Update dino.txt

dino.txt

@@ -1,14 +1,13 @@
-def detect_objects_in_video_with_dinox(video_path):
+def detect_objects_in_video(video_path):
     temp_output_path = "/tmp/output_video.mp4"
     temp_frames_dir = tempfile.mkdtemp()
     frame_count = 0
-    previous_detections = {}  # For keeping track of detections in previous frames
+    previous_detections = {}  # Untuk menyimpan deteksi objek dari frame sebelumnya
 
-    # DINO-X Configuration (For unclassified products)
+    # Inisialisasi DINO-X untuk deteksi unclassified products
     dinox_config = Config(DINOX_API_KEY)
     dinox_client = Client(dinox_config)
-    DINOX_PROMPT = "beverage . bottle . cans . boxed milk . milk"  # Customize based on your unclassified products
-    
+
     try:
         # Convert video to MP4 if necessary
         if not video_path.endswith(".mp4"):
@@ -36,79 +35,88 @@ def detect_objects_in_video_with_dinox(video_path):
             frame_path = os.path.join(temp_frames_dir, f"frame_{frame_count}.jpg")
             cv2.imwrite(frame_path, frame)
 
-            # ================== YOLO Detection (Nestlé Products) ==================
-            predictions = yolo_model.predict(frame_path, confidence=50, overlap=80).json()
+            # Process predictions for the current frame using YOLO (Nestlé products)
+            yolo_pred = yolo_model.predict(frame_path, confidence=50, overlap=80).json()
 
-            # Track current frame detections for YOLO
-            current_detections_yolo = {}
-            for prediction in predictions['predictions']:
+            # Track current frame detections (Nestlé)
+            current_detections = {}
+            for prediction in yolo_pred['predictions']:
                 class_name = prediction['class']
                 x, y, w, h = prediction['x'], prediction['y'], prediction['width'], prediction['height']
                 object_id = f"{class_name}_{x}_{y}"
 
-                if object_id not in current_detections_yolo:
-                    current_detections_yolo[object_id] = class_name
+                if object_id not in current_detections:
+                    current_detections[object_id] = class_name
 
                 # Draw bounding box for detected products
                 cv2.rectangle(frame, (int(x-w/2), int(y-h/2)), (int(x+w/2), int(y+h/2)), (0,255,0), 2)
                 cv2.putText(frame, class_name, (int(x-w/2), int(y-h/2-10)), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0,255,0), 2)
 
-            # ================== DINO-X Detection (Unclassified Products) ==================
+            # Calculate product counts (Nestlé)
+            nestle_counts = {}
+            for detection_id in current_detections.keys():
+                class_name = current_detections[detection_id]
+                nestle_counts[class_name] = nestle_counts.get(class_name, 0) + 1
+
+            # Update previous_detections for the next frame
+            previous_detections = current_detections
+
+            # --- Deteksi Unclassified Products menggunakan DINO-X ---
             image_url = dinox_client.upload_file(frame_path)
             task = DinoxTask(
                 image_url=image_url,
-                prompts=[TextPrompt(text=DINOX_PROMPT)]
+                prompts=[TextPrompt(text=DINOX_PROMPT)]  # Define the DINO-X prompt here
             )
             dinox_client.run_task(task)
             dinox_pred = task.result.objects
 
-            # Process DINO-X detections for unclassified products
-            current_detections_dinox = {}
+            # Filter & Hitung Unclassified Products
+            unclassified_counts = {}
             for obj in dinox_pred:
-                dinox_box = obj.bbox
                 class_name = obj.category.strip().lower()
+                if class_name not in unclassified_counts:
+                    unclassified_counts[class_name] = 1
+                else:
+                    unclassified_counts[class_name] += 1
 
-                # Check if the object is unclassified
-                object_id = f"{class_name}_{dinox_box[0]}_{dinox_box[1]}"
-
-                if object_id not in current_detections_dinox:
-                    current_detections_dinox[object_id] = class_name
-
-                # Draw bounding box for unclassified products
-                x1, y1, x2, y2 = dinox_box
+                # Draw bounding box for unclassified objects
+                x1, y1, x2, y2 = obj.bbox
                 cv2.rectangle(frame, (int(x1), int(y1)), (int(x2), int(y2)), (0, 0, 255), 2)
-                cv2.putText(frame, f"{class_name} {obj.score:.2f}", (int(x1), int(y1-10)), 
+                cv2.putText(frame, f"{class_name} {obj.score:.2f}", (int(x1), int(y1-10)),
                             cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 2)
 
-            # ================== Update Counts ==================
-            all_class_count = {}
-            for class_name in current_detections_yolo.values():
-                all_class_count[class_name] = all_class_count.get(class_name, 0) + 1
-
-            for class_name in current_detections_dinox.values():
-                all_class_count[class_name] = all_class_count.get(class_name, 0) + 1
-
-            # Generate count text
-            count_text = ""
-            total_product_count = 0
-            for class_name, count in all_class_count.items():
-                count_text += f"{class_name}: {count}\n"
-                total_product_count += count
-            count_text += f"\nTotal Product: {total_product_count}"
-
-            # Overlay the counts text onto the frame
+            # --- Teks Overlay untuk menghitung produk ---
+            # Format counting untuk Nestlé (dari YOLO)
+            nestle_count_text = ""
+            total_nestle = 0
+            for class_name, count in nestle_counts.items():
+                nestle_count_text += f"{class_name}: {count}\n"
+                total_nestle += count
+            nestle_count_text += f"\nTotal Nestlé Products: {total_nestle}"
+
+            # Format counting untuk Unclassified (dari DINO-X)
+            unclassified_count_text = ""
+            total_unclassified = 0
+            for class_name, count in unclassified_counts.items():
+                unclassified_count_text += f"{class_name}: {count}\n"
+                total_unclassified += count
+            unclassified_count_text += f"\nTotal Unclassified Products: {total_unclassified}"
+
+            # Overlay teks ke frame
             y_offset = 20
-            for line in count_text.split("\n"):
+            for line in nestle_count_text.split("\n"):
+                cv2.putText(frame, line, (10, y_offset), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (255, 255, 255), 2)
+                y_offset += 30
+
+            y_offset += 30  # Slight gap between sections
+            for line in unclassified_count_text.split("\n"):
                 cv2.putText(frame, line, (10, y_offset), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (255, 255, 255), 2)
-                y_offset += 30  # Move down for next line
+                y_offset += 30
 
             # Write processed frame to output video
             output_video.write(frame)
             frame_count += 1
 
-            # Update previous detections for the next frame
-            previous_detections = current_detections_yolo
-
         video.release()
         output_video.release()
 
@@ -116,3 +124,4 @@ def detect_objects_in_video_with_dinox(video_path):
 
     except Exception as e:
         return None, f"An error occurred: {e}"
+