English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In crowded scenes, detection and localization of abnormal behaviors ischallenging in that high-density people make object segmentation and trackingextremely difficult. We associate the optical flows of multiple frames tocapture short-term trajectories and introduce the histogram-based shapedescriptor referred to as shape contexts to describe such short-termtrajectories. Furthermore, we propose a K-NN similarity-based statistical modelto detect anomalies over time and space, which is an unsupervised one-classlearning algorithm requiring no clustering nor any prior assumption. Firstly,we retrieve the K-NN samples from the training set in regard to the testingsample, and then use the similarities between every pair of the K-NN samples toconstruct a Gaussian model. Finally, the probabilities of the similarities fromthe testing sample to the K-NN samples under the Gaussian model are calculatedin the form of a joint probability. Abnormal events can be detected by judgingwhether the joint probability is below predefined thresholds in terms of timeand space, separately. Such a scheme can adapt to the whole scene, since theprobability computed as such is not affected by motion distortions arising fromperspective distortion. We conduct experiments on real-world surveillancevideos, and the results demonstrate that the proposed method can reliablydetect and locate the abnormal events in the video sequences, outperforming thestate-of-the-art approaches.

Anomaly Detection and Localization in Crowded Scenes by Motion-field Shape Description and Similarity-based Statistical Learning