Create README.md
Browse files
README.md
CHANGED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Change Detection Models for National Infrastructure Monitoring
|
| 2 |
+
|
| 3 |
+
This repository contains a collection of advanced change detection models developed by Team-1 from San Jose State University as part of the National Infrastructure Monitoring project.
|
| 4 |
+
|
| 5 |
+
## Models and Contributors
|
| 6 |
+
|
| 7 |
+
Our team has implemented several state-of-the-art change detection models:
|
| 8 |
+
|
| 9 |
+
1. **ChangeViT**: Built by Nihar
|
| 10 |
+
- Combines Vision Transformer (ViT) and CNN architectures
|
| 11 |
+
- Excels at detecting both large-scale and fine-grained changes
|
| 12 |
+
- [Nihar's LinkedIn](https://www.linkedin.com/in/nihar-palem-1b955a183/)
|
| 13 |
+
|
| 14 |
+
2. **BITCD**: Developed by Charishma
|
| 15 |
+
- Uses a transformer-based approach for advanced change detection
|
| 16 |
+
- Processes images as compact token sets for improved efficiency
|
| 17 |
+
- [Charishma's LinkedIn](https://www.linkedin.com/in/sai-charishma-kurmala-080983128/)
|
| 18 |
+
|
| 19 |
+
3. **ChangeFormer**: Implemented by Keerthana
|
| 20 |
+
- Transformer-based architecture for satellite imagery change detection
|
| 21 |
+
- Captures long-range spatial and temporal dependencies
|
| 22 |
+
- [Keerthana's LinkedIn](https://www.linkedin.com/in/keerthana-raskatla-1573781a4/)
|
| 23 |
+
|
| 24 |
+
4. **Multi-Modal Adaptation Network**: Content generation by Anbu
|
| 25 |
+
- Combines optical and SAR imagery for robust change detection
|
| 26 |
+
- Utilizes domain adaptation to align features from different image types
|
| 27 |
+
- [Anbu's LinkedIn](https://www.linkedin.com/in/anbuvalluvan/)
|
| 28 |
+
|
| 29 |
+
5. **Siamese Nested UNet**: Developed by Harika
|
| 30 |
+
- Combines Siamese network and U-Net architectures
|
| 31 |
+
- Excels at image comparison tasks for change detection
|
| 32 |
+
- [Harika's LinkedIn](https://www.linkedin.com/in/harika-boyina/)
|
| 33 |
+
|
| 34 |
+
## Key Features
|
| 35 |
+
|
| 36 |
+
- Advanced change detection capabilities for high-resolution satellite imagery
|
| 37 |
+
- Utilization of transformer-based approaches for capturing long-range relationships
|
| 38 |
+
- Efficient processing of large-scale datasets
|
| 39 |
+
- Combination of multiple imaging modalities for improved accuracy
|
| 40 |
+
- Scalability to handle various image sizes and resolutions
|
| 41 |
+
|
| 42 |
+
These models represent cutting-edge approaches in remote sensing and change detection, specifically tailored for national infrastructure monitoring applications.
|