The big goal of the effort search out detect suspicious exercises in surveillance video. The approach constituted entails a number of stages of doubtful frame recognition and verification, in addition to suspicious activity-accompanying analysis of human motions inside a set of discovered doubtful frames. In the work presented attending, different types of features are derived to detect the suspicious endeavor. The technique includes GLCM feature ancestry, which includes looks like energy, prominence, contrast, deterioration, and homogeneity type of features, equal using Euclidian distance, and descriptor facial characteristics acquired by using Harris corner countenance and cosine similarity index estimation. The favorable suspicious activity labeling rate is examined, demonstrating a better accomplishment and time-saving technique when judging a sizable collection of following video.
Author(s) Details:
S. S. Gurav,
Sharad Institute of Technology, College of
Engineering, Yadrav, India.
B.
B. Godbole,
SKN
Korti, Pandharpur, India.
Please see the link here: https://stm.bookpi.org/RHST-V3/article/view/10761
No comments:
Post a Comment