Update app.py

app.py

@@ -37,6 +37,7 @@ def generate_journal_with_images(video_path):
     journal_entries = {}
     saved_images = []
     frame_count = 0
+    last_processed_frame = None
     output_folder = "detected_frames"
     os.makedirs(output_folder, exist_ok=True)  # Create folder to store images
     
@@ -45,33 +46,37 @@ def generate_journal_with_images(video_path):
         if not ret:
             break
         
-        frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-        
-        # 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
-        
-        # 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
-        saved_images.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():
-            if activity not in journal_entries:
-                journal_entries[activity] = []
-            journal_entries[activity].append((f"At {timestamp:.2f} seconds: {', '.join(objects[0])}", frame_filename))
+        # Process every Nth frame or if the current frame is different from the last processed frame
+        if frame_count % frame_interval == 0 or (last_processed_frame is not None and is_frame_different(last_processed_frame, frame)):
+            frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+            
+            # 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
+            
+            # 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
+            saved_images.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():
+                if activity not in journal_entries:
+                    journal_entries[activity] = []
+                journal_entries[activity].append((f"At {timestamp:.2f} seconds: {', '.join(objects[0])}", frame_filename))
+            
+            last_processed_frame = frame  # Update the last processed frame
         
         frame_count += 1