Learning Semantic Scene Models From Observing Activity in Visual Surveillance

Makris, Dimitrios; Ellis, Tim

doi:10.1109/tsmcb.2005.846652

Cited by 226 publications

(170 citation statements)

References 18 publications

Supporting

Mentioning

166

Contrasting

Unclassified

Order By: Relevance

“…As training progresses, routes may be merged or split according to maximum separation distances. In later work, the authors improved the learning and modelling of entry and exit regions using 2-D Gaussian mixture models, and detected unusual trajectories using hidden Markov models (HMMs) [33]. A key contribution of the algorithm is the learning of a scene model that describes semantically important spatial regions in the scene.…”

Section: Trajectory-based Methods For Unusual Behaviour Detectionmentioning

confidence: 99%

“…Like Makris and Ellis [32,33], prototype paths are learned by presenting training trajectories in sequence and updating the parameters of the matching prototype. Trajectories are then used to learn qualitative event sequences, where an event refers to a spatial interaction between two objects as defined by relative position and direction of motion (e.g.,…”

Section: Trajectory-based Methods For Unusual Behaviour Detectionmentioning

confidence: 99%

“…In their informal survey of four UK installations, Dee and Velastin reported screen to camera ratios from 1:4 to 1:30, and operator to screen ratios as high as 1:16 [12]. As the number of security cameras increases, information overload makes the task of detecting occurrences of suspicious behaviour increasingly difficult, adding to other confounding factors such as human fatigue and boredom [12,33]. These conditions make surveillance very challenging in large installations such as airports.…”

Section: Motivationmentioning

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

109

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: Trajectory-based Methods For Unusual Behaviour Detectionmentioning

confidence: 99%

Section: Trajectory-based Methods For Unusual Behaviour Detectionmentioning

confidence: 99%

Section: Motivationmentioning

confidence: 99%

See 1 more Smart Citation

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

Tung

Zelek

Clausi

2011

Image and Vision Computing

109

View full text Add to dashboard Cite

show abstract

“…Janoos et al [9] used a visual analytics approach to learn models of pedestrian motion patterns from video surveillance data, in order to distinguish typical from unusual behavior in order to flag security breaches in outdoor environments. Their semi-supervised learning approach in which users interact with video stream data improves upon the standard unsupervised learning schemes that are typically used in these scenarios (see for example [13]) allowing personnel to better train the models used for anomaly detection. The patterns encountered are fairly straightforward to visualize: motion trajectories of pedestrians visualized as flow fields.…”

Section: Related Workmentioning

confidence: 99%

“…The second rule holds for white HS grads that have the marital status 'Married_civ_spouse'. The third rule holds for whites working in the private sector, who have the minimum education level of Bachelors (13). The last rule accepts people whose marital status is 'Married_civ_spouse' and work as an executive manager.…”

Section: Census Datasetmentioning

confidence: 99%

Model-driven Visual Analytics

Garg

Nam

Ramakrishnan

et al. 2008

2008 IEEE Symposium on Visual Analytics Science and Technology

View full text Add to dashboard Cite

We describe a Visual Analytics (VA) infrastructure, rooted on techniques in machine learning and logic-based deductive reasoning that will assist analysts to make sense of large, complex data sets by facilitating the generation and validation of models representing relationships in the data. We use Logic Programming (LP) as the underlying computing machinery to encode the relations as rules and facts and compute with them. A unique aspect of our approach is that the LP rules are automatically learned, using Inductive Logic Programming, from examples of data that the analyst deems interesting when viewing the data in the highdimensional visualization interface. Using this system, analysts will be able to construct models of arbitrary relationships in the data, explore the data for scenarios that fit the model, refine the model if necessary, and query the model to automatically analyze incoming (future) data exhibiting the encoded relationships. In other words it will support both model-driven data exploration, as well as data-driven model evolution. More importantly, by basing the construction of models on techniques from machine learning and logic-based deduction, the VA process will be both flexible in terms of modeling arbitrary, user-driven relationships in the data as well as readily scale across different data domains. INTRODUCTIONModern day enterprises, be they commerce, government, science, engineering or medical, have to cope with voluminous amounts of data. Effective decision making based on large, dynamic datasets with many parameters requires a conceptual high-level understanding of the data. Acquiring such an understanding is a difficult problem, especially in the presence of incomplete, inconsistent, and noisy data acquired from disparate real-world sources.To make progress on this problem one must draw on the complementary strengths of computing machinery and human insight. Recognizing this promising human-computer synergy, Visual Analytics (VA), defined as the science of analytical reasoning facilitated by interactive visual interfaces [22], has become a major development thrust. It seeks to engage the fast visual circuitry of the human brain to quickly find relations in complex data, trigger creative thoughts, and use these elements to steer the underlying computational analysis processes towards the extraction of new information for further insight. VA has widespread applications, such as homeland security, the financial industry and internet security among others. Research papers and tools related to VA are beginning to emerge (see e.g.However, thus far the main emphasis in VA has been mostly on visualization, data management, and user interfaces (see e.g. [5] and other work mentioned in the following). As far as analytical computing goes, VA research has mainly focused on relatively low-level tasks, such as image [24] and video [12] analysis and database operations [21]. In today's VA systems, it is the human analyst who performs the actual reasoning and abstraction. Obviously this ty...

show abstract

A FPGA‐based experimentation system for designing, implementing, and evaluating real‐time video processing and analysis algorithms at undergraduate level

García

Guzmán‐Ramírez

2018

Comp Applic In Engineering

View full text Add to dashboard Cite

Real‐time digital video processing is an important area for students on computer and electronic engineering courses who have to learn how to design efficient applications required for industry, such as autonomous navigation, automatic detection and recognition of objects, autonomous process supervision, etc. Nevertheless, the computational complexity and large amount of data access within real‐time video processing have resulted in the need for alternative learning environments that facilitate this task. This paper aims to introduce a FPGA‐based system into traditional classrooms to promote experimentation when designing, implementing, and evaluating real‐time video processing and analysis algorithms at undergraduate level. With the aim of evaluating the system proposed in this paper, fourth‐year Computer and Electronic Engineering students performed various real‐time video processing and analysis experiments to effectively design robust algorithms. A qualitative research method identified positive student perceptions that might lead to improved technical skills.

show abstract

Learning Semantic Scene Models From Observing Activity in Visual Surveillance

Cited by 226 publications

References 18 publications

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

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

Model-driven Visual Analytics

A FPGA‐based experimentation system for designing, implementing, and evaluating real‐time video processing and analysis algorithms at undergraduate level

Contact Info

Product

Resources

About