suspicious activity detection using deep learning
Budget: ₹600 – ₹1,500 INR
suspicious activity detection using deep learning
# Features
Real-Time Detection: Monitors live camera feeds and detects suspicious activities instantly.
Multi-Class Detection: Classifies activities such as harassment, fighting, vandalism, and abuse.
Alert System: Sends real-time notifications to authorities upon detecting suspicious activities.
Dataset-Based Training: Trained on UCF-Crime, AVENUE Video Dataset, and Violent-Flows for high accuracy.
---
Technologies Used
YOLOv8: For real-time object and people detection.
CNN-LSTM: For recognizing and classifying human activities.
Deep Learning Frameworks: TensorFlow, PyTorch.
Backend: Flask/Django (replace with your backend framework).
Frontend: Minimalistic web interface for real-time monitoring.
Alert System: Email (integrated with SMTP).
# Features
Real-Time Detection: Monitors live camera feeds and detects suspicious activities instantly.
Multi-Class Detection: Classifies activities such as harassment, fighting, vandalism, and abuse.
Alert System: Sends real-time notifications to authorities upon detecting suspicious activities.
Dataset-Based Training: Trained on UCF-Crime, AVENUE Video Dataset, and Violent-Flows for high accuracy.
---
Technologies Used
YOLOv8: For real-time object and people detection.
CNN-LSTM: For recognizing and classifying human activities.
Deep Learning Frameworks: TensorFlow, PyTorch.
Backend: Flask/Django (replace with your backend framework).
Frontend: Minimalistic web interface for real-time monitoring.
Alert System: Email (integrated with SMTP).