Adriano/Shape_Model_2D
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: use_polarity 16-bin orientation (mod 2pi)

Browse Source 
Flag opt-in use_polarity=True su LineShapeMatcher: distingue edge
chiaro->scuro da scuro->chiaro raddoppiando i bin (8 mod pi a 16
mod 2pi). Riduce match accidentali quando il template e direzionale
ma scena ha bordo opposto (es. pezzo nero su bg chiaro vs pezzo
chiaro su bg nero).

Implementazione:
- _gradient calcola atan2 mod 2pi quando use_polarity
- _spread_bitmap usa uint16 (16 bit) invece di uint8 (8 bit)
- Nuovi kernel JIT _jit_score_bitmap_rescored_u16 e
  _jit_popcount_density_u16
- Wrapper Python score_bitmap_rescored / popcount_density fanno
  dispatch su dtype dello spread

Default off (use_polarity=False) = backward compat completo, 8 bin.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
AdrianoDev
2026-05-04 17:07:38 +02:00
parent 41976f574d
commit 84b73dc651
2 changed files with 122 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
pm2d/line_matcher.py
+33 -17
View File
@@ -46,7 +46,8 @@ from pm2d._jit_kernels import (
HAS_NUMBA,
)
N_BINS = 8 # orientamenti quantizzati modulo π
N_BINS = 8 # default: orientamento mod π (no polarity)
N_BINS_POL = 16 # use_polarity=True: orientamento mod 2π (con polarity)
def _oriented_bbox_polygon(
@@ -122,6 +123,7 @@ class LineShapeMatcher:
pyramid_levels: int = 2,
top_score_factor: float = 0.5,
n_threads: int | None = None,
use_polarity: bool = False,
) -> None:
self.num_features = num_features
self.weak_grad = weak_grad
@@ -135,6 +137,12 @@ class LineShapeMatcher:
self.pyramid_levels = max(1, pyramid_levels)
self.top_score_factor = top_score_factor
self.n_threads = n_threads or max(1, (os.cpu_count() or 2) - 1)
# Polarity-aware: 16 bin (orientamento mod 2π) usando bitmap uint16.
# Distingue edge "chiaro→scuro" da "scuro→chiaro" → 2x selettività.
# Usare quando background di scena varia (chiaro/scuro) e orientamento
# template e' direzionale.
self.use_polarity = use_polarity
self._n_bins = N_BINS_POL if use_polarity else N_BINS
self.variants: list[_Variant] = []
self.template_size: tuple[int, int] = (0, 0)
@@ -150,15 +158,20 @@ class LineShapeMatcher:
return cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
return img
@staticmethod
def _gradient(gray: np.ndarray) -> tuple[np.ndarray, np.ndarray]:
def _gradient(self, gray: np.ndarray) -> tuple[np.ndarray, np.ndarray]:
gx = cv2.Sobel(gray, cv2.CV_32F, 1, 0, ksize=3)
gy = cv2.Sobel(gray, cv2.CV_32F, 0, 1, ksize=3)
mag = cv2.magnitude(gx, gy)
ang = np.arctan2(gy, gx)
ang_mod = np.where(ang < 0, ang + np.pi, ang)
bins = np.floor(ang_mod / np.pi * N_BINS).astype(np.int16)
bins = np.clip(bins, 0, N_BINS - 1)
ang = np.arctan2(gy, gx) # [-π, π]
if self.use_polarity:
# Mod 2π: bin 0..15 codifica direzione + polarity edge.
ang_full = np.where(ang < 0, ang + 2.0 * np.pi, ang)
bins = np.floor(ang_full / (2.0 * np.pi) * N_BINS_POL).astype(np.int16)
bins = np.clip(bins, 0, N_BINS_POL - 1)
else:
ang_mod = np.where(ang < 0, ang + np.pi, ang)
bins = np.floor(ang_mod / np.pi * N_BINS).astype(np.int16)
bins = np.clip(bins, 0, N_BINS - 1)
return mag, bins
def _extract_features(
@@ -369,20 +382,22 @@ class LineShapeMatcher:
return raw
def _spread_bitmap(self, gray: np.ndarray) -> np.ndarray:
"""Spread bitmap uint8: bit b acceso dove bin b è presente nel raggio.
"""Spread bitmap: bit b acceso dove bin b è presente nel raggio.
Formato compatto 32× più denso della response map (N_BINS, H, W) float32.
dtype: uint8 per N_BINS=8, uint16 per N_BINS_POL=16 (use_polarity).
"""
mag, bins = self._gradient(gray)
valid = mag >= self.weak_grad
k = 2 * self.spread_radius + 1
kernel = np.ones((k, k), dtype=np.uint8)
H, W = gray.shape
spread = np.zeros((H, W), dtype=np.uint8)
for b in range(N_BINS):
nb = self._n_bins
dtype = np.uint16 if nb > 8 else np.uint8
spread = np.zeros((H, W), dtype=dtype)
for b in range(nb):
mask_b = ((bins == b) & valid).astype(np.uint8)
d = cv2.dilate(mask_b, kernel)
spread |= (d << b)
spread |= (d.astype(dtype) << b)
return spread
@staticmethod
@@ -632,9 +647,10 @@ class LineShapeMatcher:
x_lo = int(cx) - margin; x_hi = int(cx) + margin + 1
sh_w = y_hi - y_lo; sw_w = x_hi - x_lo
acc = np.zeros((sh_w, sw_w), dtype=np.float32)
spread_dtype = spread0.dtype.type
for i in range(len(dx)):
ddx = int(dx[i]); ddy = int(dy[i]); b = int(fb[i])
bit = np.uint8(1 << b)
bit = spread_dtype(1 << b)
sy0 = y_lo + ddy; sy1 = y_hi + ddy
sx0 = x_lo + ddx; sx1 = x_hi + ddx
a_y0 = max(0, -sy0); a_y1 = sh_w - max(0, sy1 - H)
@@ -802,8 +818,8 @@ class LineShapeMatcher:
# map float32 → MOLTO più cache-friendly per _score_by_shift.
spread_top = self._spread_bitmap(grays[top])
bit_active_top = int(
sum(1 << b for b in range(N_BINS)
if (spread_top & np.uint8(1 << b)).any())
sum(1 << b for b in range(self._n_bins)
if (spread_top & (spread_top.dtype.type(1) << b)).any())
)
if nms_radius is None:
nms_radius = max(8, min(self.template_size) // 2)
@@ -960,8 +976,8 @@ class LineShapeMatcher:
# Full-res (parallelizzato) con bitmap
spread0 = self._spread_bitmap(gray0)
bit_active_full = int(
sum(1 << b for b in range(N_BINS)
if (spread0 & np.uint8(1 << b)).any())
sum(1 << b for b in range(self._n_bins)
if (spread0 & (spread0.dtype.type(1) << b)).any())
)
density_full = _jit_popcount(spread0)
for sc in unique_scales: