Publication Date: 2023/02/02
Abstract: Many security and event management agencies throughout the world are beginning to understand the significance of crowd surveillance as public safety concerns increase. These organisations can avert any unforeseen mishaps or problems by estimating crowd dynamics. The goal of this research is to develop a system that can more effectively monitor crowds utilising Support Vector Machine (SVM) classifiers and Histogram of Oriented Gradients (HOG) features. According to our needs, we can interface two or more cameras to count the number of individuals in the input video of the cameras and to identify their locations in 3D space. This provides a sense of the density.
Keywords: No Keywords Available
DOI: https://doi.org/10.5281/zenodo.7599212
PDF: https://ijirst.demo4.arinfotech.co/assets/upload/files/IJISRT23JAN055_(1).pdf
REFERENCES