geoai-py 0.3.2__tar.gz → 0.3.3__tar.gz

{geoai_py-0.3.2 → geoai_py-0.3.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: geoai-py
-Version: 0.3.2
+Version: 0.3.3
 Summary: A Python package for using Artificial Intelligence (AI) with geospatial data
 Author-email: Qiusheng Wu <giswqs@gmail.com>
 License: MIT License
@@ -30,6 +30,7 @@ Requires-Dist: planetary-computer
 Requires-Dist: pystac-client
 Requires-Dist: rasterio
 Requires-Dist: rioxarray
+Requires-Dist: scikit-image
 Requires-Dist: scikit-learn
 Requires-Dist: torch
 Requires-Dist: torchgeo
@@ -49,9 +50,9 @@ Requires-Dist: geoai[download]; extra == "all"
 [![image](https://static.pepy.tech/badge/geoai-py)](https://pepy.tech/project/geoai-py)
 [![image](https://img.shields.io/conda/vn/conda-forge/geoai.svg)](https://anaconda.org/conda-forge/geoai)
 [![Conda Downloads](https://img.shields.io/conda/dn/conda-forge/geoai.svg)](https://anaconda.org/conda-forge/geoai)
-[![Conda Recipe](https://img.shields.io/badge/recipe-geoai-green.svg)](https://github.com/conda-forge/geoai-py-feedstock)
+[![Conda Recipe](https://img.shields.io/badge/recipe-geoai-green.svg)](https://github.com/giswqs/geoai-py-feedstock)
 [![image](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![image](https://img.shields.io/badge/YouTube-Channel-red)](https://youtube.com/@giswqs)
+[![image](https://img.shields.io/badge/YouTube-Tutorials-red)](https://bit.ly/GeoAI-Tutorials)
 
 **A powerful Python package for integrating Artificial Intelligence with geospatial data analysis and visualization**
 
@@ -85,7 +86,7 @@ GeoAI bridges the gap between AI and geospatial analysis, providing tools for pr
 -   Integration with Meta's Segment Anything Model (SAM) for automatic feature extraction
 -   Specialized segmentation algorithms optimized for satellite and aerial imagery
 -   Streamlined workflows for segmenting buildings, roads, vegetation, and water bodies
--   Export capabilities to standard geospatial formats (GeoJSON, Shapefile, GeoPackage)
+-   Export capabilities to standard geospatial formats (GeoJSON, Shapefile, GeoPackage, GeoParquet)
 
 ### 🔍 Image Classification
 
@@ -130,6 +131,12 @@ Comprehensive documentation is available at [https://geoai.gishub.org](https://g
 -   Explanation of algorithms and models
 -   Best practices for geospatial AI
 
+## 📺 Video Tutorials
+
+Check out our [YouTube channel](https://bit.ly/GeoAI-Tutorials) for video tutorials on using GeoAI for geospatial data analysis and visualization.
+
+[![cover](https://github.com/user-attachments/assets/3cde9547-ab62-4d70-b23a-3e5ed27c7407)](https://bit.ly/GeoAI-Tutorials)
+
 ## 🤝 Contributing
 
 We welcome contributions of all kinds! See our [contributing guide](https://geoai.gishub.org/contributing) for ways to get started.

{geoai_py-0.3.2 → geoai_py-0.3.3}/README.md

@@ -4,9 +4,9 @@
 [![image](https://static.pepy.tech/badge/geoai-py)](https://pepy.tech/project/geoai-py)
 [![image](https://img.shields.io/conda/vn/conda-forge/geoai.svg)](https://anaconda.org/conda-forge/geoai)
 [![Conda Downloads](https://img.shields.io/conda/dn/conda-forge/geoai.svg)](https://anaconda.org/conda-forge/geoai)
-[![Conda Recipe](https://img.shields.io/badge/recipe-geoai-green.svg)](https://github.com/conda-forge/geoai-py-feedstock)
+[![Conda Recipe](https://img.shields.io/badge/recipe-geoai-green.svg)](https://github.com/giswqs/geoai-py-feedstock)
 [![image](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![image](https://img.shields.io/badge/YouTube-Channel-red)](https://youtube.com/@giswqs)
+[![image](https://img.shields.io/badge/YouTube-Tutorials-red)](https://bit.ly/GeoAI-Tutorials)
 
 **A powerful Python package for integrating Artificial Intelligence with geospatial data analysis and visualization**
 
@@ -40,7 +40,7 @@ GeoAI bridges the gap between AI and geospatial analysis, providing tools for pr
 -   Integration with Meta's Segment Anything Model (SAM) for automatic feature extraction
 -   Specialized segmentation algorithms optimized for satellite and aerial imagery
 -   Streamlined workflows for segmenting buildings, roads, vegetation, and water bodies
--   Export capabilities to standard geospatial formats (GeoJSON, Shapefile, GeoPackage)
+-   Export capabilities to standard geospatial formats (GeoJSON, Shapefile, GeoPackage, GeoParquet)
 
 ### 🔍 Image Classification
 
@@ -85,6 +85,12 @@ Comprehensive documentation is available at [https://geoai.gishub.org](https://g
 -   Explanation of algorithms and models
 -   Best practices for geospatial AI
 
+## 📺 Video Tutorials
+
+Check out our [YouTube channel](https://bit.ly/GeoAI-Tutorials) for video tutorials on using GeoAI for geospatial data analysis and visualization.
+
+[![cover](https://github.com/user-attachments/assets/3cde9547-ab62-4d70-b23a-3e5ed27c7407)](https://bit.ly/GeoAI-Tutorials)
+
 ## 🤝 Contributing
 
 We welcome contributions of all kinds! See our [contributing guide](https://geoai.gishub.org/contributing) for ways to get started.

{geoai_py-0.3.2 → geoai_py-0.3.3}/docs/examples/building_footprints_usa.ipynb

@@ -156,7 +156,8 @@
     "    confidence_threshold=0.5,\n",
     "    overlap=0.25,\n",
     "    nms_iou_threshold=0.5,\n",
-    "    small_building_area=100,\n",
+    "    min_object_area=100,\n",
+    "    max_object_area=None,\n",
     "    mask_threshold=0.5,\n",
     "    simplify_tolerance=1.0,\n",
     ")"
@@ -256,7 +257,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "torch",
+   "display_name": "geo",
    "language": "python",
    "name": "python3"
   },
@@ -270,7 +271,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.8"
+   "version": "3.12.2"
   }
  },
  "nbformat": 4,

geoai_py-0.3.3/docs/examples/geometric_properties.ipynb

@@ -0,0 +1,199 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Geometric Properties\n",
+    "\n",
+    "[![image](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/opengeos/geoai/blob/main/docs/examples/geometric_properties.ipynb)\n",
+    "\n",
+    "This notebook demonstrates how to calculate geometric properties of objects in a vector dataset and filter out unwanted objects based on these properties.\n",
+    "\n",
+    "## Install package\n",
+    "To use the `geoai-py` package, ensure it is installed in your environment. Uncomment the command below if needed."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %pip install geoai-py"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Import package"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import geoai"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Load data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "vector_url = \"https://huggingface.co/datasets/giswqs/geospatial/resolve/main/naip_buildings_masks.geojson\"\n",
+    "raster_url = (\n",
+    "    \"https://huggingface.co/datasets/giswqs/geospatial/resolve/main/naip_train.tif\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gdf = geoai.read_vector(vector_url)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gdf.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Visualize data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "geoai.view_vector_interactive(gdf, column=\"confidence\", tiles=raster_url)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Add geometric properties"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gdf_props = geoai.add_geometric_properties(gdf, area_unit=\"m2\", length_unit=\"m\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gdf_props.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Visualize geometric properties"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "geoai.view_vector_interactive(gdf_props, column=\"area_m2\", tiles=raster_url)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "geoai.view_vector_interactive(gdf_props, column=\"elongation\", tiles=raster_url)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Filter objects based on geometric properties"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gdf_filtered = gdf_props[(gdf_props[\"area_m2\"] < 2000) & (gdf_props[\"elongation\"] < 5)]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Visualize filtered objects"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "geoai.view_vector_interactive(gdf_filtered, column=\"elongation\", tiles=raster_url)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "geo",
+   "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": "3.12.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

{geoai_py-0.3.2 → geoai_py-0.3.3}/docs/index.md

@@ -4,9 +4,9 @@
 [![image](https://static.pepy.tech/badge/geoai-py)](https://pepy.tech/project/geoai-py)
 [![image](https://img.shields.io/conda/vn/conda-forge/geoai.svg)](https://anaconda.org/conda-forge/geoai)
 [![Conda Downloads](https://img.shields.io/conda/dn/conda-forge/geoai.svg)](https://anaconda.org/conda-forge/geoai)
-[![Conda Recipe](https://img.shields.io/badge/recipe-geoai-green.svg)](https://github.com/conda-forge/geoai-py-feedstock)
+[![Conda Recipe](https://img.shields.io/badge/recipe-geoai-green.svg)](https://github.com/giswqs/geoai-py-feedstock)
 [![image](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![image](https://img.shields.io/badge/YouTube-Channel-red)](https://youtube.com/@giswqs)
+[![image](https://img.shields.io/badge/YouTube-Tutorials-red)](https://bit.ly/GeoAI-Tutorials)
 
 **A powerful Python package for integrating Artificial Intelligence with geospatial data analysis and visualization**
 
@@ -40,7 +40,7 @@ GeoAI bridges the gap between AI and geospatial analysis, providing tools for pr
 -   Integration with Meta's Segment Anything Model (SAM) for automatic feature extraction
 -   Specialized segmentation algorithms optimized for satellite and aerial imagery
 -   Streamlined workflows for segmenting buildings, roads, vegetation, and water bodies
--   Export capabilities to standard geospatial formats (GeoJSON, Shapefile, GeoPackage)
+-   Export capabilities to standard geospatial formats (GeoJSON, Shapefile, GeoPackage, GeoParquet)
 
 ### 🔍 Image Classification
 
@@ -85,6 +85,12 @@ Comprehensive documentation is available at [https://geoai.gishub.org](https://g
 -   Explanation of algorithms and models
 -   Best practices for geospatial AI
 
+## 📺 Video Tutorials
+
+Check out our [YouTube channel](https://bit.ly/GeoAI-Tutorials) for video tutorials on using GeoAI for geospatial data analysis and visualization.
+
+[![cover](https://github.com/user-attachments/assets/3cde9547-ab62-4d70-b23a-3e5ed27c7407)](https://bit.ly/GeoAI-Tutorials)
+
 ## 🤝 Contributing
 
 We welcome contributions of all kinds! See our [contributing guide](https://geoai.gishub.org/contributing) for ways to get started.

{geoai_py-0.3.2 → geoai_py-0.3.3}/geoai/__init__.py

@@ -2,7 +2,7 @@
 
 __author__ = """Qiusheng Wu"""
 __email__ = "giswqs@gmail.com"
-__version__ = "0.3.2"
+__version__ = "0.3.3"
 
 
 import os

{geoai_py-0.3.2 → geoai_py-0.3.3}/geoai/extract.py

@@ -13,7 +13,7 @@ import rasterio
 from rasterio.windows import Window
 from rasterio.features import shapes
 from huggingface_hub import hf_hub_download
-from .preprocess import get_raster_stats
+from .utils import get_raster_stats
 
 try:
     from torchgeo.datasets import NonGeoDataset
@@ -196,7 +196,8 @@ class ObjectDetector:
         self.overlap = 0.25  # Default overlap between tiles
         self.confidence_threshold = 0.5  # Default confidence threshold
         self.nms_iou_threshold = 0.5  # IoU threshold for non-maximum suppression
-        self.small_object_area = 100  # Minimum area in pixels to keep an object
+        self.min_object_area = 100  # Minimum area in pixels to keep an object
+        self.max_object_area = None  # Maximum area in pixels to keep an object
         self.mask_threshold = 0.5  # Threshold for mask binarization
         self.simplify_tolerance = 1.0  # Tolerance for polygon simplification
 
@@ -326,7 +327,8 @@ class ObjectDetector:
             **kwargs: Optional parameters:
                 simplify_tolerance: Tolerance for polygon simplification
                 mask_threshold: Threshold for mask binarization
-                small_object_area: Minimum area in pixels to keep an object
+                min_object_area: Minimum area in pixels to keep an object
+                max_object_area: Maximum area in pixels to keep an object
 
         Returns:
             List of polygons as lists of (x, y) coordinates
@@ -335,7 +337,8 @@ class ObjectDetector:
         # Get parameters from kwargs or use instance defaults
         simplify_tolerance = kwargs.get("simplify_tolerance", self.simplify_tolerance)
         mask_threshold = kwargs.get("mask_threshold", self.mask_threshold)
-        small_object_area = kwargs.get("small_object_area", self.small_object_area)
+        min_object_area = kwargs.get("min_object_area", self.min_object_area)
+        max_object_area = kwargs.get("max_object_area", self.max_object_area)
 
         # Ensure binary mask
         mask = (mask > mask_threshold).astype(np.uint8)
@@ -351,7 +354,14 @@ class ObjectDetector:
         polygons = []
         for contour in contours:
             # Filter out too small contours
-            if contour.shape[0] < 3 or cv2.contourArea(contour) < small_object_area:
+            if contour.shape[0] < 3 or cv2.contourArea(contour) < min_object_area:
+                continue
+
+            # Filter out too large contours
+            if (
+                max_object_area is not None
+                and cv2.contourArea(contour) > max_object_area
+            ):
                 continue
 
             # Simplify contour if it has many points
@@ -491,7 +501,8 @@ class ObjectDetector:
         output_path=None,
         simplify_tolerance=None,
         mask_threshold=None,
-        small_object_area=None,
+        min_object_area=None,
+        max_object_area=None,
         nms_iou_threshold=None,
         regularize=True,
         angle_threshold=15,
@@ -505,7 +516,8 @@ class ObjectDetector:
             output_path: Path to save the output GeoJSON (default: mask_path with .geojson extension)
             simplify_tolerance: Tolerance for polygon simplification (default: self.simplify_tolerance)
             mask_threshold: Threshold for mask binarization (default: self.mask_threshold)
-            small_object_area: Minimum area in pixels to keep an object (default: self.small_object_area)
+            min_object_area: Minimum area in pixels to keep an object (default: self.min_object_area)
+            max_object_area: Minimum area in pixels to keep an object (default: self.max_object_area)
             nms_iou_threshold: IoU threshold for non-maximum suppression (default: self.nms_iou_threshold)
             regularize: Whether to regularize objects to right angles (default: True)
             angle_threshold: Maximum deviation from 90 degrees for regularization (default: 15)
@@ -523,10 +535,11 @@ class ObjectDetector:
         mask_threshold = (
             mask_threshold if mask_threshold is not None else self.mask_threshold
         )
-        small_object_area = (
-            small_object_area
-            if small_object_area is not None
-            else self.small_object_area
+        min_object_area = (
+            min_object_area if min_object_area is not None else self.min_object_area
+        )
+        max_object_area = (
+            max_object_area if max_object_area is not None else self.max_object_area
         )
         nms_iou_threshold = (
             nms_iou_threshold
@@ -540,7 +553,8 @@ class ObjectDetector:
 
         print(f"Converting mask to GeoJSON with parameters:")
         print(f"- Mask threshold: {mask_threshold}")
-        print(f"- Min object area: {small_object_area}")
+        print(f"- Min object area: {min_object_area}")
+        print(f"- Max object area: {max_object_area}")
         print(f"- Simplify tolerance: {simplify_tolerance}")
         print(f"- NMS IoU threshold: {nms_iou_threshold}")
         print(f"- Regularize objects: {regularize}")
@@ -586,7 +600,11 @@ class ObjectDetector:
                 area = stats[i, cv2.CC_STAT_AREA]
 
                 # Skip if too small
-                if area < small_object_area:
+                if area < min_object_area:
+                    continue
+
+                # Skip if too large
+                if max_object_area is not None and area > max_object_area:
                     continue
 
                 # Create a mask for this object
@@ -710,7 +728,7 @@ class ObjectDetector:
                 chip_size: Size of image chips for processing (height, width)
                 nms_iou_threshold: IoU threshold for non-maximum suppression (0.0-1.0)
                 mask_threshold: Threshold for mask binarization (0.0-1.0)
-                small_object_area: Minimum area in pixels to keep an object
+                min_object_area: Minimum area in pixels to keep an object
                 simplify_tolerance: Tolerance for polygon simplification
 
         Returns:
@@ -724,7 +742,8 @@ class ObjectDetector:
         chip_size = kwargs.get("chip_size", self.chip_size)
         nms_iou_threshold = kwargs.get("nms_iou_threshold", self.nms_iou_threshold)
         mask_threshold = kwargs.get("mask_threshold", self.mask_threshold)
-        small_object_area = kwargs.get("small_object_area", self.small_object_area)
+        min_object_area = kwargs.get("min_object_area", self.min_object_area)
+        max_object_area = kwargs.get("max_object_area", self.max_object_area)
         simplify_tolerance = kwargs.get("simplify_tolerance", self.simplify_tolerance)
 
         # Print parameters being used
@@ -734,7 +753,8 @@ class ObjectDetector:
         print(f"- Chip size: {chip_size}")
         print(f"- NMS IoU threshold: {nms_iou_threshold}")
         print(f"- Mask threshold: {mask_threshold}")
-        print(f"- Min object area: {small_object_area}")
+        print(f"- Min object area: {min_object_area}")
+        print(f"- Max object area: {max_object_area}")
         print(f"- Simplify tolerance: {simplify_tolerance}")
         print(f"- Filter edge objects: {filter_edges}")
         if filter_edges:
@@ -865,7 +885,8 @@ class ObjectDetector:
                         binary_mask,
                         simplify_tolerance=simplify_tolerance,
                         mask_threshold=mask_threshold,
-                        small_object_area=small_object_area,
+                        min_object_area=min_object_area,
+                        max_object_area=max_object_area,
                     )
 
                     # Skip if no valid polygons

{geoai_py-0.3.2 → geoai_py-0.3.3}/geoai/geoai.py

@@ -1,5 +1,4 @@
 """Main module."""
 
 from .utils import *
-from .preprocess import *
 from .extract import *

{geoai_py-0.3.2 → geoai_py-0.3.3}/geoai/preprocess.py

@@ -288,7 +288,11 @@ def get_vector_info(vector_path):
         dict: Dictionary containing the basic information about the vector dataset
     """
     # Open the vector dataset
-    gdf = gpd.read_file(vector_path)
+    gdf = (
+        gpd.read_parquet(vector_path)
+        if vector_path.endswith(".parquet")
+        else gpd.read_file(vector_path)
+    )
 
     # Get basic metadata
     info = {
@@ -359,7 +363,11 @@ def print_vector_info(vector_path, show_preview=True, figsize=(10, 8)):
 
         # Show a preview if requested
         if show_preview:
-            gdf = gpd.read_file(vector_path)
+            gdf = (
+                gpd.read_parquet(vector_path)
+                if vector_path.endswith(".parquet")
+                else gpd.read_file(vector_path)
+            )
             fig, ax = plt.subplots(figsize=figsize)
             gdf.plot(ax=ax, cmap="viridis")
             ax.set_title(f"Preview: {vector_path}")
@@ -2813,7 +2821,8 @@ def masks_to_vector(
     output_path=None,
     simplify_tolerance=1.0,
     mask_threshold=0.5,
-    min_area=100,
+    min_object_area=100,
+    max_object_area=None,
     nms_iou_threshold=0.5,
 ):
     """
@@ -2824,7 +2833,8 @@ def masks_to_vector(
         output_path: Path to save the output GeoJSON (default: mask_path with .geojson extension)
         simplify_tolerance: Tolerance for polygon simplification (default: self.simplify_tolerance)
         mask_threshold: Threshold for mask binarization (default: self.mask_threshold)
-        min_area: Minimum area in pixels to keep a building (default: self.small_building_area)
+        min_object_area: Minimum area in pixels to keep a building (default: self.min_object_area)
+        max_object_area: Maximum area in pixels to keep a building (default: self.max_object_area)
         nms_iou_threshold: IoU threshold for non-maximum suppression (default: self.nms_iou_threshold)
 
     Returns:
@@ -2836,7 +2846,7 @@ def masks_to_vector(
 
     print(f"Converting mask to GeoJSON with parameters:")
     print(f"- Mask threshold: {mask_threshold}")
-    print(f"- Min building area: {min_area}")
+    print(f"- Min building area: {min_object_area}")
     print(f"- Simplify tolerance: {simplify_tolerance}")
     print(f"- NMS IoU threshold: {nms_iou_threshold}")
 
@@ -2876,7 +2886,11 @@ def masks_to_vector(
             area = stats[i, cv2.CC_STAT_AREA]
 
             # Skip if too small
-            if area < min_area:
+            if area < min_object_area:
+                continue
+
+            # Skip if too large
+            if max_object_area is not None and area > max_object_area:
                 continue
 
             # Create a mask for this building