Create dino.txt

dino.txt

@@ -0,0 +1,118 @@
+def detect_objects_in_video_with_dinox(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
+
+    # DINO-X Configuration (For 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"):
+            video_path, err = convert_video_to_mp4(video_path, temp_output_path)
+            if not video_path:
+                return None, f"Video conversion error: {err}"
+
+        # Read video and process frames
+        video = cv2.VideoCapture(video_path)
+        frame_rate = int(video.get(cv2.CAP_PROP_FPS))
+        frame_width = int(video.get(cv2.CAP_PROP_FRAME_WIDTH))
+        frame_height = int(video.get(cv2.CAP_PROP_FRAME_HEIGHT))
+        frame_size = (frame_width, frame_height)
+
+        # VideoWriter for output video
+        fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+        output_video = cv2.VideoWriter(temp_output_path, fourcc, frame_rate, frame_size)
+
+        while True:
+            ret, frame = video.read()
+            if not ret:
+                break
+
+            # Save frame temporarily for predictions
+            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()
+
+            # Track current frame detections for YOLO
+            current_detections_yolo = {}
+            for prediction in predictions['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
+
+                # 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) ==================
+            image_url = dinox_client.upload_file(frame_path)
+            task = DinoxTask(
+                image_url=image_url,
+                prompts=[TextPrompt(text=DINOX_PROMPT)]
+            )
+            dinox_client.run_task(task)
+            dinox_pred = task.result.objects
+
+            # Process DINO-X detections for unclassified products
+            current_detections_dinox = {}
+            for obj in dinox_pred:
+                dinox_box = obj.bbox
+                class_name = obj.category.strip().lower()
+
+                # 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
+                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.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
+            y_offset = 20
+            for line in 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
+
+            # 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()
+
+        return temp_output_path
+
+    except Exception as e:
+        return None, f"An error occurred: {e}"