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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Human pose estimation is one of the key problems in computer vision that hasbeen studied in the recent years. The significance of human pose estimation isin the higher level tasks of understanding human actions applications such asrecognition of anomalous actions present in videos and many other relatedapplications. The human poses can be estimated by extracting silhouettes ofhumans as silhouettes are robust to variations and it gives the shapeinformation of the human body. Some common challenges include illuminationchanges, variation in environments, and variation in human appearances. Thusthere is a need for a robust method for human pose estimation. This paperpresents a study and analysis of approaches existing for silhouette extractionand proposes a robust technique for extracting human silhouettes in videosequences. Gaussian Mixture Model (GMM) A statistical approach is combined withHSV (Hue, Saturation and Value) color space model for a robust background modelthat is used for background subtraction to produce foreground blobs, calledhuman silhouettes. Morphological operations are then performed on foregroundblobs from background subtraction. The silhouettes obtained from this work canbe used in further tasks associated with human action interpretation andactivity processes like human action classification, human pose estimation andaction recognition or action interpretation.

Robust Statistical Approach for Extraction of Moving Human Silhouettes from Videos