Tracker trees for unusual event detection

Nater, Fabian; Gräbner, Helmut; Jaeggli, Tobias; Gool, Luc Van

doi:10.1109/iccvw.2009.5457578

Cited by 16 publications

(9 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Similarly to most of our trackers (cf. [30]), GMMs are used for tracking and outlier detection, but with no hierarchical structure.…”

Section: Methodsmentioning

confidence: 99%

“…The root node tracker is a simple color-based blob tracker [28], whereas the person tracker (yellow) is based on a tracking-by-detection approach [29]. The body part trackers and the action trackers all rely on generative low-dimensional representations, as described in [30]. These trackers were trained in an offline procedure with approximately 3,000 images in which the different actions were segmented manually.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Beyond Novelty Detection: Incongruent Events, When General and Specific Classifiers Disagree

Weinshall

Zweig

Heřmanský

et al. 2012

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

Unexpected stimuli are a challenge to any machine learning algorithm. Here, we identify distinct types of unexpected events when general-level and specific-level classifiers give conflicting predictions. We define a formal framework for the representation and processing of incongruent events: Starting from the notion of label hierarchy, we show how partial order on labels can be deduced from such hierarchies. For each event, we compute its probability in different ways, based on adjacent levels in the label hierarchy. An incongruent event is an event where the probability computed based on some more specific level is much smaller than the probability computed based on some more general level, leading to conflicting predictions. Algorithms are derived to detect incongruent events from different types of hierarchies, different applications, and a variety of data types. We present promising results for the detection of novel visual and audio objects, and new patterns of motion in video. We also discuss the detection of Out-Of- Vocabulary words in speech recognition, and the detection of incongruent events in a multimodal audiovisual scenario.

show abstract

“…Similarly to most of our trackers (cf. [30]), GMMs are used for tracking and outlier detection, but with no hierarchical structure.…”

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Beyond Novelty Detection: Incongruent Events, When General and Specific Classifiers Disagree

Weinshall

Zweig

Heřmanský

et al. 2012

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In five of the six evaluated cases however, the annotation of ten frames vs. one frame only improves the performance marginally. We underline that the number of labelled training samples needed is in any case two or at least one order of magnitude smaller than what originally requested to update the activity tracker in [23].…”

Section: Activity Trackingmentioning

confidence: 98%

“…In the same way as in [23], we create a low dimensional model in order to describe the observed training data. To this end, silhouettes of a human person are extracted from the training video sequences and are represented on a three-dimensional manifold.…”

Section: Activity Tracking For Unusual Event Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Transferring activities: Updating human behavior analysis

Nater

Tommasi

Gräbner

et al. 2011

2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops)

Self Cite

View full text Add to dashboard Cite

One of the great open challenges in visual recognitionis the ability to cope with unexpected stimuli. In this work, we present a technique to interpret detected anomalies and update the existing knowledge of normal situations. The addressed context is the analysis of human behavior in indoor surveillance scenarios, where new activities might need to be learned, once the system is already in operation. Our approach is based on human tracking with multiple activity trackers. The main contribution is to integrate a learning stage, where labeled and unlabeled information is collected and analyzed. To this end we develop a new multiclass version of transfer learning which requires minimal human interaction but still provides semantic labels of the new classes. The activity model is then updated with the new activities. Experiments show promising results.

show abstract