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

This paper proposes a novel approach to create an automated visualsurveillance system which is very efficient in detecting and tracking movingobjects in a video captured by moving camera without any apriori informationabout the captured scene. Separating foreground from the background ischallenging job in videos captured by moving camera as both foreground andbackground information change in every consecutive frames of the imagesequence; thus a pseudo-motion is perceptive in background. In the proposedalgorithm, the pseudo-motion in background is estimated and compensated usingphase correlation of consecutive frames based on the principle of Fourier shifttheorem. Then a method is proposed to model an acting background from recenthistory of commonality of the current frame and the foreground is detected bythe differences between the background model and the current frame. Furtherexploiting the recent history of dissimilarities of the current frame, actualmoving objects are detected in the foreground. Next, a two-steppedmorphological operation is proposed to refine the object region for an optimumobject size. Each object is attributed by its centroid, dimension and threehighest peaks of its gray value histogram. Finally, each object is trackedusing Kalman filter based on its attributes. The major advantage of thisalgorithm over most of the existing object detection and tracking algorithms isthat, it does not require initialization of object position in the first frameor training on sample data to perform. Performance of the algorithm is testedon benchmark videos containing variable background and very satisfiable resultsis achieved. The performance of the algorithm is also comparable with some ofthe state-of-the-art algorithms for object detection and tracking.

An Efficient Approach for Object Detection and Tracking of Objects in a Video with Variable Background