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 · Capstone
Cloud Removal from Satellite Images
Reconstructs ground detail hidden under cloud in Sentinel-2 imagery
5-6 weeks build
Overview
Uses the public SEN12MS-CR dataset, which pairs cloudy Sentinel-2 optical tiles with cloud-free references and Sentinel-1 radar that sees through cloud. A conditional GAN fuses radar and cloudy optical input to predict the clear scene, and is compared with a temporal-mosaic baseline using PSNR, SSIM and spectral angle mapper.
What makes it stand up
- 01Multispectral GeoTIFF handling with Rasterio
- 02Radar and optical fusion as generator input
- 03Cloud mask generation to target only obscured pixels
- 04Temporal-mosaic baseline for a fair comparison
- 05PSNR, SSIM and spectral angle mapper in the report
Module breakdown
- 01
Data pipeline
SEN12MS-CR loading, band selection and normalisation.
- 02
Cloud masking
Threshold and index-based detection of cloudy pixels.
- 03
Fusion GAN
Generator taking SAR and optical bands, PatchGAN critic.
- 04
Baseline
Least-cloudy temporal mosaic for comparison.
- 05
Viewer
Streamlit tile viewer with cloudy, predicted and reference panes.
After this, you will be able to
- Explain why radar complements optical imagery under cloud
- Defend spectral metrics alongside visual ones for remote sensing
- Demo cloud removal on held-out tiles from a new region
Technology stack
- Python
- PyTorch
- Rasterio
- NumPy
- Streamlit
- Level
- Capstone
- Domain
- Artificial Intelligence
- Build time
- 5-6 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