Intelligent Violence Detection: An AI Driven Approach for Enhanced Surveillance System

Author(s)	Ms. Ahilya Sanjay Sarnaik, Mr. Rohan Sunil Sardesai, Mr. Sarvesh Pratap Padwal, Mr. Akhilesh Ravindra Huddar, Ms. Komal Jadhav
Country	India
Abstract	Violence Alert System is an AI-powered surveillance system for real-time detection of violent attacks and threats. Through the use of advanced machine learning techniques, the system integrates human detection, violence recognition, and new weapon detection to enhance public safety. Real-time human detection is achieved with the use of Faster R-CNN architecture, with MobileNetV2 used for detecting violent behavior. Integration of weapon detection enhances threat analysis by detecting guns and knives in videos. The system gives real-time alert via Telegram, with the images being time-stamped with location details, thus enabling timely response by law enforcement agencies. Image and face detection enhancement using MTCNN enables more accurate identification, with Firebase Cloud Firestore enabling secure storage and retrieval of data. With the implementation of multi-layered threat assessment, the Violence Alert System offers an effective and scalable solution for active public security surveillance in public places, schools, and business segments.
Keywords	Violence Detection , Deep Learning, RCNN, YOLO , MobilenetV2
Field	Computer
Published In	Volume 7, Issue 3, May-June 2025
Published On	2025-05-10

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research