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
Real-Time People Counting & Tracking
Detects, tracks and counts people crossing a virtual line
2-3 weeks build
Overview
A footfall counter for entrances, corridors and pedestrian crossings. YOLOv8 finds each person, a multi-object tracker such as ByteTrack or DeepSORT keeps a stable ID across frames, and a direction-aware line counts entries and exits once per track. Hourly counts feed a small dashboard, and the tracker is evaluated on the public MOT17 benchmark.
What makes it stand up
- 01Person detection with persistent track IDs
- 02ByteTrack and DeepSORT implemented and compared
- 03Direction-aware line and zone counting with no double counts
- 04Occupancy estimate from entries minus exits
- 05Tracking metrics such as MOTA and IDF1 reported on MOT17
Module breakdown
- 01
Detection
YOLOv8 person detector with confidence filtering.
- 02
Tracking
Motion and appearance association across frames.
- 03
Counting
Line crossing logic with direction and cooldown.
- 04
Dashboard
Streamlit charts of hourly footfall and occupancy.
- 05
Evaluation
MOT metrics scripts and ID-switch analysis.
After this, you will be able to
- Explain how Kalman filters and IoU matching link detections
- Defend your choice of tracker with MOT metrics
- Demo live counts on a corridor video
Technology stack
- Python
- YOLOv8
- ByteTrack
- OpenCV
- Streamlit
- 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