Files
HVideoTool/hvideotool/core/detection/composite.py
T

52 lines
1.9 KiB
Python

"""Composite detector: runs several detectors and merges their results.
Used for the "combined" mode = YOLO (mosaic) + classic-CV (black bars / blur).
Detections from all sub-detectors are concatenated, then de-duplicated by IoU
(higher score wins) so overlapping hits from different detectors don't stack.
"""
from __future__ import annotations
from ..video.frame import Frame
from .base import Detector
from .types import Detection
class CompositeDetector(Detector):
def __init__(self, detectors: list[Detector], iou_threshold: float = 0.6) -> None:
if not detectors:
raise ValueError("CompositeDetector requires at least one detector")
self._detectors = detectors
self._iou = iou_threshold
@property
def name(self) -> str:
return "Composite(" + " + ".join(d.name for d in self._detectors) + ")"
def detect(self, frame: Frame) -> list[Detection]:
merged: list[Detection] = []
for detector in self._detectors:
try:
merged += detector.detect(frame)
except Exception: # noqa: BLE001 - one detector failing must not kill the frame
continue
return self._dedup(merged)
def _dedup(self, dets: list[Detection]) -> list[Detection]:
dets = sorted(dets, key=lambda d: d.score, reverse=True)
kept: list[Detection] = []
for d in dets:
if all(self._iou_of(d.bbox, k.bbox) < self._iou for k in kept):
kept.append(d)
return kept
@staticmethod
def _iou_of(a: tuple[int, int, int, int], b: tuple[int, int, int, int]) -> float:
ax, ay, aw, ah = a
bx, by, bw, bh = b
ix, iy = max(ax, bx), max(ay, by)
ix2, iy2 = min(ax + aw, bx + bw), min(ay + ah, by + bh)
inter = max(0, ix2 - ix) * max(0, iy2 - iy)
union = aw * ah + bw * bh - inter
return inter / union if union > 0 else 0.0