Motion Pattern Extraction and Event Detection for Automatic Visual Surveillance

Benabbas, Yassine; Ihaddadene, Nacim; Djeraba, Chabane

doi:10.1155/2011/163682

Cited by 63 publications

(48 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to our method, particle advection methods have been shown successful to handle dense videos [ 21,24,2,15]. However, some of these methods were designed to detect local anomalies [24,15] and thus are not suited to recover long-range MPs.…”

Section: (A) and (D)mentioning

confidence: 93%

“…Conventional surveillance system may fail for high density of objects, regarding both accuracy and computation. We can leverage the results of crowd behavior analysis to crowd flux statistics and congestion analysis [20], [21], anomaly detection and alarming [11]- [13], [22], etc.…”

Section: A Real-world Applicationsmentioning

confidence: 99%

“…Optical flow is robust to multiple and simultaneous camera and object motions, and it is widely used in crowd motion detection and segmentation [4], [19]- [21], [53], [54]. However, optical flow does not capture long-range temporal dependencies, and can not represent spatial and temporal properties of a flow.…”

Section: A Flow-based Featuresmentioning

confidence: 99%

“…2(c) and (d)) since each pixel is assigned only one motion label. Solmaz et al [21] use particles to recognize among five crowd behaviors based on the eigenvalues of a flow-based Jacobian matrix. It is not clear though how this method can recover individual MPs, especially if their shape differs from the five predefined behaviors.…”

Section: (A) and (D)mentioning

confidence: 99%

“…Motion patterns learning is important in automated visual surveillance [5], [6], [21]. In crowded scene analysis, it is highly desirable to analyze the motion patterns and obtain some high-level interpretation.…”

Section: Crowd Motion Pattern Segmentationmentioning

confidence: 99%

See 4 more Smart Citations

Crowded Scene Analysis: A Survey

Chang

Wang

et al. 2015

IEEE Trans. Circuits Syst. Video Technol.

436

201

View full text Add to dashboard Cite

Abstract-Automated scene analysis has been a topic of great interest in computer vision and cognitive science. Recently, with the growth of crowd phenomena in the real world, crowded scene analysis has attracted much attention. However, the visual occlusions and ambiguities in crowded scenes, as well as the complex behaviors and scene semantics, make the analysis a challenging task. In the past few years, an increasing number of works on crowded scene analysis have been reported, covering different aspects including crowd motion pattern learning, crowd behavior and activity analysis, and anomaly detection in crowds. This paper surveys the state-of-the-art techniques on this topic. We first provide the background knowledge and the available features related to crowded scenes. Then, existing models, popular algorithms, evaluation protocols, as well as system performance are provided corresponding to different aspects of crowded scene analysis. We also outline the available datasets for performance evaluation. Finally, some research problems and promising future directions are presented with discussions.

show abstract