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
Golf Posture Detection
Swing video analysed from pose keypoints with phase-by-phase feedback
3-4 weeks build
Overview
Upload a down-the-line or face-on swing video and the kit extracts pose keypoints frame by frame, segments the swing into address, top of backswing, impact and finish, and measures spine tilt, knee flex, head movement and lead-arm angle at each phase. Measurements are compared against reference ranges and shown as an annotated report.
What makes it stand up
- 01Frame-by-frame pose extraction from recorded swing video
- 02Swing phase segmentation from wrist trajectory and velocity
- 03Posture metrics for spine tilt, knee flex and head sway
- 04Side-by-side comparison with a reference swing
- 05Annotated key frames and a downloadable feedback report
Module breakdown
- 01
Video ingest
Upload, frame sampling and orientation handling.
- 02
Keypoint extraction
MediaPipe Pose with gap filling for occluded joints.
- 03
Phase detection
Wrist height and speed curves split the swing into phases.
- 04
Posture metrics
Angle and displacement measures checked against reference ranges.
- 05
Report
Streamlit view with annotated frames and plotted angle curves.
After this, you will be able to
- Explain how swing phases are detected without manual labels
- Defend the choice and limits of your reference ranges
- Demo analysis on a fresh swing clip recorded on a phone
Technology stack
- Python
- MediaPipe
- OpenCV
- scikit-learn
- Streamlit
- Level
- Major Project
- Domain
- Artificial Intelligence
- Build time
- 3-4 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