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

The problem of automated crowd segmentation and counting has garneredsignificant interest in the field of video surveillance. This paper proposes anovel scene invariant crowd segmentation and counting algorithm designed withhigh accuracy yet low computational complexity in mind, which is key forwidespread industrial adoption. A novel low-complexity, scale-normalizedfeature called Histogram of Moving Gradients (HoMG) is introduced for highlyeffective spatiotemporal representation of individuals and crowds within avideo. Real-time crowd segmentation is achieved via boosted cascade of weakclassifiers based on sliding-window HoMG features, while linear SVM regressionof crowd-region HoMG features is employed for real-time crowd counting.Experimental results using multi-camera crowd datasets show that the proposedalgorithm significantly outperform state-of-the-art crowd counting algorithms,as well as achieve very promising crowd segmentation results, thusdemonstrating the efficacy of the proposed method for highly-accurate,real-time video-driven crowd analysis.

Scene Invariant Crowd Segmentation and Counting Using Scale-Normalized Histogram of Moving Gradients (HoMG)