Building a multi-human bodies detection at different distances based on RCNN and faster RCNN techniques

The detection of humans bodies in surveillance systems is very important due to its wide applications, and therefore the researchers paid great attention to human detection at close distances and did not focus on the different distances in the detection. In this paper, the focus is on human detectio...

Full description

Saved in:
Bibliographic Details
Main Authors: Qetheth, Majed Kamil, Al-Zuky, Ali A. D., Hamza, B. Hadi
Format: Conference Proceeding
Language:English
Subjects:
Human beings
Surveillance systems
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The detection of humans bodies in surveillance systems is very important due to its wide applications, and therefore the researchers paid great attention to human detection at close distances and did not focus on the different distances in the detection. In this paper, the focus is on human detection at different distances and the effect of the difference in distances on the detection quality. Using faster RCNN and RCNN techniques, 400 images of a group of people at different distances were used in the training, and promising results were obtained, as 100% high-quality detection was achieved up to a distance of 60m using the faster RCNN technique, and by 100% up to a distance of 35m using the RCNN technique.
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0195999