Spaces:
No application file
No application file
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,13 +1,53 @@
|
|
| 1 |
---
|
| 2 |
title: Geodect
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
sdk: gradio
|
| 7 |
-
sdk_version:
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
-
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
title: Geodect
|
| 3 |
+
emoji: βοΈ
|
| 4 |
+
colorFrom: gray
|
| 5 |
+
colorTo: green
|
| 6 |
sdk: gradio
|
| 7 |
+
sdk_version: 5.0.0
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
+
license: mit
|
| 11 |
+
short_description: AI-assisted computer vision for 3D geological modeling.
|
| 12 |
---
|
| 13 |
|
| 14 |
+
# βοΈ Geodect: Geological 3D & Mapping
|
| 15 |
+
|
| 16 |
+
Geodect is an AI-assisted computer vision tool designed to convert field video of geological surfaces or rock samples into clean 3D models and high-resolution 2D orthomosaic maps.
|
| 17 |
+
|
| 18 |
+
## π Key Features
|
| 19 |
+
|
| 20 |
+
* **2D Orthomosaic Mapping:** Automatically extract, align, and stitch video frames into a single, high-resolution undistorted map.
|
| 21 |
+
* **3D Sample Reconstruction:** Transform video orbits of rock samples into interactive `.obj` meshes using Structure from Motion (SfM).
|
| 22 |
+
* **Intelligent Background Removal:** Designed to segment and remove unwanted objects (like hands or tools) to focus on the geological surface.
|
| 23 |
+
* **CPU Optimized:** Built to run efficiently within a Hugging Face Space without requiring high-end GPU resources.
|
| 24 |
+
|
| 25 |
+
## π Technical Workflow
|
| 26 |
+
|
| 27 |
+
1. **Extraction:** OpenCV extracts optimal frames from uploaded field video.
|
| 28 |
+
2. **Processing:** * **Orthomosaic Mode:** Detects features via SIFT/ORB and estimates homography for seamless stitching.
|
| 29 |
+
* **3D Mode:** Estimates camera poses and generates a dense point cloud converted into a surface mesh via Trimesh.
|
| 30 |
+
3. **Visualization:** Interactive 3D rendering and high-res image downloads provided via the Gradio interface.
|
| 31 |
+
|
| 32 |
+
## π Architecture
|
| 33 |
+
|
| 34 |
+
This project is implemented as a lightweight four-file Python application:
|
| 35 |
+
|
| 36 |
+
* `app.py`: The main Gradio interface and pipeline controller.
|
| 37 |
+
* `Orthomosaic.py`: The 2D stitching and blending engine.
|
| 38 |
+
* `ThreeDimagery.py`: The 3D reconstruction and SfM module.
|
| 39 |
+
* `requirements.txt`: Environment dependencies including OpenCV, SciPy, and Trimesh.
|
| 40 |
+
|
| 41 |
+
## π€ Credits & Acknowledgments
|
| 42 |
+
|
| 43 |
+
**Developer:** **Adedoyin Ifeoluwa James**
|
| 44 |
+
|
| 45 |
+
**X:** **https://x.com/IAdedoyin64700**
|
| 46 |
+
|
| 47 |
+
**portfolio website:** **https://adedoyinjames-portfolio.vercel.app**
|
| 48 |
+
|
| 49 |
+
**blog:** **https://theadedoyinjournal.wordpress.com**
|
| 50 |
+
|
| 51 |
+
**Technical Resources:** This project was developed with the technical support and computational resources of **NORA RESEARCH LAB**.
|
| 52 |
+
|
| 53 |
+
---
|