A motion-based image processing system for detecting potentially dangerous situations in underground railway stations

Velastín, Sergio A.; Boghossian, B.; Vicencio-Silva, M.A.

doi:10.1016/j.trc.2006.05.006

Cited by 57 publications

(47 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Instead of segmenting the crowd in a set of pedestrians, Some approaches propose a global analysis of the motion of the crowd. In (Velastin et al, 2006), a model of expected motion is built from priors on circulation way for detecting wrong way moving person or suspect motionless people. The image motion is then estimated with optical flow techniques, coupled with an additional foreground extraction step.…”

Section: Related Workmentioning

confidence: 99%

An Unsupervised Learning Based Approach for Unexpected Event Detection

Luvison

Chateau

Sayd

et al. 2009

Proceedings of the Fourth International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

Abstract:This paper presents a generic unsupervised learning based solution to unexpected event detection from a static uncalibrated camera. The system can be represented into a probabilistic framework in which the detection is achieved by a likelihood based decision. We propose an original method to approximate the likelihood function using a sparse vector machine based model. This model is then used to detect efficiently unexpected events online. Moreover, features used are based on optical flow orientation within image blocks. The resulting application is able to learn automatically expected optical flow orientations from training video sequences and to detect unexpected orientations (corresponding to unexpected event) in a near real-time frame rate. Experiments show that the algorithm can be used in various applications like crowd or traffic event detection.

show abstract

Section: Related Workmentioning

confidence: 99%

An Unsupervised Learning Based Approach for Unexpected Event Detection

Luvison

Chateau

Sayd

et al. 2009

Proceedings of the Fourth International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

show abstract

“…Finally, the incoming and outgoing persons could be measured by counting the people data on the space time images of each moving direction. Velastin et al (2006) have developed a people detection system to detect important situations of interest to public transport operators. This has been done by using a monochrome video camera and motion detection board developed by the authors.…”

Section: Introductionmentioning

confidence: 99%

Real-time crowd density mapping using a novel sensory fusion model of infrared and visual systems

Yaseen

Al‐Habaibeh

et al. 2013

Safety Science

View full text Add to dashboard Cite

Abstract. Crowd dynamic management research has seen significant attention in recent years in research and industry in an attempt to improve safety level and management of large scale events and in large public places such as stadiums, theatres, railway stations, subways and other places where high flow of people at high densities is expected. Failure to detect the crowd behaviour at the right time could lead to unnecessary injuries and fatalities. Over the past decades there have been many incidents of crowd which caused major injuries and fatalities and lead to physical damages. Examples of crowd disasters occurred in past decades include the tragedy of Hillsborough football stadium at Sheffield where at least 93 football supporters have been killed and 400 injured in 1989 in Britain's worst-ever sporting disaster (BBC, 1989). Recently in Cambodia a pedestrians stampede during the Water Festival celebration resulted in 345 deaths and 400 injuries (BBC, 2010) and in 2011 at least 16 people were killed and 50 others were injured in a stampede in the northern Indian town of Haridwar (BBC, 2011). Such disasters could be avoided or losses reduced by using different technologies. Crowd simulation models have been found effective in the prediction of potential crowd hazards in critical situations and thus help in reducing fatalities. However, there is a need to combine the advancement in simulation with real time crowd characterisation such as the estimation of real time density in order to provide accurate prognosis in crowd behaviour and enhance crowd management and safety, particularly in mega event such as the Hajj. This paper addresses the use of novel sensory technology in order to estimate people's dynamic density during one of the Hajj activities. The ultimate goal is that real time accurate estimation of density in different areas within the crowd could help to improve the decision making process and provide more accurate prediction of the crowd dynamics. This paper investigates the use of infrared and visual cameras supported by auxiliary sensors and artificial intelligence to evaluate the accuracy in estimating crowd density in an open space during Muslims Pilgrimage to Makkah (Mecca).

show abstract

“…Screen doors or detection mats may be used in subways to prevent falling accidents; however, the cost of installation is very high, and the screen door is not appropriate for outdoor stations. A number of vision based surveillance systems have been proposed to confirm safe railway operation [1][2][3][4][5][6][7][8]. These systems are focused on measuring the level of crowding on the passenger platforms of train services.…”

Section: Introductionmentioning

confidence: 99%

“…If overcrowding is detected, the system will notify the station operators to take appropriate actions to prevent dangerous situations such as people falling off or being pushed onto the tracks [9][10][11][12][13][14]. Background subtraction is commonly used to locate passengers and thereby to estimate the crowd density [1][2][3][4][5]7] Edge information may be used to measure the regions occupied by passengers [1,4]. In addition, motion information may be utilized to detect and track moving objects in Ref.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

3D Vision-based Security Monitoring for Railroad Stations

Park

Lee

2010

Journal of the Optical Society of Korea

View full text Add to dashboard Cite

Increasing demands on the safety of public train services have led to the development of various types of security monitoring systems. Most of the surveillance systems are focused on the estimation of crowd level in the platform, thereby yielding too many false alarms. In this paper, we present a novel security monitoring system to detect critically dangerous situations such as when a passenger falls from the station platform, or when a passenger walks on the rail tracks. The method is composed of two stages of detecting dangerous situations. Objects falling over to the dangerous zone are detected by motion tracking. 3D depth information retrieved by the stereo vision is used to confirm fallen events. Experimental results show that virtually no error of either false positive or false negative is found while providing highly reliable detection performance. Since stereo matching is performed on a local image only when potentially dangerous situations are found; real-time operation is feasible without using dedicated hardware.

show abstract

A motion-based image processing system for detecting potentially dangerous situations in underground railway stations

Cited by 57 publications

References 11 publications

An Unsupervised Learning Based Approach for Unexpected Event Detection

An Unsupervised Learning Based Approach for Unexpected Event Detection

Real-time crowd density mapping using a novel sensory fusion model of infrared and visual systems

3D Vision-based Security Monitoring for Railroad Stations

Contact Info

Product

Resources

About