mirror of
https://github.com/SikongJueluo/Mini-Nav.git
synced 2026-07-12 20:15:31 +08:00
SikongJueluo
a127032e18
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(...).
42 lines
1.7 KiB
Python
42 lines
1.7 KiB
Python
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass
|
|
|
|
import numpy as np
|
|
|
|
|
|
# --- 1. 物品节点：极其扁平，只存"当前最新/平均"状态 ---
|
|
@dataclass
|
|
class ObjectNode:
|
|
obj_id: str # 唯一ID (例如: "obj_001")
|
|
room_id: str # 所属房间的直接外键，不搞复杂的层级关系
|
|
|
|
# 位置：在 debug 阶段，一切认准全局坐标，不要搞局部坐标系
|
|
position: np.ndarray # [x, y, z] 世界坐标系下的中心点或锚点
|
|
|
|
# 特征：直接存你压缩后的 512bit 结果，不搞历史缓存
|
|
visual_hash: bytes # 512bit 视觉特征 (用于外观检索)
|
|
semantic_hash: bytes # 512bit 语义特征 (用于类别对齐)
|
|
|
|
# Debug 必备：极简的生命周期管理，防止满屏"幽灵节点"
|
|
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")
|