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
Lane Detection for Self-Driving Cars
Classical Canny + Hough and a deep lane model, side by side
2-3 weeks build
Overview
Dashcam video is processed two ways: a classical pipeline of colour masking, Canny edges, a region of interest and Hough lines with temporal smoothing, and a segmentation network trained on a public lane dataset such as TuSimple. A Streamlit viewer overlays both, so you can show exactly where the hand-tuned method breaks and the learned one holds.
What makes it stand up
- 01Full classical pipeline with every intermediate stage visualised
- 02Deep lane segmentation trained on a public benchmark dataset
- 03Frame-to-frame smoothing so drawn lanes do not jitter
- 04Lane-centre offset and curvature estimate on each frame
- 05Side-by-side comparison on night, rain and curve clips
Module breakdown
- 01
Preprocessing
Colour thresholds, grayscale, blur and region of interest.
- 02
Classical lanes
Canny edges, Hough transform and line averaging.
- 03
Deep lanes
Segmentation network with training and inference scripts.
- 04
Geometry
Perspective warp, curvature and vehicle offset.
- 05
Viewer
Streamlit app comparing both methods on uploaded video.
After this, you will be able to
- Explain the Hough transform from edge points to lines
- Defend where classical methods fail and why
- Demo both detectors on your own dashcam clip
Technology stack
- Python
- OpenCV
- PyTorch
- NumPy
- 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