feat(scenegraph): add SceneGraphBuilder for pipeline-driven graph construction

Introduce SceneGraphBuilder + SceneGraphBuildConfig to decouple scene graph
construction from the verification notebook. The builder handles batch
inference, hash encoding, and object node creation internally.

- Add SceneGraphBuilder.build_from_room_views() as the main entry point
- Add SceneGraphBuildConfig for inference_batch_size and position strategy
- Add SceneGraphBuildArtifacts to carry cropped images and debug metadata
- Extend ObjectNode with optional detection metadata (label, confidence,
  bbox_xyxy, source_view_id, position_confidence)
- Add RoomView frozen dataclass as a structured view container
- Add flatten_room_views() utility to replace inline list comprehensions
- Refactor notebooks/verification.py to use the new builder API

BREAKING CHANGE: ObjectNode now accepts additional optional fields; direct
scene_graph.objects[obj_id] = ObjectNode(...) construction in the notebook
is replaced by builder.build_from_room_views(...).
This commit is contained in:
2026-05-30 15:40:58 +08:00
parent 97e53d44f8
commit a127032e18
8 changed files with 910 additions and 129 deletions

View File

@@ -1,3 +1,5 @@
from __future__ import annotations
from dataclasses import dataclass
import numpy as np
@@ -20,10 +22,20 @@ class ObjectNode:
hit_count: int = 1 # 被观测到的次数。太低的可以直接过滤掉
last_seen_frame: int = 0 # 最后一次看到的帧号或时间戳
# Optional detection metadata (from M0 integration)
label: str | None = None
confidence: float | None = None
bbox_xyxy: tuple[float, float, float, float] | None = None
source_view_id: str | None = None
position_confidence: float | None = None
def __post_init__(self):
self.position = np.asarray(self.position, dtype=np.float32)
if len(self.visual_hash) != 64:
raise ValueError("visual_hash must be exactly 64 bytes (512 bits)")
if len(self.semantic_hash) != 64:
raise ValueError("semantic_hash must be exactly 64 bytes (512 bits)")
if self.position.shape != (3,):
raise ValueError("position must have shape (3,)")
if self.bbox_xyxy is not None and len(self.bbox_xyxy) != 4:
raise ValueError("bbox_xyxy must have exactly 4 elements")