1038 lines
46 KiB
Python
1038 lines
46 KiB
Python
from __future__ import annotations
|
|
|
|
import uuid
|
|
from datetime import UTC, datetime
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
from geoalchemy2.shape import from_shape, to_shape
|
|
from shapely.geometry import MultiPolygon, Polygon, mapping, shape
|
|
from shapely.validation import make_valid
|
|
from sqlalchemy import func
|
|
|
|
from app.core.config import Settings, get_settings
|
|
from app.core.errors import AppError
|
|
from app.models import AnalysisRun, Dataset, Job, Project, Segmentation, VectorFeature
|
|
from app.schemas.segmentation import (
|
|
SegmentationListResponse,
|
|
SegmentationRead,
|
|
SegmentationRunListResponse,
|
|
SegmentationRunRead,
|
|
SegmentationRunResponse,
|
|
)
|
|
from app.services.detection_georeferencing import pixel_points_to_epsg4326_polygon
|
|
from app.services.detection_metrics_service import DetectionMetricsService
|
|
from app.services.detection_qa_service import DetectionQaService
|
|
from app.services.detection_service import DetectionService
|
|
from app.services.dataset_consumption_gate_service import DatasetConsumptionGate
|
|
from app.services.model_registry_service import ModelRegistryService
|
|
from app.services.qa_service import QaService
|
|
from app.services.quality_service import QualityService
|
|
from app.services.runtime_model_provenance_service import RuntimeModelProvenance, RuntimeModelProvenanceService
|
|
from app.services.segmentation_adapter import (
|
|
FixtureSegmentationAdapter,
|
|
SamSegmentationAdapter,
|
|
YoloSegmentationAdapter,
|
|
)
|
|
from app.services.tile_manifest_service import TileManifestService
|
|
|
|
|
|
class SegmentationService:
|
|
@staticmethod
|
|
def _now() -> datetime:
|
|
return datetime.now(UTC)
|
|
|
|
@staticmethod
|
|
def run_segmentation(
|
|
db,
|
|
project_id: uuid.UUID,
|
|
dataset_id: uuid.UUID,
|
|
model_id: str,
|
|
confidence_threshold: float,
|
|
class_filter: list[str] | None = None,
|
|
tile_manifest_path: str | None = None,
|
|
parameters_json: dict[str, Any] | None = None,
|
|
settings: Settings | None = None,
|
|
yolo_seg_adapter_class: type[YoloSegmentationAdapter] = YoloSegmentationAdapter,
|
|
sam_adapter_class: type[SamSegmentationAdapter] = SamSegmentationAdapter,
|
|
existing_job: Job | None = None,
|
|
) -> SegmentationRunResponse:
|
|
parameters = dict(parameters_json or {})
|
|
resolved_settings = settings or get_settings()
|
|
dataset = SegmentationService._validate_run_request(db, project_id=project_id, dataset_id=dataset_id)
|
|
|
|
model = ModelRegistryService.get_model_capability(
|
|
model_id,
|
|
settings=resolved_settings,
|
|
task_type="segmentation",
|
|
yolo_seg_adapter_class=yolo_seg_adapter_class,
|
|
sam_adapter_class=sam_adapter_class,
|
|
)
|
|
if model is None:
|
|
raise AppError(code="SEGMENTATION_MODEL_NOT_FOUND", message="Segmentation model not found", status_code=404)
|
|
if model.model_id == "fixture-segmenter" and parameters.get("fixture_mode") is not True:
|
|
raise AppError(
|
|
code="FIXTURE_MODE_REQUIRED",
|
|
message="Fixture segmenter requires explicit fixture_mode=true",
|
|
status_code=400,
|
|
)
|
|
configured_model_ids = {resolved_settings.yolo_seg_model_id, resolved_settings.sam_model_id}
|
|
if model.model_id in configured_model_ids and model.configured and not tile_manifest_path:
|
|
raise AppError(
|
|
code="SEGMENTATION_TILE_MANIFEST_REQUIRED",
|
|
message="Configured segmentation inference requires an existing raster tile manifest path",
|
|
status_code=400,
|
|
)
|
|
|
|
# Production segmentation must consume only a passed, complete and
|
|
# non-quarantined dataset. The fixture segmenter is QA/test-only and
|
|
# cannot be classified as production inference.
|
|
if model.model_id == "fixture-segmenter":
|
|
DatasetConsumptionGate.assert_eligible(
|
|
dataset,
|
|
purpose="quality_assessment",
|
|
fixture_mode=True,
|
|
)
|
|
elif model.model_id in configured_model_ids and model.configured:
|
|
DatasetConsumptionGate.assert_eligible(dataset, purpose="production_inference")
|
|
|
|
run_parameters = {
|
|
"model_id": model.model_id,
|
|
"confidence_threshold": confidence_threshold,
|
|
"class_filter": class_filter or [],
|
|
"tile_manifest_path": tile_manifest_path,
|
|
"parameters_json": parameters,
|
|
}
|
|
job = SegmentationService._create_job(db, project_id, dataset_id, run_parameters, existing_job=existing_job)
|
|
analysis_run = SegmentationService._create_analysis_run(db, project_id, dataset_id, job.id, model, run_parameters)
|
|
|
|
if not model.configured:
|
|
message = model.limitation_message
|
|
SegmentationService._mark_failed(
|
|
db,
|
|
analysis_run,
|
|
job,
|
|
code="SEGMENTATION_MODEL_UNAVAILABLE",
|
|
message=message,
|
|
)
|
|
return SegmentationRunResponse(
|
|
analysis_run_id=analysis_run.id,
|
|
job_id=job.id,
|
|
project_id=project_id,
|
|
dataset_id=dataset_id,
|
|
model_id=model.model_id,
|
|
status="failed",
|
|
segmentation_count=0,
|
|
error_code="SEGMENTATION_MODEL_UNAVAILABLE",
|
|
message=message,
|
|
)
|
|
|
|
if model.model_id == "fixture-segmenter":
|
|
try:
|
|
segmentations = SegmentationService._persist_fixture_segmentations(
|
|
db=db,
|
|
project_id=project_id,
|
|
dataset_id=dataset_id,
|
|
analysis_run=analysis_run,
|
|
job=job,
|
|
model_name=model.model_id,
|
|
model_version=model.version,
|
|
raw_segmentations=parameters.get("fixture_segmentations"),
|
|
confidence_threshold=confidence_threshold,
|
|
class_filter=class_filter or [],
|
|
settings=resolved_settings,
|
|
)
|
|
except Exception as exc:
|
|
# A rejected fixture payload must never leave the run stuck in "running".
|
|
SegmentationService._fail_run_after_exception(db, analysis_run, job, exc, fallback_code="SEGMENTATION_INTERNAL_ERROR")
|
|
raise
|
|
SegmentationService._mark_success(db, analysis_run, job, segmentation_count=len(segmentations))
|
|
return SegmentationRunResponse(
|
|
analysis_run_id=analysis_run.id,
|
|
job_id=job.id,
|
|
project_id=project_id,
|
|
dataset_id=dataset_id,
|
|
model_id=model.model_id,
|
|
status="success",
|
|
segmentation_count=len(segmentations),
|
|
message="Fixture segmentations persisted.",
|
|
)
|
|
|
|
if model.model_id in configured_model_ids:
|
|
try:
|
|
segmentations, postprocess_summary = SegmentationService._run_configured_segmentation(
|
|
db=db,
|
|
project_id=project_id,
|
|
dataset_id=dataset_id,
|
|
analysis_run=analysis_run,
|
|
job=job,
|
|
model_name=model.model_id,
|
|
model_version=model.version,
|
|
tile_manifest_path=tile_manifest_path,
|
|
confidence_threshold=confidence_threshold,
|
|
class_filter=class_filter or [],
|
|
settings=resolved_settings,
|
|
yolo_seg_adapter_class=yolo_seg_adapter_class,
|
|
sam_adapter_class=sam_adapter_class,
|
|
)
|
|
except AppError as exc:
|
|
SegmentationService._mark_failed(db, analysis_run, job, code=exc.code, message=exc.message)
|
|
return SegmentationRunResponse(
|
|
analysis_run_id=analysis_run.id,
|
|
job_id=job.id,
|
|
project_id=project_id,
|
|
dataset_id=dataset_id,
|
|
model_id=model.model_id,
|
|
status="failed",
|
|
segmentation_count=0,
|
|
error_code=exc.code,
|
|
message=exc.message,
|
|
)
|
|
except Exception as exc:
|
|
# An unexpected inference error must never leave the run stuck in "running".
|
|
SegmentationService._fail_run_after_exception(db, analysis_run, job, exc, fallback_code="SEGMENTATION_INTERNAL_ERROR")
|
|
raise
|
|
SegmentationService._mark_success(
|
|
db,
|
|
analysis_run,
|
|
job,
|
|
segmentation_count=len(segmentations),
|
|
extra_result=postprocess_summary,
|
|
)
|
|
return SegmentationRunResponse(
|
|
analysis_run_id=analysis_run.id,
|
|
job_id=job.id,
|
|
project_id=project_id,
|
|
dataset_id=dataset_id,
|
|
model_id=model.model_id,
|
|
status="success",
|
|
segmentation_count=len(segmentations),
|
|
message="Configured segmentation inference persisted georeferenced masks.",
|
|
)
|
|
|
|
SegmentationService._mark_failed(
|
|
db,
|
|
analysis_run,
|
|
job,
|
|
code="SEGMENTATION_MODEL_UNAVAILABLE",
|
|
message="Segmentation model is unavailable",
|
|
)
|
|
raise AppError(code="SEGMENTATION_MODEL_UNAVAILABLE", message="Segmentation model is unavailable", status_code=503)
|
|
|
|
@staticmethod
|
|
def _fail_run_after_exception(db, analysis_run: AnalysisRun, job: Job, exc: Exception, fallback_code: str) -> None:
|
|
try:
|
|
db.rollback()
|
|
except Exception:
|
|
pass
|
|
code = getattr(exc, "code", None) or fallback_code
|
|
message = getattr(exc, "message", None) or "Unexpected internal error during analysis run"
|
|
try:
|
|
SegmentationService._mark_failed(db, analysis_run, job, code=str(code), message=str(message))
|
|
except Exception:
|
|
pass
|
|
|
|
@staticmethod
|
|
def get_run(db, analysis_run_id: uuid.UUID) -> SegmentationRunRead:
|
|
run = db.get(AnalysisRun, analysis_run_id)
|
|
if not run or run.analysis_type != "segmentation":
|
|
raise AppError(code="SEGMENTATION_RUN_NOT_FOUND", message="Segmentation run not found", status_code=404)
|
|
return SegmentationRunRead.model_validate(run)
|
|
|
|
@staticmethod
|
|
def list_runs(
|
|
db,
|
|
*,
|
|
project_id: uuid.UUID | None = None,
|
|
dataset_id: uuid.UUID | None = None,
|
|
limit: int | None = None,
|
|
offset: int = 0,
|
|
) -> SegmentationRunListResponse:
|
|
query = db.query(AnalysisRun).filter(AnalysisRun.analysis_type == "segmentation")
|
|
if project_id is not None:
|
|
query = query.filter(AnalysisRun.project_id == project_id)
|
|
if dataset_id is not None:
|
|
query = query.filter(AnalysisRun.dataset_id == dataset_id)
|
|
rows = query.order_by(AnalysisRun.created_at.desc()).all()
|
|
# Runs accumulate with every analysis; the panel draws the recent ones.
|
|
resolved_limit = DetectionService.DEFAULT_RUN_LIST_LIMIT if limit is None else int(limit)
|
|
page, total, truncated = DetectionService.paginate(rows, limit=resolved_limit, offset=offset)
|
|
return SegmentationRunListResponse(
|
|
items=[SegmentationRunRead.model_validate(row) for row in page],
|
|
total=total,
|
|
limit=resolved_limit,
|
|
offset=max(0, int(offset)),
|
|
truncated=truncated,
|
|
)
|
|
|
|
@staticmethod
|
|
def list_segmentations(
|
|
db,
|
|
analysis_run_id: uuid.UUID | None = None,
|
|
*,
|
|
dataset_id: uuid.UUID | None = None,
|
|
class_name: str | None = None,
|
|
min_confidence: float | None = None,
|
|
limit: int | None = None,
|
|
offset: int = 0,
|
|
) -> SegmentationListResponse:
|
|
if analysis_run_id is not None:
|
|
run = db.get(AnalysisRun, analysis_run_id)
|
|
if not run or run.analysis_type != "segmentation":
|
|
raise AppError(code="SEGMENTATION_RUN_NOT_FOUND", message="Segmentation run not found", status_code=404)
|
|
rows = SegmentationService._query_segmentation_rows(
|
|
db,
|
|
analysis_run_id=analysis_run_id,
|
|
dataset_id=dataset_id,
|
|
class_name=class_name,
|
|
min_confidence=min_confidence,
|
|
)
|
|
resolved_limit = DetectionService.DEFAULT_RESULT_LIMIT if limit is None else int(limit)
|
|
page, total, truncated = DetectionService.paginate(
|
|
rows,
|
|
limit=resolved_limit,
|
|
offset=offset,
|
|
)
|
|
return SegmentationListResponse(
|
|
items=[SegmentationRead.model_validate(row) for row in page],
|
|
total=total,
|
|
limit=resolved_limit,
|
|
offset=max(0, int(offset)),
|
|
truncated=truncated,
|
|
)
|
|
|
|
@staticmethod
|
|
def get_segmentation(db, segmentation_id: uuid.UUID) -> SegmentationRead:
|
|
segmentation = db.get(Segmentation, segmentation_id)
|
|
if not segmentation:
|
|
raise AppError(code="SEGMENTATION_NOT_FOUND", message="Segmentation not found", status_code=404)
|
|
return SegmentationRead.model_validate(segmentation)
|
|
|
|
@staticmethod
|
|
def segmentations_to_geojson(
|
|
db,
|
|
*,
|
|
analysis_run_id: uuid.UUID | None = None,
|
|
dataset_id: uuid.UUID | None = None,
|
|
class_name: str | None = None,
|
|
min_confidence: float | None = None,
|
|
limit: int | None = None,
|
|
) -> dict[str, Any]:
|
|
rows = SegmentationService._query_segmentation_rows(
|
|
db,
|
|
analysis_run_id=analysis_run_id,
|
|
dataset_id=dataset_id,
|
|
class_name=class_name,
|
|
min_confidence=min_confidence,
|
|
)
|
|
resolved_limit = DetectionService.DEFAULT_RESULT_LIMIT if limit is None else int(limit)
|
|
segmentations, total, truncated = DetectionService.paginate(rows, limit=resolved_limit, offset=0)
|
|
return {
|
|
"type": "FeatureCollection",
|
|
"geointel_result_window": {
|
|
"feature_count": len(segmentations),
|
|
"total_feature_count": total,
|
|
"limit": resolved_limit,
|
|
"truncated": truncated,
|
|
},
|
|
"features": [
|
|
{
|
|
"type": "Feature",
|
|
"id": str(segmentation.id),
|
|
"properties": SegmentationService._segmentation_properties(segmentation),
|
|
"geometry": mapping(to_shape(segmentation.geometry)),
|
|
}
|
|
for segmentation in segmentations
|
|
],
|
|
}
|
|
|
|
@staticmethod
|
|
def compare_segmentations_with_reference(
|
|
db,
|
|
analysis_run_id: uuid.UUID,
|
|
reference_dataset_id: uuid.UUID,
|
|
iou_threshold: float = 0.5,
|
|
class_name: str | None = None,
|
|
min_confidence: float | None = None,
|
|
calibration_thresholds: list[float] | None = None,
|
|
) -> dict[str, Any]:
|
|
run = db.get(AnalysisRun, analysis_run_id)
|
|
if not run or run.analysis_type != "segmentation":
|
|
raise AppError(code="SEGMENTATION_RUN_NOT_FOUND", message="Segmentation run not found", status_code=404)
|
|
reference_dataset = db.get(Dataset, reference_dataset_id)
|
|
if not reference_dataset:
|
|
raise AppError(code="DATASET_NOT_FOUND", message="Reference dataset not found", status_code=404)
|
|
if reference_dataset.project_id != run.project_id:
|
|
raise AppError(code="INVALID_DATASET_SCOPE", message="Reference dataset does not belong to segmentation project", status_code=400)
|
|
if reference_dataset.dataset_type not in {"vector", "geojson"}:
|
|
raise AppError(code="INVALID_DATASET_TYPE", message="Reference dataset must be vector data", status_code=400)
|
|
|
|
candidate_dataset = db.get(Dataset, run.dataset_id)
|
|
if not candidate_dataset:
|
|
raise AppError(code="DATASET_NOT_FOUND", message="Segmentation source dataset not found", status_code=404)
|
|
run_parameters = run.parameters_json if isinstance(run.parameters_json, dict) else {}
|
|
fixture_parameters = run_parameters.get("parameters_json")
|
|
fixture_mode = bool(
|
|
run.model_name == "fixture-segmenter"
|
|
and isinstance(fixture_parameters, dict)
|
|
and fixture_parameters.get("fixture_mode") is True
|
|
)
|
|
DatasetConsumptionGate.assert_eligible(
|
|
candidate_dataset,
|
|
purpose="quality_assessment",
|
|
fixture_mode=fixture_mode,
|
|
)
|
|
DatasetConsumptionGate.assert_eligible(
|
|
reference_dataset,
|
|
purpose="reference_validation",
|
|
reference_task="building_validation",
|
|
)
|
|
|
|
segmentations = SegmentationService._query_segmentation_rows(
|
|
db,
|
|
analysis_run_id=analysis_run_id,
|
|
dataset_id=run.dataset_id,
|
|
class_name=class_name,
|
|
min_confidence=min_confidence,
|
|
)
|
|
if not segmentations:
|
|
raise AppError(
|
|
code="SEGMENTATIONS_NOT_FOUND",
|
|
message="Segmentation run has no persisted geometries for QA",
|
|
status_code=422,
|
|
)
|
|
# Score against the footprint the model actually saw. Without this the
|
|
# whole reference dataset is the denominator for recall, and every
|
|
# building outside the inferred tiles is counted as a miss.
|
|
manifest_path = DetectionQaService.tile_manifest_path(run_parameters)
|
|
coverage = None
|
|
if manifest_path:
|
|
settings_for_qa = get_settings()
|
|
manifest = DetectionService._load_tile_manifest(
|
|
manifest_path, settings_for_qa.yolo_max_tiles, settings_for_qa
|
|
)
|
|
coverage = DetectionQaService.build_tile_coverage(
|
|
manifest,
|
|
manifest_path=manifest_path,
|
|
expected_dataset_id=run.dataset_id,
|
|
)
|
|
|
|
reference_query = db.query(VectorFeature).filter(VectorFeature.dataset_id == reference_dataset_id)
|
|
if coverage is not None and hasattr(reference_query, "count"):
|
|
reference_raw_count = reference_query.count()
|
|
references = reference_query.filter(
|
|
func.ST_Intersects(VectorFeature.geometry, from_shape(coverage.geometry, srid=4326))
|
|
).all()
|
|
else:
|
|
references = reference_query.all()
|
|
reference_raw_count = len(references)
|
|
if reference_raw_count == 0:
|
|
raise AppError(
|
|
code="REFERENCE_FEATURES_NOT_FOUND",
|
|
message="Reference dataset has no persisted vector features for QA",
|
|
status_code=422,
|
|
)
|
|
|
|
raw_candidate_geometries = [
|
|
(
|
|
{"id": str(row.id), "class_name": row.class_name, "confidence": row.confidence},
|
|
to_shape(row.geometry),
|
|
)
|
|
for row in segmentations
|
|
]
|
|
raw_reference_geometries = [
|
|
({"id": str(row.id), "feature_class": row.feature_class}, to_shape(row.geometry)) for row in references
|
|
]
|
|
candidate_geometries = raw_candidate_geometries
|
|
reference_geometries = raw_reference_geometries
|
|
|
|
coverage_summary: dict[str, Any] = {
|
|
"applied": False,
|
|
"mode": "unbounded_no_manifest",
|
|
"manifest_path": None,
|
|
"tile_count": 0,
|
|
"source_crs_values": [],
|
|
"candidate_raw_count": len(raw_candidate_geometries),
|
|
"candidate_evaluated_count": len(raw_candidate_geometries),
|
|
"candidate_excluded_outside_count": 0,
|
|
"candidate_clipped_boundary_count": 0,
|
|
"reference_raw_count": reference_raw_count,
|
|
"reference_evaluated_count": len(raw_reference_geometries),
|
|
"reference_excluded_outside_count": 0,
|
|
"reference_clipped_boundary_count": 0,
|
|
}
|
|
coverage_warnings: list[str] = []
|
|
if coverage is not None:
|
|
candidate_population = DetectionQaService.filter_population(raw_candidate_geometries, coverage)
|
|
reference_population = DetectionQaService.filter_population(
|
|
raw_reference_geometries,
|
|
coverage,
|
|
raw_count=reference_raw_count,
|
|
)
|
|
candidate_geometries = candidate_population.geometries
|
|
reference_geometries = reference_population.geometries
|
|
if not reference_geometries:
|
|
raise AppError(
|
|
code="REFERENCE_FEATURES_OUTSIDE_COVERAGE",
|
|
message="Reference dataset has no polygon features inside persisted inference tile coverage",
|
|
status_code=422,
|
|
)
|
|
coverage_summary = {
|
|
"applied": True,
|
|
"mode": "persisted_tile_manifest_union",
|
|
"manifest_path": coverage.manifest_path,
|
|
"tile_count": coverage.tile_count,
|
|
"source_crs_values": list(coverage.source_crs_values),
|
|
"candidate_raw_count": candidate_population.raw_count,
|
|
"candidate_evaluated_count": candidate_population.evaluated_count,
|
|
"candidate_excluded_outside_count": candidate_population.excluded_outside_count,
|
|
"candidate_clipped_boundary_count": candidate_population.clipped_boundary_count,
|
|
"reference_raw_count": reference_population.raw_count,
|
|
"reference_evaluated_count": reference_population.evaluated_count,
|
|
"reference_excluded_outside_count": reference_population.excluded_outside_count,
|
|
"reference_clipped_boundary_count": reference_population.clipped_boundary_count,
|
|
}
|
|
coverage_warnings.append(
|
|
"QA populations were clipped to the union of persisted inference tile footprints before matching."
|
|
)
|
|
|
|
evidence = QaService._match_io_u_evidence(
|
|
candidate_geometries,
|
|
reference_geometries,
|
|
iou_threshold,
|
|
)
|
|
# Segmentation confidences rank the same way detections do, so the same
|
|
# threshold-independent view applies. Detection had it and segmentation
|
|
# did not, which made the two QA panels answer different questions.
|
|
precision_recall_curve = DetectionMetricsService.precision_recall_curve(
|
|
candidate_geometries,
|
|
reference_geometries,
|
|
iou_threshold=iou_threshold,
|
|
)
|
|
calibration_sweep = DetectionMetricsService.calibration_sweep(
|
|
precision_recall_curve,
|
|
thresholds=list(calibration_thresholds or []),
|
|
)
|
|
mean_iou = None if not evidence.match_iou_values else sum(evidence.match_iou_values) / len(evidence.match_iou_values)
|
|
precision = evidence.matches / (evidence.matches + evidence.false_positives) if evidence.matches + evidence.false_positives > 0 else None
|
|
recall = evidence.matches / (evidence.matches + evidence.false_negatives) if evidence.matches + evidence.false_negatives > 0 else None
|
|
f1_score = None
|
|
if precision is not None and recall is not None:
|
|
f1_score = (2 * precision * recall) / (precision + recall) if precision + recall > 0 else 0.0
|
|
status = "unsupported" if evidence.unsupported else "ok"
|
|
quality_check = QualityService.persist_quality_check(
|
|
db=db,
|
|
project_id=run.project_id,
|
|
analysis_run_id=analysis_run_id,
|
|
candidate_dataset_id=run.dataset_id,
|
|
reference_dataset_id=reference_dataset_id,
|
|
check_type="segmentations_vs_reference",
|
|
status=status,
|
|
score=f1_score,
|
|
parameters={
|
|
"analysis_run_id": str(analysis_run_id),
|
|
"reference_dataset_id": str(reference_dataset_id),
|
|
"iou_threshold": iou_threshold,
|
|
"class_name": class_name,
|
|
"min_confidence": min_confidence,
|
|
"coverage_policy": coverage_summary["mode"],
|
|
},
|
|
findings={
|
|
"matches": evidence.matches,
|
|
"false_positives": evidence.false_positives,
|
|
"false_negatives": evidence.false_negatives,
|
|
"warnings": coverage_warnings + evidence.warnings,
|
|
"unsupported_geometry": evidence.unsupported,
|
|
"coverage": coverage_summary,
|
|
"precision_recall_curve": precision_recall_curve,
|
|
"calibration_sweep": calibration_sweep,
|
|
"match_evidence": evidence.match_evidence,
|
|
"false_positive_evidence": evidence.false_positive_evidence,
|
|
"false_negative_evidence": evidence.false_negative_evidence,
|
|
},
|
|
metrics={
|
|
"precision": precision,
|
|
"recall": recall,
|
|
"f1": f1_score,
|
|
"mean_iou": mean_iou,
|
|
"false_positive_count": evidence.false_positives,
|
|
"false_negative_count": evidence.false_negatives,
|
|
"average_precision": precision_recall_curve["average_precision"],
|
|
"best_f1": precision_recall_curve["best_f1"],
|
|
"best_f1_threshold": precision_recall_curve["best_f1_threshold"],
|
|
},
|
|
)
|
|
return {
|
|
"status": status,
|
|
"quality_check_id": str(quality_check.id),
|
|
"analysis_run_id": str(analysis_run_id),
|
|
"reference_dataset_id": str(reference_dataset_id),
|
|
"candidate_feature_count": len(candidate_geometries),
|
|
"reference_feature_count": len(reference_geometries),
|
|
"candidate_feature_count_raw": len(raw_candidate_geometries),
|
|
"reference_feature_count_raw": reference_raw_count,
|
|
"matches": evidence.matches,
|
|
"false_positives": evidence.false_positives,
|
|
"false_negatives": evidence.false_negatives,
|
|
"precision": precision,
|
|
"recall": recall,
|
|
"f1_score": f1_score,
|
|
"mean_iou": mean_iou,
|
|
"iou_threshold": iou_threshold,
|
|
"warnings": coverage_warnings + evidence.warnings,
|
|
"coverage": coverage_summary,
|
|
"precision_recall_curve": precision_recall_curve,
|
|
"calibration_sweep": calibration_sweep,
|
|
"match_evidence": evidence.match_evidence,
|
|
"false_positive_evidence": evidence.false_positive_evidence,
|
|
"false_negative_evidence": evidence.false_negative_evidence,
|
|
}
|
|
|
|
@staticmethod
|
|
def mask_artifact_path(storage_root: str, project_id: uuid.UUID, analysis_run_id: uuid.UUID, tile_index: int | None, segmentation_id: uuid.UUID) -> str:
|
|
tile_folder = f"tile_{tile_index if tile_index is not None else 0}"
|
|
return (Path(storage_root) / "masks" / str(project_id) / str(analysis_run_id) / tile_folder / f"mask_{segmentation_id}.png").as_posix()
|
|
|
|
@staticmethod
|
|
def _create_job(
|
|
db,
|
|
project_id: uuid.UUID,
|
|
dataset_id: uuid.UUID,
|
|
parameters: dict[str, Any],
|
|
existing_job: Job | None = None,
|
|
) -> Job:
|
|
if existing_job is not None:
|
|
# Reuse the queued job so the operator polls one identifier.
|
|
existing_job.status = "running"
|
|
existing_job.dataset_id = dataset_id
|
|
existing_job.input_dataset_id = dataset_id
|
|
existing_job.parameters_json = {**(existing_job.parameters_json or {}), **parameters}
|
|
existing_job.started_at = SegmentationService._now()
|
|
db.add(existing_job)
|
|
db.commit()
|
|
db.refresh(existing_job)
|
|
return existing_job
|
|
job = Job(
|
|
id=uuid.uuid4(),
|
|
job_type="segmentation.run",
|
|
status="running",
|
|
project_id=project_id,
|
|
dataset_id=dataset_id,
|
|
input_dataset_id=dataset_id,
|
|
parameters_json=parameters,
|
|
started_at=SegmentationService._now(),
|
|
)
|
|
db.add(job)
|
|
db.commit()
|
|
db.refresh(job)
|
|
return job
|
|
|
|
@staticmethod
|
|
def _validate_run_request(db, *, project_id: uuid.UUID, dataset_id: uuid.UUID) -> Dataset:
|
|
project = db.get(Project, project_id)
|
|
if not project:
|
|
raise AppError(code="PROJECT_NOT_FOUND", message="Project not found", status_code=404)
|
|
dataset = db.get(Dataset, dataset_id)
|
|
if not dataset or dataset.project_id != project_id:
|
|
raise AppError(code="DATASET_NOT_FOUND", message="Dataset not found", status_code=404)
|
|
if dataset.dataset_type != "raster":
|
|
raise AppError(
|
|
code="INVALID_DATASET_TYPE",
|
|
message="Segmentation requires a raster dataset",
|
|
details={"dataset_type": dataset.dataset_type},
|
|
status_code=400,
|
|
)
|
|
return dataset
|
|
|
|
@staticmethod
|
|
def enqueue_segmentation(
|
|
db,
|
|
project_id: uuid.UUID,
|
|
dataset_id: uuid.UUID,
|
|
model_id: str,
|
|
confidence_threshold: float,
|
|
class_filter: list[str] | None = None,
|
|
tile_manifest_path: str | None = None,
|
|
parameters_json: dict[str, Any] | None = None,
|
|
) -> Job:
|
|
"""Accept a segmentation run for background execution."""
|
|
|
|
SegmentationService._validate_run_request(db, project_id=project_id, dataset_id=dataset_id)
|
|
job = Job(
|
|
id=uuid.uuid4(),
|
|
job_type="segmentation.run",
|
|
status="queued",
|
|
project_id=project_id,
|
|
dataset_id=dataset_id,
|
|
input_dataset_id=dataset_id,
|
|
parameters_json={
|
|
"project_id": str(project_id),
|
|
"dataset_id": str(dataset_id),
|
|
"model_id": model_id,
|
|
"confidence_threshold": confidence_threshold,
|
|
"class_filter": class_filter or [],
|
|
"tile_manifest_path": tile_manifest_path,
|
|
"parameters_json": dict(parameters_json or {}),
|
|
},
|
|
)
|
|
db.add(job)
|
|
db.commit()
|
|
db.refresh(job)
|
|
return job
|
|
|
|
@staticmethod
|
|
def _create_analysis_run(db, project_id, dataset_id, job_id, model, parameters: dict[str, Any]) -> AnalysisRun:
|
|
analysis_run = AnalysisRun(
|
|
id=uuid.uuid4(),
|
|
project_id=project_id,
|
|
dataset_id=dataset_id,
|
|
job_id=job_id,
|
|
analysis_type="segmentation",
|
|
status="running",
|
|
model_name=model.model_id,
|
|
model_version=model.version,
|
|
parameters_json=parameters,
|
|
started_at=SegmentationService._now(),
|
|
)
|
|
db.add(analysis_run)
|
|
db.commit()
|
|
db.refresh(analysis_run)
|
|
return analysis_run
|
|
|
|
@staticmethod
|
|
def _mark_failed(db, analysis_run: AnalysisRun, job: Job, code: str, message: str) -> None:
|
|
result = {"error_code": code, "message": message, "segmentation_count": 0}
|
|
analysis_run.status = "failed"
|
|
analysis_run.finished_at = SegmentationService._now()
|
|
analysis_run.error_message = message
|
|
analysis_run.result_json = result
|
|
job.status = "failed"
|
|
job.finished_at = analysis_run.finished_at
|
|
job.error_message = message
|
|
job.result_json = result
|
|
db.add(analysis_run)
|
|
db.add(job)
|
|
db.commit()
|
|
db.refresh(analysis_run)
|
|
db.refresh(job)
|
|
|
|
@staticmethod
|
|
def _mark_success(db, analysis_run: AnalysisRun, job: Job, segmentation_count: int, extra_result: dict[str, Any] | None = None) -> None:
|
|
result = {"segmentation_count": segmentation_count}
|
|
if extra_result:
|
|
result.update(extra_result)
|
|
analysis_run.status = "success"
|
|
analysis_run.finished_at = SegmentationService._now()
|
|
analysis_run.result_json = result
|
|
job.status = "success"
|
|
job.finished_at = analysis_run.finished_at
|
|
job.result_json = result
|
|
db.add(analysis_run)
|
|
db.add(job)
|
|
db.commit()
|
|
db.refresh(analysis_run)
|
|
db.refresh(job)
|
|
|
|
@staticmethod
|
|
def _run_configured_segmentation(
|
|
db,
|
|
project_id: uuid.UUID,
|
|
dataset_id: uuid.UUID,
|
|
analysis_run: AnalysisRun,
|
|
job: Job,
|
|
model_name: str,
|
|
model_version: str | None,
|
|
tile_manifest_path: str | None,
|
|
confidence_threshold: float,
|
|
class_filter: list[str],
|
|
settings: Settings,
|
|
yolo_seg_adapter_class: type[YoloSegmentationAdapter],
|
|
sam_adapter_class: type[SamSegmentationAdapter],
|
|
) -> tuple[list[Segmentation], dict[str, Any]]:
|
|
manifest = DetectionService._load_tile_manifest(tile_manifest_path, settings.yolo_max_tiles, settings)
|
|
dataset = db.get(Dataset, dataset_id)
|
|
if dataset is None:
|
|
raise AppError(code="DATASET_NOT_FOUND", message="Dataset not found", status_code=404)
|
|
manifest_binding = TileManifestService.validate_for_inference(
|
|
db,
|
|
dataset,
|
|
manifest,
|
|
manifest_path=tile_manifest_path or "",
|
|
settings=settings,
|
|
error_prefix="SEGMENTATION",
|
|
)
|
|
DetectionService._attach_tile_manifest_binding(analysis_run, job, manifest_binding)
|
|
if model_name == settings.sam_model_id:
|
|
model_path = Path(settings.sam_model_path or "").expanduser()
|
|
allowed_frameworks = ("ultralytics/sam", "sam", "ultralytics", "pytorch")
|
|
adapter = sam_adapter_class(settings)
|
|
else:
|
|
model_path = Path(settings.yolo_seg_model_path or "").expanduser()
|
|
allowed_frameworks = ("ultralytics/pytorch", "ultralytics", "pytorch")
|
|
adapter = yolo_seg_adapter_class(settings)
|
|
runtime_model_provenance = RuntimeModelProvenanceService.validate_for_production_runtime(
|
|
db=db,
|
|
model_path=model_path,
|
|
model_id=model_name,
|
|
task_type="segmentation",
|
|
expected_model_version=model_version,
|
|
allowed_frameworks=allowed_frameworks,
|
|
)
|
|
SegmentationService._attach_runtime_model_provenance(
|
|
analysis_run,
|
|
job,
|
|
runtime_model_provenance,
|
|
)
|
|
model = adapter.load_model(model_path)
|
|
|
|
allowed_classes = {DetectionService._canonical_class_name(value) for value in class_filter if DetectionService._canonical_class_name(value)}
|
|
manifest_crs = DetectionService._require_manifest_crs(manifest)
|
|
candidates: list[dict[str, Any]] = []
|
|
for tile in manifest["tiles"]:
|
|
tile_path = DetectionService._resolve_tile_path(tile, Path(tile_manifest_path or "").expanduser(), settings)
|
|
for raw in adapter.predict_tile(model, tile_path, confidence_threshold):
|
|
model_class_name = str(raw.get("class_name") or "").strip()
|
|
class_name = DetectionService._canonical_class_name(model_class_name)
|
|
confidence = raw.get("confidence")
|
|
confidence = float(confidence) if confidence is not None else None
|
|
if allowed_classes and class_name not in allowed_classes:
|
|
continue
|
|
if confidence is not None and confidence < confidence_threshold:
|
|
continue
|
|
points = raw.get("points")
|
|
if not isinstance(points, list) or len(points) < 3:
|
|
continue
|
|
geometry = pixel_points_to_epsg4326_polygon(points=points, tile=tile, crs=tile.get("crs") or manifest_crs)
|
|
properties = dict(raw.get("properties") or {})
|
|
if model_class_name and model_class_name != class_name:
|
|
properties.setdefault("model_class_name", model_class_name)
|
|
candidates.append(
|
|
{
|
|
"class_name": class_name,
|
|
"confidence": confidence if confidence is not None else 0.0,
|
|
"reported_confidence": confidence,
|
|
"geometry": geometry,
|
|
"bbox": raw.get("bbox"),
|
|
"source_tile_path": str(tile_path),
|
|
"tile_index": tile.get("index"),
|
|
"properties": {**properties, "tile_index": tile.get("index")},
|
|
}
|
|
)
|
|
filtered_candidates = DetectionService._suppress_duplicate_candidates(
|
|
candidates,
|
|
iou_threshold=float(settings.segmentation_duplicate_iou_threshold),
|
|
containment_threshold=float(settings.segmentation_containment_nms_threshold),
|
|
)
|
|
persisted: list[Segmentation] = []
|
|
for candidate in filtered_candidates:
|
|
geometry = candidate["geometry"]
|
|
if isinstance(geometry, Polygon):
|
|
geometry = MultiPolygon([geometry])
|
|
bbox = candidate.get("bbox")
|
|
bbox_json = None
|
|
if isinstance(bbox, list) and len(bbox) == 4:
|
|
bbox_json = {
|
|
"x_min": float(bbox[0]),
|
|
"y_min": float(bbox[1]),
|
|
"x_max": float(bbox[2]),
|
|
"y_max": float(bbox[3]),
|
|
}
|
|
segmentation = Segmentation(
|
|
id=uuid.uuid4(),
|
|
project_id=project_id,
|
|
dataset_id=dataset_id,
|
|
analysis_run_id=analysis_run.id,
|
|
job_id=job.id,
|
|
model_name=model_name,
|
|
model_version=model_version,
|
|
class_name=candidate["class_name"],
|
|
confidence=candidate["reported_confidence"],
|
|
geometry=from_shape(geometry, srid=4326),
|
|
bbox_json=bbox_json,
|
|
area_m2=SegmentationService._geodesic_area_m2(geometry),
|
|
mask_path=None,
|
|
source_tile_path=candidate["source_tile_path"],
|
|
tile_index=candidate["tile_index"] if isinstance(candidate["tile_index"], int) else None,
|
|
properties_json=candidate["properties"],
|
|
provenance_json={
|
|
"inference": "local",
|
|
"model_id": model_name,
|
|
"tile_manifest_path": str(Path(tile_manifest_path or "").expanduser()),
|
|
"tile_index": candidate["tile_index"],
|
|
"device": settings.yolo_device,
|
|
"runtime_model_provenance": runtime_model_provenance.as_dict(),
|
|
},
|
|
)
|
|
db.add(segmentation)
|
|
persisted.append(segmentation)
|
|
db.commit()
|
|
for segmentation in persisted:
|
|
db.refresh(segmentation)
|
|
return persisted, {
|
|
"raw_segmentation_count": len(candidates),
|
|
"suppressed_segmentation_count": len(candidates) - len(filtered_candidates),
|
|
"duplicate_iou_threshold": float(settings.segmentation_duplicate_iou_threshold),
|
|
"containment_suppression_threshold": float(settings.segmentation_containment_nms_threshold),
|
|
"tile_manifest_path": str(Path(tile_manifest_path or "").expanduser()),
|
|
"tile_manifest_binding": manifest_binding,
|
|
"runtime_model_provenance": runtime_model_provenance.as_dict(),
|
|
}
|
|
|
|
@staticmethod
|
|
def _attach_runtime_model_provenance(
|
|
analysis_run: AnalysisRun,
|
|
job: Job,
|
|
provenance: RuntimeModelProvenance,
|
|
) -> None:
|
|
"""Record immutable model evidence with a configured segmentation run."""
|
|
|
|
evidence = provenance.as_dict()
|
|
analysis_parameters = dict(analysis_run.parameters_json or {})
|
|
analysis_parameters["runtime_model_provenance"] = evidence
|
|
analysis_run.parameters_json = analysis_parameters
|
|
job_parameters = dict(job.parameters_json or {})
|
|
job_parameters["runtime_model_provenance"] = evidence
|
|
job.parameters_json = job_parameters
|
|
|
|
@staticmethod
|
|
def _geodesic_area_m2(geometry: MultiPolygon | Polygon) -> float | None:
|
|
try:
|
|
from pyproj import Geod
|
|
|
|
area, _ = Geod(ellps="WGS84").geometry_area_perimeter(geometry)
|
|
return abs(float(area))
|
|
except Exception:
|
|
return None
|
|
|
|
@staticmethod
|
|
def _persist_fixture_segmentations(
|
|
db,
|
|
project_id: uuid.UUID,
|
|
dataset_id: uuid.UUID,
|
|
analysis_run: AnalysisRun,
|
|
job: Job,
|
|
model_name: str,
|
|
model_version: str | None,
|
|
raw_segmentations: Any,
|
|
confidence_threshold: float,
|
|
class_filter: list[str],
|
|
settings: Settings,
|
|
) -> list[Segmentation]:
|
|
if not isinstance(raw_segmentations, list):
|
|
raise AppError(code="INVALID_FIXTURE_SEGMENTATIONS", message="fixture_segmentations must be a list", status_code=400)
|
|
adapter = FixtureSegmentationAdapter()
|
|
adapter_results = adapter.segment(raw_segmentations)
|
|
if len(adapter_results) != len(raw_segmentations):
|
|
raise AppError(code="INVALID_FIXTURE_SEGMENTATION", message="Each fixture segmentation must be an object", status_code=400)
|
|
persisted: list[Segmentation] = []
|
|
allowed_classes = set(class_filter)
|
|
for raw in adapter_results:
|
|
class_name = raw.class_name
|
|
confidence = raw.confidence
|
|
if allowed_classes and class_name not in allowed_classes:
|
|
continue
|
|
if confidence is not None and confidence < confidence_threshold:
|
|
continue
|
|
if not isinstance(raw.geometry, dict):
|
|
raise AppError(code="INVALID_FIXTURE_SEGMENTATION", message="Fixture segmentation geometry is required", status_code=400)
|
|
geometry = SegmentationService._validated_multipolygon(raw.geometry)
|
|
segmentation_id = uuid.uuid4()
|
|
mask_path = raw.mask_path or SegmentationService.mask_artifact_path(
|
|
settings.storage_root,
|
|
project_id,
|
|
analysis_run.id,
|
|
raw.tile_index,
|
|
segmentation_id,
|
|
)
|
|
segmentation = Segmentation(
|
|
id=segmentation_id,
|
|
project_id=project_id,
|
|
dataset_id=dataset_id,
|
|
analysis_run_id=analysis_run.id,
|
|
job_id=job.id,
|
|
model_name=model_name,
|
|
model_version=model_version,
|
|
class_name=class_name,
|
|
confidence=confidence,
|
|
geometry=from_shape(geometry, srid=4326),
|
|
bbox_json=raw.bbox_json,
|
|
area_m2=raw.area_m2,
|
|
mask_path=mask_path,
|
|
source_tile_path=raw.source_tile_path,
|
|
tile_index=raw.tile_index,
|
|
properties_json=raw.properties_json,
|
|
provenance_json={**dict(raw.provenance_json or {}), "fixture_mode": True},
|
|
)
|
|
db.add(segmentation)
|
|
persisted.append(segmentation)
|
|
db.commit()
|
|
for segmentation in persisted:
|
|
db.refresh(segmentation)
|
|
return persisted
|
|
|
|
@staticmethod
|
|
def _validated_multipolygon(geometry_payload: dict[str, Any]) -> MultiPolygon:
|
|
try:
|
|
geometry = shape(geometry_payload)
|
|
except Exception as exc:
|
|
raise AppError(code="INVALID_FIXTURE_GEOMETRY", message="Fixture segmentation geometry must be valid GeoJSON", status_code=400) from exc
|
|
if geometry.is_empty:
|
|
raise AppError(code="INVALID_FIXTURE_GEOMETRY", message="Fixture segmentation geometry must not be empty", status_code=400)
|
|
if not geometry.is_valid:
|
|
geometry = make_valid(geometry)
|
|
if geometry.is_empty or not geometry.is_valid:
|
|
raise AppError(code="INVALID_FIXTURE_GEOMETRY", message="Fixture segmentation geometry must be valid", status_code=400)
|
|
if isinstance(geometry, Polygon):
|
|
geometry = MultiPolygon([geometry])
|
|
if not isinstance(geometry, MultiPolygon):
|
|
raise AppError(code="INVALID_FIXTURE_GEOMETRY", message="Fixture segmentation geometry must be Polygon or MultiPolygon", status_code=400)
|
|
if geometry.area <= 0:
|
|
raise AppError(code="INVALID_FIXTURE_GEOMETRY", message="Fixture segmentation geometry must have positive area", status_code=400)
|
|
return geometry
|
|
|
|
@staticmethod
|
|
def _query_segmentation_rows(
|
|
db,
|
|
*,
|
|
analysis_run_id: uuid.UUID | None = None,
|
|
dataset_id: uuid.UUID | None = None,
|
|
class_name: str | None = None,
|
|
min_confidence: float | None = None,
|
|
) -> list[Segmentation]:
|
|
query = db.query(Segmentation)
|
|
if analysis_run_id is not None:
|
|
query = query.filter(Segmentation.analysis_run_id == analysis_run_id)
|
|
if dataset_id is not None:
|
|
query = query.filter(Segmentation.dataset_id == dataset_id)
|
|
if class_name:
|
|
query = query.filter(Segmentation.class_name == class_name)
|
|
if min_confidence is not None:
|
|
query = query.filter(Segmentation.confidence >= min_confidence)
|
|
# One transaction timestamp is shared by every row in a run, so
|
|
# ordering by it alone leaves the row order — and therefore the QA
|
|
# score — undefined. See DetectionService._query_detection_rows.
|
|
return query.order_by(
|
|
Segmentation.confidence.desc(),
|
|
Segmentation.created_at.desc(),
|
|
Segmentation.id.asc(),
|
|
).all()
|
|
|
|
@staticmethod
|
|
def _segmentation_properties(segmentation: Segmentation) -> dict[str, Any]:
|
|
return {
|
|
"segmentation_id": str(segmentation.id),
|
|
"class_name": segmentation.class_name,
|
|
"confidence": segmentation.confidence,
|
|
"area_m2": segmentation.area_m2,
|
|
"model_name": segmentation.model_name,
|
|
"model_version": segmentation.model_version,
|
|
"analysis_run_id": str(segmentation.analysis_run_id) if segmentation.analysis_run_id else None,
|
|
"dataset_id": str(segmentation.dataset_id) if segmentation.dataset_id else None,
|
|
"job_id": str(segmentation.job_id) if segmentation.job_id else None,
|
|
"source_tile_path": segmentation.source_tile_path,
|
|
"tile_index": segmentation.tile_index,
|
|
"mask_path": segmentation.mask_path,
|
|
"bbox_json": segmentation.bbox_json,
|
|
"provenance_json": segmentation.provenance_json,
|
|
}
|