Semi-supervised Learning for Anomalous Trajectory Detection

Sillito, Rowland R.; Fisher, Robert B.

doi:10.5244/c.22.103

Cited by 90 publications

(65 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Sillito and Fisher's work was described earlier in Section 2.1. The proposed method detects all unusual trajectories with 22% probability of false alarm, which is comparable to both Dee and Hogg's method [11] and Sillito and Fisher's method [47] (approximately 25% and 24%, respectively). …”

Section: Dee Andsupporting

confidence: 55%

“…The following chapter elaborates on the contributions of this thesis to the goal-based approach. Johnson and Hogg [25] Owens and Hunter [40] Stauffer and Grimson [48] Hu et al [19] Makris and Ellis [32,33] Fernyhough et al [14] Piciarelli and Foresti [41] Piciarelli et al [42] Junejo et al [26] Naftel and Khalid [39] Jiang et al [24] Sillito and Fisher [47] Dee and Hogg [11] Proposed Method…”

Section: Discussionmentioning

confidence: 99%

“…Sillito and Fisher proposed a semi-supervised method for learning normal trajectories and detecting unusual behaviour [47]. The greater the goal-directedness of a trajectory, the more likely it represents normal behaviour.…”

Section: Trajectory-based Methods For Unusual Behaviour Detectionmentioning

confidence: 99%

“…Manual editing of trajectories to correct tracking errors was not performed as in [9,10,11]. [47]. Sillito and Fisher's work was described earlier in Section 2.1.…”

Section: Dee Andmentioning

confidence: 99%

See 3 more Smart Citations

Goal-based trajectory analysis for unusual behaviour detection in intelligent surveillance

Tung

Zelek

Clausi

2011

Image and Vision Computing

108

View full text Add to dashboard Cite

Video surveillance systems are playing an increasing role in preventing and investigating crime, protecting public safety, and safeguarding national security. In a typical surveillance installation, a human operator has to constantly monitor a large array of video feeds for suspicious behaviour. As the number of cameras increases, information overload makes manual surveillance increasingly difficult, adding to other confounding factors like human fatigue and boredom.The objective of an intelligent vision-based surveillance system is to automate the monitoring and event detection components of surveillance, alerting the operator only when unusual behaviour or other events of interest are detected. While most traditional methods for trajectory-based unusual behaviour detection rely on low-level trajectory features, this thesis improves a recently introduced approach that makes use of higher-level features of intentionality. Individuals in a scene are modelled as intentional agents instead of simply objects. Unusual behaviour detection then becomes a task of determining whether an agent's trajectory is explicable in terms of learned spatial goals. The proposed method extends the original goal-based approach in three ways: first, the spatial scene structure is learned in a training phase; second, a region transition model is learned to describe normal movement patterns between spatial regions; and third, classification of trajectories in progress is performed in a probabilistic framework using particle filtering. Experimental validation on three published third-party datasets demonstrates the validity of the proposed approach.iii

show abstract

Section: Dee Andsupporting

confidence: 55%

Section: Discussionmentioning

confidence: 99%

Section: Trajectory-based Methods For Unusual Behaviour Detectionmentioning

confidence: 99%

“…Manual editing of trajectories to correct tracking errors was not performed as in [9,10,11]. [47]. Sillito and Fisher's work was described earlier in Section 2.1.…”

Section: Dee Andmentioning

confidence: 99%

See 2 more Smart Citations

Goal-based trajectory analysis for unusual behaviour detection in intelligent surveillance

Tung

Zelek

Clausi

2011

Image and Vision Computing

108

View full text Add to dashboard Cite

show abstract

“…Sillito and Fisher [61] formulate a method to harnesses human feedback on-the-fly for improving unusual event detection performance. Specifically, human approval is sought if a newly observed instance deviates statistically from the learned normal profile.…”

Section: Human In the Loopmentioning

confidence: 99%

Security and Surveillance

Gong

Loy

Xiang

2011

Visual Analysis of Humans

View full text Add to dashboard Cite

Human eyes are highly efficient devices for scanning through a large quantity of low-level visual sensory data and delivering selective information to one's brain for high-level semantic interpretation and gaining situational awareness. Over the last few decades, the computer vision community has endeavoured to bring about similar perceptual capabilities to artificial visual sensors. Substantial efforts have been made towards understanding static images of individual objects and the corresponding processes in the human visual system. This endeavour is intensified further by the need for understanding a massive quantity of video data, with the aim to comprehend multiple entities not only within a single image but also over time across multiple video frames for understanding their spatio-temporal relations. A significant application of video analysis and understanding is intelligent surveillance, which aims to interpret automatically human activity and detect unusual events that could pose a threat to public security and safety.

show abstract

Public Space Behavior Modeling With Video and Sensor Analytics

Ho¹,

Matthews²,

O’Gorman³

et al. 2012

Bell Labs Tech. J.

View full text Add to dashboard Cite

We present a review of technologies relevant to public space surveillance and describe a pilot study to explore the challenges. The general purpose of this study is to capture and analyze behavior patterns and anomalies of people behavior in a public space. On the capture side, we explore a small array of networked cameras as well as an ultrasonic sensor array for measuring the height of walking persons. After capture, video and ultrasound signals are analyzed and statistics calculated for such measurements, including the duration and speed of the trajectory of each tracked person, and a person's height which is a useful biometric feature for tracking the person across multiple, non-overlapping camera views. These statistics are first analyzed offline to determine the expected patterns of measured values over many captured events. Based on the expected patterns, anomalies can be detected as outliers in real time. Since this is a broad-based pilot study, conclusions relate to the effectiveness of the capture modalities and approaches investigated. We discuss how we use these findings to guide our future work. © 2012 Alcatel-Lucent. a proof-of-concept pilot study on observing people behavior in a public space using state-of-the-art equipment.In the pilot study, the primary experiment involved a small network of video cameras installed to monitor a laboratory hallway. Algorithms were developed to detect events like presence and movement of people and objects, recurrent presence and movement patterns of people over time, and the anomalies with respect to past statistics. Additional experiments were conducted to investigate the utility of a pair of ultrasonic sensors for height measurement. A person's

show abstract

Semi-supervised Learning for Anomalous Trajectory Detection

Cited by 90 publications

References 14 publications

Goal-based trajectory analysis for unusual behaviour detection in intelligent surveillance

Goal-based trajectory analysis for unusual behaviour detection in intelligent surveillance

Security and Surveillance

Public Space Behavior Modeling With Video and Sensor Analytics

Contact Info

Product

Resources

About