adding table and information about detected buildings

gradio_with_map.py

@@ -15,8 +15,9 @@ import os
 IMAGE_WIDTH = 4000
 IMAGE_HEIGHT = 3000
 
+
 # Load YOLO model
-model = YOLOv10("weights/yolov10m-e100-b16-full-best.pt")
+model = YOLOv10("./weights/yolov10m-e100-b16-full-best.pt")
 
 # Define the directory for saving uploaded images
 UPLOAD_DIR = 'uploads'  # Or any other directory within your project
@@ -82,12 +83,7 @@ def predict_image(img, conf_threshold, iou_threshold):
         print(f"Gimbal Pitch Degree: {gimbal_pitch_degree}")
     else:
         print("XMP data not found in the image.")
-        # Set default values when XMP data is not found
-        relative_altitude = 60.0  # Default relative altitude
-        gimbal_yaw_degree = 30.0  # Default yaw degree
-        gimbal_pitch_degree = -90.0  # Default pitch degree
-
-    # Continue with the rest of the function...
+    
     # Extract EXIF data
     exif_data = img.info.get("exif")
     try:
@@ -102,7 +98,7 @@ def predict_image(img, conf_threshold, iou_threshold):
         img.save(img_path, exif=exif_data)  # Save the image with its EXIF data
     else:
         img.save(img_path)  # Save without EXIF data if not available
-
+    
     # Convert PIL Image to OpenCV image
     img_cv2 = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)
 
@@ -185,9 +181,17 @@ def predict_image(img, conf_threshold, iou_threshold):
         tiles='Esri.WorldImagery'
     )
 
-    # Add markers for each detected building
+    # Initialize counters for damaged and undamaged buildings
+    damaged_count = 0
+    undamaged_count = 0
+
+    # Add markers for each detected building and count the damaged and undamaged buildings
     for i, (building_lat, building_lon, class_id) in enumerate(building_locations):
         building_status = 'Damaged' if class_id == 1 else 'Undamaged'
+        if class_id == 1:
+            damaged_count += 1
+        else:
+            undamaged_count += 1
 
         folium.Marker(
             location=(building_lat, building_lon),
@@ -203,7 +207,23 @@ def predict_image(img, conf_threshold, iou_threshold):
     encoded_html = base64.b64encode(folium_map_html.encode()).decode('utf-8')
     data_url = f"data:text/html;base64,{encoded_html}"
 
-    return im, f'<iframe src="{data_url}" width="100%" height="600" style="border:none;"></iframe>'
+    # Create a summary of the building counts
+    summary = f"Damaged Buildings: {damaged_count}, Undamaged Buildings: {undamaged_count}"
+
+    # Create an HTML table for building information
+    table_html = "<table style='width: 100%; border-collapse: collapse;'>"
+    table_html += "<tr><th style='border: 1px solid black;'>Building Number</th><th style='border: 1px solid black;'>Building Type</th><th style='border: 1px solid black;'>Location (Lat, Lon)</th></tr>"
+
+    for i, (lat, lon, class_id) in enumerate(building_locations):
+        building_type = 'Damaged' if class_id == 1 else 'Undamaged'
+        table_html += f"<tr><td style='border: 1px solid black;'>{i+1}</td><td style='border: 1px solid black;'>{building_type}</td><td style='border: 1px solid black;'>{lat}, {lon}</td></tr>"
+
+    table_html += "</table>"
+
+    return im, f'<iframe src="{data_url}" width="100%" height="600" style="border:none;"></iframe>', summary, table_html
+
+
+logo_url = "https://www.bewelltech.com.tr/_app/immutable/assets/bewell_logo.fda8f209.png"
 
 description_with_logo = """
 <img src="https://www.bewelltech.com.tr/_app/immutable/assets/bewell_logo.fda8f209.png" alt="Logo" style="width: 150px; margin-bottom: 10px;">
@@ -221,6 +241,8 @@ iface = gr.Interface(
     outputs=[
         gr.Image(type="pil", label="Annotated Image"),
         gr.HTML(label="Map"),
+        gr.HTML(label="Summary"),  # New output for the summary
+        gr.HTML(label="Building Information"),  # New output for the table
     ],
     title="Custom trained Yolov10 Model on Rescuenet Dataset",
     description=description_with_logo,