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

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:
2026-05-04 17:07:38 +02:00
parent 41976f574d
commit 84b73dc651
2 changed files with 122 additions and 21 deletions
+89 -4
View File
@@ -328,6 +328,65 @@ if HAS_NUMBA:
out[vi] = best if best > 0.0 else 0.0
return out
@nb.njit(cache=True, parallel=True, fastmath=True, boundscheck=False)
def _jit_score_bitmap_rescored_u16(
spread: np.ndarray, # uint16 (H, W) - 16 bit di polarity-aware
dx: np.ndarray, dy: np.ndarray, bins: np.ndarray,
bit_active: np.uint16,
bg: np.ndarray,
) -> np.ndarray:
"""Versione uint16 di _jit_score_bitmap_rescored per polarity 16-bin.
Identica logica ma mask = uint16(1) << b dove b in [0..15]
(orientamento mod 2π invece di mod π).
"""
H, W = spread.shape
N = dx.shape[0]
acc = np.zeros((H, W), dtype=np.float32)
for y in nb.prange(H):
for i in range(N):
b = bins[i]
mask = np.uint16(1) << b
if (bit_active & mask) == 0:
continue
ddy = dy[i]
yy = y + ddy
if yy < 0 or yy >= H:
continue
ddx = dx[i]
x_lo = 0 if ddx >= 0 else -ddx
x_hi = W if ddx <= 0 else W - ddx
for x in range(x_lo, x_hi):
if spread[yy, x + ddx] & mask:
acc[y, x] += 1.0
if N > 0:
inv = 1.0 / N
for y in nb.prange(H):
for x in range(W):
v = acc[y, x] * inv
bgv = bg[y, x]
if bgv < 1.0:
r = (v - bgv) / (1.0 - bgv + 1e-6)
acc[y, x] = r if r > 0.0 else 0.0
else:
acc[y, x] = 0.0
return acc
@nb.njit(cache=True, parallel=True, fastmath=True, boundscheck=False)
def _jit_popcount_density_u16(spread: np.ndarray) -> np.ndarray:
"""Popcount per uint16 (16 bin polarity)."""
H, W = spread.shape
out = np.zeros((H, W), dtype=np.float32)
for y in nb.prange(H):
for x in range(W):
v = spread[y, x]
cnt = 0
for b in range(16):
if v & (np.uint16(1) << b):
cnt += 1
out[y, x] = float(cnt)
return out
@nb.njit(cache=True, parallel=True, fastmath=True, boundscheck=False)
def _jit_popcount_density(spread: np.ndarray) -> np.ndarray:
"""Conta bit set per pixel: ritorna (H, W) float32 in [0..8]."""
@@ -368,6 +427,11 @@ if HAS_NUMBA:
spread, dx, dy, b, offsets, np.uint8(0xFF), bg_pv, scale_idx,
)
_jit_popcount_density(spread)
spread16 = np.zeros((32, 32), dtype=np.uint16)
_jit_score_bitmap_rescored_u16(
spread16, dx, dy, b, np.uint16(0xFFFF), bg,
)
_jit_popcount_density_u16(spread16)
else: # pragma: no cover
@@ -392,6 +456,12 @@ else: # pragma: no cover
):
raise RuntimeError("numba non disponibile")
def _jit_score_bitmap_rescored_u16(spread, dx, dy, bins, bit_active, bg):
raise RuntimeError("numba non disponibile")
def _jit_popcount_density_u16(spread):
raise RuntimeError("numba non disponibile")
def _jit_popcount_density(spread):
raise RuntimeError("numba non disponibile")
@@ -426,16 +496,20 @@ def score_bitmap_rescored(
) -> np.ndarray:
"""Score bitmap + rescore fusi in un solo pass (JIT).
stride > 1: valuta solo pixel su griglia stride×stride. Le celle non
valutate restano 0 nello score map. Pensato per coarse-pass al top
della piramide; il refinement full-res poi recupera precisione.
Dispatch per dtype: uint16 → kernel polarity 16-bin, uint8 → kernel
standard 8-bin (con eventuale stride > 1 per coarse top-level).
"""
if HAS_NUMBA and len(dx) > 0:
spread_c = np.ascontiguousarray(spread, dtype=np.uint8)
dx_c = np.ascontiguousarray(dx, dtype=np.int32)
dy_c = np.ascontiguousarray(dy, dtype=np.int32)
bins_c = np.ascontiguousarray(bins, dtype=np.int8)
bg_c = np.ascontiguousarray(bg, dtype=np.float32)
if spread.dtype == np.uint16:
spread_c = np.ascontiguousarray(spread, dtype=np.uint16)
return _jit_score_bitmap_rescored_u16(
spread_c, dx_c, dy_c, bins_c, np.uint16(bit_active), bg_c,
)
spread_c = np.ascontiguousarray(spread, dtype=np.uint8)
if stride > 1:
return _jit_score_bitmap_rescored_strided(
spread_c, dx_c, dy_c, bins_c, np.uint8(bit_active), bg_c,
@@ -528,6 +602,17 @@ def popcount_density(spread: np.ndarray) -> np.ndarray:
2) numpy.bitwise_count (NumPy 2.0+, SIMD ma single-thread)
3) Fallback numpy bit-shift puro
"""
if spread.dtype == np.uint16:
spread_c = np.ascontiguousarray(spread, dtype=np.uint16)
if HAS_NUMBA:
return _jit_popcount_density_u16(spread_c)
if _HAS_NP_BITCOUNT:
return np.bitwise_count(spread_c).astype(np.float32, copy=False)
H, W = spread_c.shape
out = np.zeros((H, W), dtype=np.float32)
for b in range(16):
out += ((spread_c >> b) & 1).astype(np.float32)
return out
spread_c = np.ascontiguousarray(spread, dtype=np.uint8)
if HAS_NUMBA:
return _jit_popcount_density(spread_c)