refactor(pipeline): integrate SAM segmentation and modularize model loading

mini-nav/utils/image.py

@@ -0,0 +1,68 @@
+from typing import Any
+
+import numpy as np
+from PIL import Image
+
+
+def segment_image(
+    mask_generator: Any,
+    image: Image.Image,
+    min_area: int = 32 * 32,
+    max_masks: int = 5,
+    points_per_batch=64,
+) -> list[dict[str, Any]]:
+    """Segment image using SAM to extract object masks.
+
+    Args:
+        mask_generator: SAM2 mask generator.
+        image: PIL Image to segment.
+        min_area: Minimum mask area threshold in pixels.
+        max_masks: Maximum number of masks to return.
+        points_per_batch: Number of prompt points to process in each batch.
+    Returns:
+        List of mask dictionaries with keys:
+            - segment: Binary mask (numpy array)
+            - area: Mask area in pixels
+            - bbox: Bounding box [x, y, width, height]
+            - predicted_iou: Model's confidence in the mask
+            - stability_score: Stability score for the mask
+    """
+    # Convert PIL Image to numpy array
+    image_np = np.array(image.convert("RGB"))
+
+    # Generate masks
+    masks = mask_generator(image_np, points_per_batch=points_per_batch)["masks"]
+
+    if not masks:
+        return []
+
+    # Filter by minimum area
+    filtered_masks = [m for m in masks if m["area"] >= min_area]
+
+    if not filtered_masks:
+        return []
+
+    # Sort by area (largest first) and limit to max_masks
+    sorted_masks = sorted(filtered_masks, key=lambda x: x["area"], reverse=True)
+    return sorted_masks[:max_masks]
+
+
+def extract_masked_region(
+    image: Image.Image,
+    mask: np.ndarray,
+) -> Image.Image:
+    """Extract masked region from image.
+
+    Args:
+        image: Original PIL Image.
+        mask: Binary mask as numpy array (True = keep).
+
+    Returns:
+        PIL Image with only the masked region visible.
+    """
+    image_np = np.array(image.convert("RGB"))
+
+    # Apply mask
+    masked_np = image_np * mask[:, :, np.newaxis]
+
+    return Image.fromarray(masked_np.astype(np.uint8))