---
license: etalab-2.0
tags:
- pytorch
- segmentation
- point clouds
- aerial lidar scanning
- IGN
model-index:
- name: FRACTAL-LidarHD_7cl_randlanet
  results:
  - task:
      type: semantic-segmentation
    dataset:
      name: IGNF/FRACTAL
      type: point-cloud-segmentation-dataset
    metrics:
    - name: mIoU
      type: mIoU
      value: 77.2
    - name: IoU Other
      type: IoU
      value: 48.1
    - name: IoU Ground
      type: IoU
      value: 91.7
    - name: IoU Vegetation
      type: IoU
      value: 93.7
    - name: IoU Building
      type: IoU
      value: 90.0
    - name: IoU Water
      type: IoU
      value: 90.8
    - name: IoU Bridge
      type: IoU
      value: 63.5
    - name: IoU Permanent Structure
      type: IoU
      value: 59.9
---

<div style="border:1px solid black; padding:25px; background-color:#FDFFF4 ; padding-top:10px; padding-bottom:1px;">
  <h1>FRACTAL-LidarHD_7cl_randlanet</h1> 
  <p>The general characteristics of this specific model <strong>FRACTAL-LidarHD_7cl_randlanet</strong> are :</p>
  <ul style="list-style-type:disc;">
    <li>Trained with the FRACTAL dataset</li>
    <li>Aerial lidar point clouds, colorized with rgb + near-infrared, with high point density (~40 pts/m²)</li>
    <li>RandLa-Net architecture as implemented in the Myria3D library</li>
    <li>7 class nomenclature : [other, ground, vegetation, building, water, bridge, permanent structure]</li>
  </ul>
</div>

## Model Informations
- **Code repository:** https://github.com/IGNF/myria3d (V3.8)
- **Paper:** TBD
- **Developed by:** IGN
- **Compute infrastructure:** 
    - software: python, pytorch-lightning
    - hardware: in-house HPC/AI resources
- **License:** : Etalab 2.0

---

## Uses
The model was specifically trained and designed for the segmentation of aerial lidar point clouds from the Lidar HD program (2020-2025), 
an ambitious initiative that aim to obtain a 3D description of the French territory by 2026. 
While the model could be applied to other types of point clouds, Lidar HD data have specific geometric specifications. Furthermore, the training data was colorized 
with very-high-definition aerial images from the ([BD ORTHO®](https://geoservices.ign.fr/bdortho)), which have their own spatial and radiometric specifications.

Consequently, the model's prediction would improve for aerial lidar point clouds with similar densities and colorimetries than the original ones.

**Data preprocessing**
Point clouds were preprocessed for training with point subsampling, filtering of artefacts points, on-the-fly creation of colorimetric features, and normalization of features and coordinates. 
For inference, the same preprocessing should be used (refer to the inference configuration and to the code repository).

**Inference library: Myria3D**
Model was trained in an open source deep learning code reposiroty developped in-house, and inference is only supported in this library. 
The library comes with a Dockerfile as well as detailed documentation for inference. 
Patched inference from large point clouds (e.g. 1 x 1 km Lidar HD tiles) is supported, with or without (default) overlapping sliding windows. 
The original point cloud is augmented with several dimensions: a PredictedClassification dimension, an entropy dimension, and (optionnaly) class probability dimensions (e.g. building, ground...). 
Refer to Myria3D's documentation for custom settings.

## Bias, Risks, Limitations and Recommendations

---

## How to Get Started with the Model

Visit ([https://github.com/IGNF/FLAIR-1](https://github.com/IGNF/myria3d)) to use the model.
Fine-tuning and prediction tasks are detailed in the README file.


---

## Training Details

### Training Data


### Training Procedure

#### Preprocessing



#### Training Hyperparameters


#### Speeds, Sizes, Times


## Evaluation

### Testing Data, Factors & Metrics

#### Testing Data

#### Metrics


### Results

Samples of results


---

## Citation


**BibTeX:**

```

```


**APA:**
```

```

## Contact : TBD