INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
The average yearly death toll from acts of human
aggression worldwide is 7.9 per 10,000 individuals.
The majority of these acts of violence against
people occur suddenly or in remote places.One of
the most interesting and difficult study areas in
computer vision is violence recognition. Finding
violence using surveillance cameras in public and
private spaces is one of its unique uses. We demand
that these violent incidents be immediately under
control. They must conduct a thorough search for
automated violence detection systems because
human operators are required to monitor the
surveillance video screen, which frequently results
in mistakes and neglects to identify the occurrence
of unexpected events. One of the main obstacles to
halting these activities is the information delay in
this case. In this work, the detecting technique is
employed to thrive on this issue. One of the best
computer vision algorithms is the one that uses
CCTV to detect moving things. These days, CCTV
cameras are installed on every street and are quite
useful for case solving. Certain deep learning
algorithms are applied in computer vision to
anticipate and identify actions and attributes in
videos. When police arrive at dangerous locations
in real time, they analyse CCTV footage and begin
an investigation before moving further. The
purpose of this study is to consciously identify
violent crimes seen on CCTV. Several uses for
gathered video features are made possible by the
use of computer vision and machine learning
techniques, one of which is safety monitoring. The
effectiveness of violent event detection is
determined by how accurate and efficient it is. We
describe a unique architecture for video
surveillance camera-based violence detection in
this study. The Yolo v8 models identify the usage
of weapons in the incident, as well as the violent
act. These deep learning models constitute the basis
of the work and are utilised to create a video
detection system. Real-time software or an
application programming interface (API) can be
created using this concept. According to the study's
findings, the suggested model has a 74% accuracy
Keywords:
Closed-circuit television (CCTV), Human violence, deep learning, Machine learning, Transfer learning.
Cite Article:
"Transformative solution for violence identification", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.9, Issue 4, page no.f605-f612, April-2024, Available :http://www.ijnrd.org/papers/IJNRD2404574.pdf
Downloads:
00025
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn