorithms focused on adapting to varying illumination conditions, geometry reconfiguration of background structure, and repetitive motion from clutter. Among others may include methods such as: (a) background subtraction methods for modelling a multiple modal background distribution [6], which use a Gaussian-based approach for real-time applications, (b) statistical background modelling [7], where an edge segmentbased statistical background modelling is used, and (c) universal background subtraction algorithm for video sequences [8], which stores a set of values taken in the past in the same location or in the neighbourhood.…”

Section: Motion Detectionmentioning

confidence: 99%

A Review on Outdoor and Indoor Automated Video Surveillance Systems

Kumar¹,

Bharathi²

2015

IJCA

View full text Add to dashboard Cite

Video surveillance is an important area of computer vision research, its applications including both outdoor and indoor automated surveillance systems. Detecting through video image processing is one of the most attractive alternative new technologies as it offers opportunities for performing substantially more complex tasks and providing more information than other sensors. Video Surveillance systems have as main goal to control the safety and the security of materials of which utilizing people. This paper provides an overview of various methods and techniques from the research area that address the problems of representation, recognition and learning of events, actions and activities of inhabitants from an environment.

show abstract

Section: Motion Detectionmentioning

confidence: 99%

A Review on Outdoor and Indoor Automated Video Surveillance Systems

Kumar¹,

Bharathi²

2015

IJCA

View full text Add to dashboard Cite

show abstract

“…A big number of BS methods have been proposed in recent years, trying to retrieve a background model using different approaches. Basically, classification is divided into two types of algorithms [11] parametric and non-parametric models. Parametric models represent a probability density function (pdf) parametrically.…”

Section: Related Workmentioning

confidence: 99%

“…Otherwise, the priority is the model that was built with previous versions. We should find the number of static pixels using the gradient direction mask, this is illustrated in (11) and (12).…”

Section: A 2 Ba: Solution Descriptionmentioning

confidence: 99%

A2Ba: Adaptive Background Modelling for Visual Aerial Surveillance Conditions

Sanchez-Fernandez¹,

Brunet²,

Senouci³

2015

EAI Endorsed Transactions on Industrial Networks and Intelligen

View full text Add to dashboard Cite

Background modelling algorithms are widely used to define a part of an image that most time remains stationary in a video. In surveillance tasks, this model helps to recognize those outlier objects in an area under monitoring. Set up a background model on mobile platforms (UAVs, intelligent cars, etc.) is a challenging task due camera motion when images are acquired. In this paper, we propose A 2 Ba, a robust method to support instabilities caused by aerial images fusing different information about image motion. We used frame difference as first approximation, then age of pixels is estimated. This latter gives us an invariability level of a pixel over time. Gradient direction of ages and an adaptive weight are used to reduce impact from camera motion on background modelling. We tested A 2 Ba simulating several conditions that impair aerial image acquisition such as intentional and unintentional camera motion. Experimental results show improved performance compared to baseline algorithms GMM and KDE.

show abstract

“…Recent background subtraction algorithms focused on adapting to varying illumination conditions, geometry reconfiguration of background structure, and repetitive motion from clutter. Among others may include methods such as: (a) background subtraction methods for modeling a multiple modal background distribution [12], which use a Gaussian− based approach for real− time applications, (b) statistical background modeling [13], where an edge segment− based statistical background modeling is used, and (c) universal background subtraction algorithm for video sequences [9], which stores a set of values taken in the past in the same location or in the neighborhood. In temporal differencing the subtraction of two or more consecutive frames followed by thresholding is applied.…”

Section: Motion Detectionmentioning

confidence: 99%

Intelligent Home Security System using illumination sensitive background model

2014

IJAERD

View full text Add to dashboard Cite

Home security has been a concern of worldwide. The need of security systems is considered as one of the important aspects of our modern life, people are using such systems to be aware about anything could be happen in their places like their houses when they are away, these system also let them feel more secure and that is what the people really need. As the technology is developing, rich home based security systems are implemented to ensure safety and security of. Video surveillance is an important area of computer vision research, its applications including both outdoor and indoor automated surveillance systems Home security system is an essential mean of protecting our home from illegal invasion. A conventional home security system consists of a Closed Circuit Television, CCTV and burglar alarm which can be replaced by computer based systems with the capability of smarter detection and alert system. In the context of smart home environments, the In-House Video Surveillance systems have as main goal to control the safety and the security of materials and of people living in a domestic environment. This paper provides a comparative approach between tracking learning and detection algorithm with illumination sensitive background model. Further a face recognition module is implemented which has the capability of identify intruder. On finding the intruder, the system sends an email on the owner mail id with images of the intruders so that the further action can be initiated.

show abstract

Real-time background subtraction for video surveillance: From research to reality

Cited by 16 publications

References 26 publications

A Review on Outdoor and Indoor Automated Video Surveillance Systems

A Review on Outdoor and Indoor Automated Video Surveillance Systems

A2Ba: Adaptive Background Modelling for Visual Aerial Surveillance Conditions

Intelligent Home Security System using illumination sensitive background model

Contact Info

Product

Resources

About