PopularMajor Project
Artificial Intelligence
Face Recognition Attendance System
Camera-based attendance with liveness detection and analytics
- Python
- OpenCV
- FaceNet
- Flask
- +2
₹4,900₹5,999
4.8/301 reviews
Artificial Intelligence · Major Project
Fire & Smoke Detection with Person Alerts
Spots fire, smoke and people in frame and raises an alarm
2-3 weeks build
Overview
A single YOLOv8 model trained on a public fire and smoke dataset such as D-Fire, combined with COCO person detection, watches a camera feed for flames, smoke and anyone nearby. When fire persists, the system sounds a local alarm and sends a Telegram message stating how many people are in view, so responders know whether the room is occupied.
What makes it stand up
- 01Fire and smoke detector trained on a public dataset
- 02Person count in frame included in every alert
- 03Persistence window so a flickering lamp does not trigger it
- 04Local buzzer plus Telegram bot notifications
- 05Hard-negative testing on sunsets, lamps and red clothing
Module breakdown
- 01
Detector
YOLOv8 trained for fire and smoke classes.
- 02
Person layer
COCO person detection counted per frame.
- 03
Decision logic
Confidence and duration thresholds before alarming.
- 04
Alerts
Buzzer output and Telegram bot messages with snapshots.
- 05
Monitor page
Flask live view with event history.
After this, you will be able to
- Explain why smoke is harder to detect than flame
- Discuss hard negatives and how you tested them
- Demo an alert from a fire video with people in view
Technology stack
- Python
- YOLOv8
- OpenCV
- Flask
- Telegram Bot API
- Level
- Major Project
- Domain
- Artificial Intelligence
- Build time
- 2-3 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support