Hidden Markov Models for Optical Flow Analysis in Crowds

Andrade, E.L.; Bellows, Scott; Fisher, Robert B.

doi:10.1109/icpr.2006.621

Cited by 119 publications

(62 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, flow vectors are normally filtered based on a predefined threshold to reduce potential observation noise. Moreover, the extracted optical flow information is usually combined with a foreground mask so that only the vectors caused by foreground objects are considered, while all the flow vectors outside the foreground mask are set to zero [17]. Like foreground pixel-based representation, optical flow based representation avoids explicit tracking of individual objects.…”

Section: Pixel Based Representationmentioning

confidence: 99%

Exploring Behavior Analysis in Video Surveillance Applications

Taha¹,

Zayed²,

Khalifa³

et al. 2014

IJCA

View full text Add to dashboard Cite

Video surveillance is recently one of the most active research topics in computer vision. It has a wide spectrum of promising public safety and security applications. As the number of cameras exceeds the capability of human operators to monitor them, the traditional passive video surveillance is proving ineffective. Hence, converting to intelligent visual surveillance is inevitable. Intelligent visual surveillance aims to detect, recognize and track certain objects from image sequences automatically, and more generally to understand and describe object behaviors. Many researchers have contributed to the field of automated video surveillance through detection, classification, and tracking algorithms. Despite recent progress in computer vision and other related areas, there are still major technical challenges to be overcome before reliable automated video surveillance can be realized. Recently, the problem of analyzing behavior in videos has been the focus of several researchers' efforts. It aims to analyze and interpret individual behaviors and interactions between different objects found in the scene. Hence, obtaining a description of what is happening in a monitored area, and then taking appropriate action based on that interpretation. In this paper, we give a survey of behavior analysis work in video surveillance and compare the performance of the state-of-the-art algorithms on different datasets. Moreover, useful datasets are analyzed in order to provide help for initiating research projects.

show abstract

Section: Pixel Based Representationmentioning

confidence: 99%

Exploring Behavior Analysis in Video Surveillance Applications

Taha¹,

Zayed²,

Khalifa³

et al. 2014

IJCA

View full text Add to dashboard Cite

show abstract

“…The vehicle motion is detected and tracked over the frames using the Horn and Schunck optical flow method [5]. Andrade et al [43] developed a method for modeling normal behavior in order to detect abnormal events. This solution combines the optical flow vectors, Hidden Markov Models (HMM) [44], spectral clustering and principal component analysis for detecting crowd emergency scenarios.…”

Section: Real-time Motion Tracking Using Optical Flow On Multiple Gpusmentioning

confidence: 99%

Real-time motion tracking using optical flow on multiple GPUs

Mahmoudi¹,

Kierzynka²,

Manneback³

et al. 2014

Bulletin of the Polish Academy of Sciences: Technical Sciences

View full text Add to dashboard Cite

Abstract. Motion tracking algorithms are widely used in computer vision related research. However, the new video standards, especially those in high resolutions, cause that current implementations, even running on modern hardware, no longer meet the needs of real-time processing. To overcome this challenge several GPU (Graphics Processing Unit) computing approaches have recently been proposed. Although they present a great potential of a GPU platform, hardly any is able to process high definition video sequences efficiently. Thus, a need arose to develop a tool being able to address the outlined problem.In this paper we present software that implements optical flow motion tracking using the Lucas-Kanade algorithm. It is also integrated with the Harris corner detector and therefore the algorithm may perform sparse tracking, i.e. tracking of the meaningful pixels only. This allows to substantially lower the computational burden of the method. Moreover, both parts of the algorithm, i.e. corner selection and tracking, are implemented on GPU and, as a result, the software is immensely fast, allowing for real-time motion tracking on videos in Full HD or even 4K format. In order to deliver the highest performance, it also supports multiple GPU systems, where it scales up very well.

show abstract

“…Trajectories can also infer interactions between individuals (people separating, coming closer, fighting ...) (Blunsden et al, 2007). In (Andrade et al, 2006), the main components (extracted from a SVD decomposition) of crowd motion are learnt using a Hidden Markov Model (HMM). Other learning machines aim at classifying an entry between two classes which correspond well to the wanted system.…”

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

Hidden Markov Models for Optical Flow Analysis in Crowds

Abstract: Abstract

Cited by 119 publications

References 9 publications

Exploring Behavior Analysis in Video Surveillance Applications

Exploring Behavior Analysis in Video Surveillance Applications

Real-time motion tracking using optical flow on multiple GPUs

An Unsupervised Learning Based Approach for Unexpected Event Detection

Contact Info

Product

Resources

About