Update app.py

app.py

@@ -63,26 +63,29 @@ def generate_journal_with_images(video_path, frame_interval=30):
             # Make predictions using YOLOv10 on the current frame
             results = model.predict(source=frame_rgb, device=device)
             
-            # Plot bounding boxes and labels on the image
-            annotated_frame = results[0].plot()  # Plot detection results on the frame
+            # Extract detected objects
+            detected_objects = [model.names[int(box.cls)] for box in results[0].boxes]
             
-            # Save the annotated image
-            frame_filename = os.path.join(output_folder, f"frame_{frame_count}.jpg")
-            cv2.imwrite(frame_filename, annotated_frame[:, :, ::-1])  # Convert back to BGR for saving
-            image_paths.append(frame_filename)
-            
-            # Extract labels (class indices) and map them to class names
-            detected_objects = [model.names[int(box.cls)] for box in results[0].boxes]  # Access the first result
-            
-            # Get current timestamp in the video
-            timestamp = cap.get(cv2.CAP_PROP_POS_MSEC) / 1000  # Convert ms to seconds
-            
-            # Categorize the detected objects into activities
-            activity_summary = categorize_activity(detected_objects)
-            
-            # Store the activities with their timestamp
-            for activity, objects in activity_summary.items():
-                journal_entries.append(f"At {timestamp:.2f} seconds: {', '.join(objects[0])}")
+            # Only process frames where objects are detected
+            if detected_objects:  # If there are detected objects in the frame
+                
+                # Plot bounding boxes and labels on the image
+                annotated_frame = results[0].plot()  # Plot detection results on the frame
+                
+                # Save the annotated image
+                frame_filename = os.path.join(output_folder, f"frame_{frame_count}.jpg")
+                cv2.imwrite(frame_filename, annotated_frame[:, :, ::-1])  # Convert back to BGR for saving
+                image_paths.append(frame_filename)
+                
+                # Get current timestamp in the video
+                timestamp = cap.get(cv2.CAP_PROP_POS_MSEC) / 1000  # Convert ms to seconds
+                
+                # Categorize the detected objects into activities
+                activity_summary = categorize_activity(detected_objects)
+                
+                # Store the activities with their timestamp
+                for activity, objects in activity_summary.items():
+                    journal_entries.append(f"At {timestamp:.2f} seconds: {', '.join(objects[0])}")
             
             last_processed_frame = frame  # Update the last processed frame
         
@@ -90,10 +93,6 @@ def generate_journal_with_images(video_path, frame_interval=30):
     
     cap.release()
     
-    # Debug print to verify the return values
-    print(f"journal_entries: {journal_entries}")
-    print(f"image_paths: {image_paths}")
-    
     return journal_entries, image_paths