HIERARCHICAL FILTERED MOTION FOR ACTION RECOGNITION IN CROWDED VIDEOS
Rs4,500.00
10000 in stock
SupportDescription
ABSTRACT:
In this paper, we propose an efficient hierarchical filtering technique to extract motion
information and reduce the distracting motions that are caused by the background moving
objects. Initially we segment the person from the video. In this paper, we detect the 2-D Harris
corner detection, MHI calculation. These corner points are play as a feature values. Finally it will
classify by the GMM(Gaussian Mixture model). It will predict about the action.
Only logged in customers who have purchased this product may leave a review.
Reviews
There are no reviews yet.