feat: add notebooks for data analysis in paper

.gitignore

@@ -160,6 +160,7 @@ data
 *.csv
 *.pl
 
+**.laz
 **.tif
 **.log
 **.wandb

configs/3d-geoinfo-2025/baseline/run_baseline_evaluation.bat

@@ -0,0 +1,9 @@
+python .\scripts\prediction.py --config-path .\configs\baseline\predict_without_finetuning_2_5_cm.toml
+python .\scripts\prediction.py --config-path .\configs\baseline\predict_without_finetuning_5_cm.toml
+python .\scripts\prediction.py --config-path .\configs\baseline\predict_without_finetuning_7_5_cm.toml
+python .\scripts\prediction.py --config-path .\configs\baseline\predict_without_finetuning_10_cm.toml
+
+python .\scripts\evaluate.py --config-path .\configs\baseline\evaluate_without_finetuning_2_5_cm.toml
+python .\scripts\evaluate.py --config-path .\configs\baseline\evaluate_without_finetuning_5_cm.toml
+python .\scripts\evaluate.py --config-path .\configs\baseline\evaluate_without_finetuning_7_5_cm.toml
+python .\scripts\evaluate.py --config-path .\configs\baseline\evaluate_without_finetuning_10_cm.toml

notebooks/3d-geoinfo-2025/1_table_dataset_overview.ipynb

@@ -0,0 +1,168 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Table 1: Dataset Overview\n",
+    "\n",
+    "This notebook can be used to create the table providing an overview of the datasets used in this study."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "from pathlib import Path\n",
+    "\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# adjust base directory if needed\n",
+    "base_dir = Path(\"G:/3D-GeoInfo-2025/data/1_base_data/labels\")\n",
+    "csv_output_file_path = \"./datasets.csv\"\n",
+    "\n",
+    "datasets = [\n",
+    "    # small plot that was labeled using all three labeling approaches\n",
+    "    {\n",
+    "        \"LabelFile\": \"./manual_labeling/s1_p1_small_coco.json\",\n",
+    "        \"Site\": 1,\n",
+    "        \"Plot\": \"Plot 1.0\",\n",
+    "        \"Size\": \"50 x 50\",\n",
+    "        \"Labeling\": \"ML\",\n",
+    "        \"Usage\": \"train (small)\"\n",
+    "    },\n",
+    "    {\n",
+    "        \"LabelFile\": \"./manual_correction/s1_p1_small_coco.json\",\n",
+    "        \"Site\": 1,\n",
+    "        \"Plot\": \"Plot 1.0\",\n",
+    "        \"Size\": \"50 x 50\",\n",
+    "        \"Labeling\": \"MC\",\n",
+    "        \"Usage\": \"train (small)\"\n",
+    "    },\n",
+    "    {\n",
+    "        \"LabelFile\": \"./automatic_labeling/s1_p1_small_coco.json\",\n",
+    "        \"Site\": 1,\n",
+    "        \"Plot\": \"Plot 1.0\",\n",
+    "        \"Size\": \"50 x 50\",\n",
+    "        \"Labeling\": \"AL\",\n",
+    "        \"Usage\": \"train (small)\"\n",
+    "    },\n",
+    "    # additional manually labeled data\n",
+    "    {\n",
+    "        \"LabelFile\": \"./manual_labeling/s1_p1_ext_ml_coco.json\",\n",
+    "        \"Site\": 1,\n",
+    "        \"Plot\": \"Plot 1.1\",\n",
+    "        \"Size\": \"100 x 100\",\n",
+    "        \"Labeling\": \"ML\",\n",
+    "        \"Usage\": \"train (ext.)\"\n",
+    "    },\n",
+    "    # additional manually corrected data\n",
+    "    {\n",
+    "        \"LabelFile\": \"./manual_correction/s1_p1_ext_mc_coco.json\",\n",
+    "        \"Site\": 1,\n",
+    "        \"Plot\": \"Plot 1.2\",\n",
+    "        \"Size\": \"120 x 80\",\n",
+    "        \"Labeling\": \"MC\",\n",
+    "        \"Usage\": \"train (ext.)\"\n",
+    "    },\n",
+    "    {\n",
+    "        \"LabelFile\": \"./manual_correction/s1_p2_mc_coco.json\",\n",
+    "        \"Site\": 1,\n",
+    "        \"Plot\": \"Plot 2\",\n",
+    "        \"Size\": \"120 x 120\",\n",
+    "        \"Labeling\": \"MC\",\n",
+    "        \"Usage\": \"train (ext.)\"\n",
+    "    },\n",
+    "    {\n",
+    "        \"LabelFile\": \"./manual_correction/s2_p1_mc_coco.json\",\n",
+    "        \"Site\": 2,\n",
+    "        \"Plot\": \"Plot 1\",\n",
+    "        \"Size\": \"120 x 120\",\n",
+    "        \"Labeling\": \"MC\",\n",
+    "        \"Usage\": \"train (ext.)\"\n",
+    "    },\n",
+    "    # additional automatically labeled data\n",
+    "    {\n",
+    "        \"LabelFile\": \"./automatic_labeling/s1_p1_ext_al_coco.json\",\n",
+    "        \"Site\": 1,\n",
+    "        \"Plot\": \"Plot 1.3\",\n",
+    "        \"Size\": \"200 x 100\",\n",
+    "        \"Labeling\": \"AL\",\n",
+    "        \"Usage\": \"train (ext.)\"\n",
+    "    },\n",
+    "    {\n",
+    "        \"LabelFile\": \"./automatic_labeling/s1_p2_al_coco.json\",\n",
+    "        \"Site\": 1,\n",
+    "        \"Plot\": \"Plot 2\",\n",
+    "        \"Size\": \"150 x 100\",\n",
+    "        \"Labeling\": \"AL\",\n",
+    "        \"Usage\": \"train (ext.)\"\n",
+    "    },\n",
+    "    {\n",
+    "        \"LabelFile\": \"./automatic_labeling/s1_p3_al_coco.json\",\n",
+    "        \"Site\": 1,\n",
+    "        \"Plot\": \"Plot 3\",\n",
+    "        \"Size\": \"100 x 100\",\n",
+    "        \"Labeling\": \"AL\",\n",
+    "        \"Usage\": \"train (ext.)\"\n",
+    "    },\n",
+    "    # test set\n",
+    "    {\n",
+    "        \"LabelFile\": \"./manual_labeling/s3_p1_coco.json\",\n",
+    "        \"Site\": 3,\n",
+    "        \"Plot\": \"Plot 1\",\n",
+    "        \"Size\": \"50 x 50\",\n",
+    "        \"Labeling\": \"ML\",\n",
+    "        \"Usage\": \"test\"\n",
+    "    },\n",
+    "]\n",
+    "\n",
+    "dataset_metadata_list = []\n",
+    "\n",
+    "for dataset in datasets:\n",
+    "    label_file_path = base_dir / dataset[\"LabelFile\"]\n",
+    "    assert label_file_path.exists(), f\"{label_file_path} does not exist.\"\n",
+    "    with open(label_file_path, \"r\", encoding=\"utf-8\") as f:\n",
+    "        labels = json.load(f)\n",
+    "    dataset[\"NumTrees\"] = len(labels[\"annotations\"])\n",
+    "    dataset[\"Plot\"] = dataset[\"Plot\"].replace(\"_\", r\"\\_\")\n",
+    "    dataset[\"Size\"] = dataset[\"Size\"].replace(\"x\", r\"$\\times$\")\n",
+    "    dataset_metadata_list.append(dataset)\n",
+    "\n",
+    "dataset_metadata = pd.DataFrame(dataset_metadata_list)\n",
+    "dataset_metadata.to_csv(csv_output_file_path, index=False)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "deepforest-env",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}