update filter, flow ema 0.5 + med 3

sensors/box/sensor.json

@@ -33,6 +33,14 @@
     "algorithm_list": ["raft", "dis"],
     "hhd_downsample": 3
   },
+  "filters": {
+    "enabled": true,
+    "flow_ema_alpha": 0.5,
+    "force_median_window": 3,
+    "force_lowpass_cutoff_hz": 0.0,
+    "force_lowpass_order": 2,
+    "force_lowpass_sample_rate_hz": "auto"
+  },
   "contact": {
     "min_contour_area": 3000,
     "flow_threshold":5,

sensors/finger/sensor.json

@@ -22,7 +22,15 @@
     "dis_preset": "medium",
     "dis_mode": 1,
     "algorithm_list": ["raft", "dis"],
-    "hhd_downsample": 3
+    "hhd_downsample": 2
+  },
+  "filters": {
+    "enabled": true,
+    "flow_ema_alpha": 0.5,
+    "force_median_window": 3,
+    "force_lowpass_cutoff_hz": 0.0,
+    "force_lowpass_order": 2,
+    "force_lowpass_sample_rate_hz": "auto"
   },
   "contact": {
     "min_contour_area": 3000,

sensors/mini/sensor.json

@@ -29,10 +29,18 @@
     "loop_closure_interval": 1,
     "algorithm": "dis",
     "dis_preset": "medium",
-    "dis_mode": 3,
+    "dis_mode": 1,
     "algorithm_list": ["raft", "dis"],
     "hhd_downsample": 3
   },
+  "filters": {
+    "enabled": true,
+    "flow_ema_alpha": 0.5,
+    "force_median_window": 3,
+    "force_lowpass_cutoff_hz": 0.0,
+    "force_lowpass_order": 2,
+    "force_lowpass_sample_rate_hz": "auto"
+  },
   "contact": {
     "min_contour_area": 3000,
     "flow_threshold":5,

src/orisys/calibration.py

@@ -242,7 +242,9 @@ class Calibration:
         meta: dict[str, Any] = {}
         meta.update(self.provenance)
         meta.update({k: v for k, v in self.identity.items() if k not in meta})
-        for key in ("stitch_resolution", "dis_mode", "hhd_downsample", "config_ref"):
+        for key in ("stitch_resolution", "dis_mode", "hhd_downsample",
+                   "flow_ema_alpha", "force_median_window", "force_lowpass_cutoff_hz",
+                   "config_ref"):
             if key in self.pipeline and self.pipeline[key] is not None:
                 meta[key] = self.pipeline[key]
         if self.measurements:
@@ -387,7 +389,8 @@ def check(doc: dict | Calibration, *, pipeline: dict | None = None) -> CheckResu
         warns.append("empty sn on factory calibration")
 
     if pipeline is not None and isinstance(doc, Calibration):
-        for key in ("stitch_resolution", "dis_mode", "hhd_downsample"):
+        for key in ("stitch_resolution", "dis_mode", "hhd_downsample",
+                "flow_ema_alpha", "force_median_window", "force_lowpass_cutoff_hz"):
             if key in doc.pipeline and key in pipeline and doc.pipeline[key] != pipeline[key]:
                 warns.append(f"pipeline mismatch: {key}")
 
@@ -601,11 +604,14 @@ def load(
 
 
 def pipeline_from_sensor_json(path: str | Path | None) -> dict[str, Any]:
-    """Pull stitch / tracker fields from a sensor.json for export pipeline/meta."""
+    """Pull stitch / tracker / filter fields from a sensor.json for export pipeline/meta."""
     pipeline: dict[str, Any] = {
         "stitch_resolution": None,
         "dis_mode": None,
         "hhd_downsample": None,
+        "flow_ema_alpha": None,
+        "force_median_window": None,
+        "force_lowpass_cutoff_hz": None,
         "config_ref": None,
     }
     if path is None:
@@ -622,6 +628,7 @@ def pipeline_from_sensor_json(path: str | Path | None) -> dict[str, Any]:
         return pipeline
     camera = data.get("camera") if isinstance(data.get("camera"), dict) else {}
     tracker = data.get("tracker") if isinstance(data.get("tracker"), dict) else {}
+    filters = data.get("filters") if isinstance(data.get("filters"), dict) else {}
     stitch = camera.get("resolution_stitch")
     if isinstance(stitch, (list, tuple)) and len(stitch) >= 2:
         pipeline["stitch_resolution"] = [int(stitch[0]), int(stitch[1])]
@@ -635,6 +642,29 @@ def pipeline_from_sensor_json(path: str | Path | None) -> dict[str, Any]:
             pipeline["hhd_downsample"] = int(tracker["hhd_downsample"])
         except (TypeError, ValueError):
             pipeline["hhd_downsample"] = tracker.get("hhd_downsample")
+    # Signal-conditioning settings change the reported force values, so they
+    # belong to the pipeline identity just like dis_mode / hhd_downsample.
+    if filters:
+        enabled = bool(filters.get("enabled", True))
+        for key in ("flow_ema_alpha", "force_lowpass_cutoff_hz"):
+            if key in filters:
+                try:
+                    pipeline[key] = float(filters[key]) if enabled else 0.0
+                except (TypeError, ValueError):
+                    pipeline[key] = filters.get(key)
+            elif key == "flow_ema_alpha":
+                pipeline[key] = 0.5 if enabled else 0.0
+            else:
+                pipeline[key] = 10.0 if enabled else 0.0
+        if "force_median_window" in filters:
+            try:
+                pipeline["force_median_window"] = (
+                    int(filters["force_median_window"]) if enabled else 1
+                )
+            except (TypeError, ValueError):
+                pipeline["force_median_window"] = filters.get("force_median_window")
+        else:
+            pipeline["force_median_window"] = 3 if enabled else 1
     return pipeline
 
 
@@ -717,7 +747,8 @@ def build(
         for k, v in extra_meta.items():
             if k == "samples":
                 continue
-            if k in ("stitch_resolution", "dis_mode", "hhd_downsample", "config_ref"):
+            if k in ("stitch_resolution", "dis_mode", "hhd_downsample", "config_ref",
+                "flow_ema_alpha", "force_median_window", "force_lowpass_cutoff_hz"):
                 if k not in pipeline or pipeline[k] is None:
                     pipeline[k] = v
             elif k in ("sensor_type", "sn", "hardware_rev", "gel_id"):

src/orisys/finger/runtime.py

@@ -293,6 +293,15 @@ class FingerRuntime:
         capture = capture_source.cap
 
         sensor = Sensor("external", config_name=config, verbose=verbose, mirror=mirror)
+        if not is_live_camera(video):
+            # File playback: wall-clock cadence is not signal time, so pin the
+            # force-filter design rate to the configured camera fps.
+            try:
+                fps = float(geometry.config.get("camera", {}).get("fps", 0.0) or 0.0)
+            except (TypeError, ValueError):
+                fps = 0.0
+            if fps > 0:
+                sensor.configure(lowpass_sample_rate_hz=fps)
         frame_processor = FrameUnwarper(
             domain.remap,
             camera_matrix=geometry.source_K if geometry.dist_coeffs is not None else None,

src/orisys/frame_processors.py

@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+import time
+
 import cv2
 import numpy as np
 from pathlib import Path
@@ -12,11 +14,24 @@ class CompoundEyeFrameProcessor:
 
     def __init__(self, stitcher):
         self.stitcher = stitcher
+        # Per-call sub-stage timings (seconds), read by Sensor.get_img() for
+        # _last_stage_times. Keys: units, extract_tiles, stitch.
+        self.last_timings = {}
 
     def process(self, frame):
+        t0 = time.perf_counter()
         self.stitcher.get_stitch_unit(frame)
+        t1 = time.perf_counter()
         self.stitcher.extract_tiles()
-        return self.stitcher.stitch_rt_optimized()
+        t2 = time.perf_counter()
+        stitched = self.stitcher.stitch_rt_optimized()
+        t3 = time.perf_counter()
+        self.last_timings = {
+            "units": t1 - t0,
+            "extract_tiles": t2 - t1,
+            "stitch": t3 - t2,
+        }
+        return stitched
 
 
 class SingleCameraFrameProcessor:

src/orisys/hhd/api.py

@@ -73,8 +73,49 @@ class nHHD(object):
             raise ValueError("nHHD Solver works only for 2 and 3 dimensions")
 
         self._force_cpu_cache = None
+        self._force_ref_shape = None
+        ref_shape = kwargs.get('force_reference_grid')
+        if ref_shape is not None:
+            try:
+                ref_h, ref_w = int(ref_shape[0]), int(ref_shape[1])
+            except (TypeError, ValueError, IndexError):
+                ref_h = ref_w = 0
+            if ref_h > 0 and ref_w > 0:
+                self._force_ref_shape = (ref_h, ref_w)
         self.psolver.prepare(False)
 
+    def _force_scale(self, shape):
+        """Area/linear weights mapping grid sums at ``shape`` to the reference grid.
+
+        ``Sn``/``Stx``/``Sty``/``Stor`` are *sums over grid pixels*, and the
+        torque term additionally uses pixel-index moment arms. When the flow is
+        downsampled by ``hhd_downsample=k`` before decomposition, the same
+        physical deformation therefore reports roughly ``1/k^2`` of the force
+        magnitude (and ``1/k^3`` of the torque) unless the sums are rescaled
+        back onto the reference grid.
+
+        returns: (area_scale, linear_scale); (1.0, 1.0) when no reference grid
+            was configured or the current grid already is the reference.
+        """
+        ref = self._force_ref_shape
+        if ref is None or (int(shape[0]), int(shape[1])) == ref:
+            return 1.0, 1.0
+        cur_area = float(shape[0]) * float(shape[1])
+        if cur_area <= 0.0:
+            return 1.0, 1.0
+        area_scale = (float(ref[0]) * float(ref[1])) / cur_area
+        return area_scale, float(numpy.sqrt(area_scale))
+
+    def _apply_force_scale(self, shape):
+        """Rescale aggregate force sums from a downsampled grid to the reference grid."""
+        area_scale, linear_scale = self._force_scale(shape)
+        if area_scale == 1.0 and linear_scale == 1.0:
+            return
+        self.Sn = float(self.Sn) * area_scale
+        self.Stx = float(self.Stx) * area_scale
+        self.Sty = float(self.Sty) * area_scale
+        self.Stor = float(self.Stor) * area_scale * linear_scale
+
     def _normalize_mask(self, valid_mask, shape):
         if valid_mask is None:
             return None
@@ -402,6 +443,8 @@ class nHHD(object):
             cross_n = numpy.where(mask, cross_n, 0)
         self.Stor = numpy.sum(cross_p) + numpy.sum(cross_n)
 
+        self._apply_force_scale(shape)
+
         # Optimized: pre-allocate output array with explicit dtype
         output = numpy.array([self.Sn, self.Stx, self.Sty, self.Stor], dtype=numpy.float32)
 
@@ -515,6 +558,8 @@ class nHHD(object):
             ))
 
         self.Sn, self.Stx, self.Sty, self.Stor = Sn, Stx, Sty, Stor
+        self._apply_force_scale(shape)
+        Sn, Stx, Sty, Stor = self.Sn, self.Stx, self.Sty, self.Stor
         output = numpy.array([Sn, Stx, Sty, Stor], dtype=numpy.float32)
 
         # Keep stable CPU copies for get_normal()/get_shear() so callers get this frame's

src/orisys/hhd/domain.py

@@ -29,6 +29,39 @@ def compute_boundary_mask(active):
     return active & ~fully_surrounded
 
 
+def build_masked_factor(lap):
+    """Factorize the masked Laplacian for fast repeated triangular solves.
+
+    The reduced system is a symmetric M-matrix (graph Laplacian of the active
+    pixels with an extra Dirichlet pin), so SuperLU can skip partial pivoting
+    (``SymmetricMode`` + ``diag_pivot_thresh=0``), which is ~2x faster than the
+    default pivoting factorization. Factoring in float32 halves the memory
+    traffic of the triangular solves; relative error against the float64
+    reference stays around 1e-7 for these systems.
+
+    ``rhs_dtype`` is returned because ``SuperLU.solve`` refuses to cast a
+    float64 right-hand side down to a float32 factor.
+
+    lap: (N, N) symmetric sparse Laplacian (any scipy dtype)
+    returns: (solve_callable, rhs_dtype)
+    """
+    lap_csc = lap.tocsc()
+    lap32 = lap_csc.astype(numpy.float32, copy=False)
+    for diag_pivot_thresh in (0.0, 1.0):
+        try:
+            lu = sparse_linalg.splu(
+                lap32,
+                permc_spec="MMD_AT_PLUS_A",
+                diag_pivot_thresh=diag_pivot_thresh,
+                options=dict(SymmetricMode=True),
+            )
+            return lu.solve, numpy.float32
+        except Exception:
+            continue
+    # Last resort: the original pivoting LU on the float64 matrix.
+    return sparse_linalg.factorized(lap_csc), numpy.float64
+
+
 def sample_boundary_coords(boundary_coords, config: MaskedPoissonConfig):
     """Subsample boundary pixel coordinates for capacitance correction."""
     if boundary_coords.size == 0:
@@ -53,6 +86,7 @@ class MaskedDomain:
         "mask",
         "index_map",
         "factor",
+        "factor_dtype",
         "lap",
         "num_active",
         "pinned",
@@ -75,11 +109,13 @@ class MaskedDomain:
         pinned,
         active_coords,
         active_linear_indices,
+        factor_dtype=numpy.float32,
     ):
         self.shape = shape
         self.mask = mask
         self.index_map = index_map
         self.factor = factor
+        self.factor_dtype = numpy.dtype(factor_dtype)
         self.lap = lap
         self.num_active = num_active
         self.pinned = pinned
@@ -156,7 +192,7 @@ class MaskedDomain:
                 data.append(diag)
 
         lap = sparse.csc_matrix((data, (rows, cols)), shape=(num_active, num_active), dtype=numpy.float64)
-        factor = sparse_linalg.factorized(lap)
+        factor, factor_dtype = build_masked_factor(lap)
         return cls(
             shape=active.shape,
             mask=active.copy(),
@@ -167,6 +203,7 @@ class MaskedDomain:
             pinned=pinned,
             active_coords=active_coords,
             active_linear_indices=active_linear_indices,
+            factor_dtype=factor_dtype,
         )
 
     def matches(self, mask):
@@ -179,13 +216,20 @@ class MaskedDomain:
 
         f: (H, W) scalar source field
         returns: (N,) RHS on active pixels; empty if no active pixels
+
+        The returned dtype matches the factorization (see ``factor_dtype``):
+        ``SuperLU.solve`` will not downcast a float64 RHS for a float32 factor.
         """
         if self.num_active == 0:
-            return numpy.zeros(0, dtype=numpy.float64)
+            return numpy.zeros(0, dtype=self.factor_dtype)
-        if self._rhs_buffer is None or self._rhs_buffer.shape != (self.num_active,):
+        if (
-            self._rhs_buffer = numpy.empty(self.num_active, dtype=numpy.float64)
+            self._rhs_buffer is None
+            or self._rhs_buffer.shape != (self.num_active,)
+            or self._rhs_buffer.dtype != self.factor_dtype
+        ):
+            self._rhs_buffer = numpy.empty(self.num_active, dtype=self.factor_dtype)
         numpy.take(
-            numpy.asarray(f, dtype=numpy.float64).ravel(),
+            numpy.asarray(f, dtype=self.factor_dtype).ravel(),
             self.active_linear_indices,
             out=self._rhs_buffer,
         )
@@ -197,11 +241,15 @@ class MaskedDomain:
     def prepare_rhs_pair(self, f0, f1):
         """Extract two gauge-fixed RHS vectors into one reusable (N, 2) buffer."""
         if self.num_active == 0:
-            return numpy.zeros((0, 2), dtype=numpy.float64)
+            return numpy.zeros((0, 2), dtype=self.factor_dtype)
-        if self._rhs_pair_buffer is None or self._rhs_pair_buffer.shape != (self.num_active, 2):
+        if (
-            self._rhs_pair_buffer = numpy.empty((self.num_active, 2), dtype=numpy.float64)
+            self._rhs_pair_buffer is None
-        flat0 = numpy.asarray(f0, dtype=numpy.float64).ravel()
+            or self._rhs_pair_buffer.shape != (self.num_active, 2)
-        flat1 = numpy.asarray(f1, dtype=numpy.float64).ravel()
+            or self._rhs_pair_buffer.dtype != self.factor_dtype
+        ):
+            self._rhs_pair_buffer = numpy.empty((self.num_active, 2), dtype=self.factor_dtype)
+        flat0 = numpy.asarray(f0, dtype=self.factor_dtype).ravel()
+        flat1 = numpy.asarray(f1, dtype=self.factor_dtype).ravel()
         numpy.take(flat0, self.active_linear_indices, out=self._rhs_pair_buffer[:, 0])
         numpy.take(flat1, self.active_linear_indices, out=self._rhs_pair_buffer[:, 1])
         self._rhs_pair_buffer -= self._rhs_pair_buffer.mean(axis=0, keepdims=True)
@@ -255,6 +303,7 @@ class MaskedDomain:
             "mask": self.mask,
             "index_map": self.index_map,
             "factor": self.factor,
+            "factor_dtype": self.factor_dtype,
             "lap": self.lap,
             "num_active": self.num_active,
             "pinned": self.pinned,

src/orisys/hhd/solvers/masked_sparse.py

@@ -33,7 +33,11 @@ class MaskedSparseSolver:
         try:
             sol_pair = -domain.factor(rhs_pair)  # (N, 2) reduced-system potentials
         except Exception:
+            # Some factorizations need contiguous 1-D right-hand sides.
             sol_pair = -numpy.column_stack(
-                [domain.factor(rhs_pair[:, 0]), domain.factor(rhs_pair[:, 1])]
+                [
+                    domain.factor(numpy.ascontiguousarray(rhs_pair[:, 0])),
+                    domain.factor(numpy.ascontiguousarray(rhs_pair[:, 1])),
+                ]
             )
         return domain.scatter_pair(sol_pair, f0)

src/orisys/sensor.py

@@ -26,8 +26,22 @@ from .backend_availability import (check_cupy_available, check_opencl_available)
 from .frame_processors import create_frame_processor
 from .signal_processing import (
     DEFAULT_SAMPLE_RATE_HZ,
+    CausalMedianFilter,
     LowpassFilter,
+    SampleRateEstimator,
 )
+
+# Default signal-conditioning settings (config: top-level "filters" block).
+# Measured on dd02-0703 at 280x300 (see the noise analysis in the perf notes):
+# flow EMA 0.5 + median 3 costs ~2 frames at 30 fps, cuts steady-press force
+# jitter by roughly half and removes ~85% of the heavy-tailed spikes, while also
+# stabilising vnormal/contact (which a force-level filter cannot do).
+# The force low-pass is OFF by default: on top of the EMA it added no measurable
+# noise benefit at the same latency, so it is kept as an opt-in stage for sites
+# with different noise characteristics.
+DEFAULT_FORCE_LOWPASS_HZ = 0.0
+DEFAULT_FORCE_MEDIAN_WINDOW = 3
+DEFAULT_FLOW_EMA_ALPHA = 0.5
 from .capture import (
     CaptureConfig,
     CaptureSource,
@@ -154,16 +168,92 @@ class Sensor:
         self.calibration: Optional[cal_mod.Calibration] = None
         self._force_cal_sensor_name: Optional[str] = None
         self._init_force_calibration()
-        self._lowpass_enabled = False
+
-        self._lowpass_cutoff_hz = 0.0
+        # ---------------------------------------------------------------
-        self._lowpass_sample_rate_hz = float(DEFAULT_SAMPLE_RATE_HZ)
+        # Signal conditioning (config: top-level "filters" block)
+        # ---------------------------------------------------------------
+        # These settings change the reported force values, so they are part of
+        # the measurement-pipeline identity and are recorded in the calibration
+        # metadata / mismatch check alongside dis_mode and hhd_downsample.
+        # Filtering is ON by default; set filters.enabled=false (or a per-key
+        # zero) to get the unfiltered chain.
+        filters_cfg = self._config.get("filters")
+        if not isinstance(filters_cfg, dict):
+            filters_cfg = {}
+        self._filters_enabled = bool(filters_cfg.get("enabled", True))
+
         self._lowpass_order = 2
+        self._lowpass_sample_rate_hz = float(DEFAULT_SAMPLE_RATE_HZ)
+        self._lowpass_cutoff_hz = 0.0
+        self._lowpass_rate_auto = True
+        self._config_fps = 0.0
+        try:
+            self._config_fps = float(self.__config_cam.get("fps", 0.0) or 0.0)
+        except (TypeError, ValueError):
+            self._config_fps = 0.0
+        if self._config_fps <= 0:
+            self._config_fps = float(DEFAULT_SAMPLE_RATE_HZ)
+        self._lowpass_sample_rate_hz = self._config_fps
+        try:
+            self._lowpass_order = max(1, int(filters_cfg.get("force_lowpass_order", 2)))
+            rate_cfg = filters_cfg.get("force_lowpass_sample_rate_hz", "auto")
+            if isinstance(rate_cfg, str):
+                self._lowpass_rate_auto = rate_cfg.strip().lower() in ("auto", "", "measured")
+            else:
+                rate = float(rate_cfg) if rate_cfg is not None else 0.0
+                self._lowpass_rate_auto = rate <= 0.0
+                if not self._lowpass_rate_auto:
+                    self._lowpass_sample_rate_hz = rate
+            if self._filters_enabled:
+                self._lowpass_cutoff_hz = float(
+                    filters_cfg.get("force_lowpass_cutoff_hz", DEFAULT_FORCE_LOWPASS_HZ)
+                )
+        except (TypeError, ValueError):
+            self._lowpass_order = 2
+            self._lowpass_sample_rate_hz = self._config_fps
+            self._lowpass_rate_auto = True
+            self._lowpass_cutoff_hz = (
+                DEFAULT_FORCE_LOWPASS_HZ if self._filters_enabled else 0.0
+            )
+        if self._lowpass_sample_rate_hz <= 0:
+            self._lowpass_sample_rate_hz = self._config_fps
+        if not (0.0 <= self._lowpass_cutoff_hz < 0.5 * self._lowpass_sample_rate_hz):
+            self._lowpass_cutoff_hz = (
+                DEFAULT_FORCE_LOWPASS_HZ
+                if (self._filters_enabled and 0.0 < DEFAULT_FORCE_LOWPASS_HZ < 0.5 * self._lowpass_sample_rate_hz)
+                else 0.0
+            )
+        self._lowpass_enabled = self._lowpass_cutoff_hz > 0
         self._force_filter = LowpassFilter(
             cutoff_hz=self._lowpass_cutoff_hz,
             sample_rate_hz=self._lowpass_sample_rate_hz,
             order=self._lowpass_order,
             n_channels=3,
         )
+        # Rate tracking: only meaningful while the force low-pass is in use.
+        self._force_rate = SampleRateEstimator(initial_hz=self._config_fps)
+        self._force_rate_source = "config"
+
+        self._force_median_window = 1
+        if self._filters_enabled:
+            try:
+                self._force_median_window = max(
+                    1, int(filters_cfg.get("force_median_window", DEFAULT_FORCE_MEDIAN_WINDOW))
+                )
+            except (TypeError, ValueError):
+                self._force_median_window = DEFAULT_FORCE_MEDIAN_WINDOW
+        self._force_median = CausalMedianFilter(window=self._force_median_window, n_channels=3)
+
+        self._flow_ema_alpha = 1.0
+        if self._filters_enabled:
+            try:
+                alpha = float(filters_cfg.get("flow_ema_alpha", DEFAULT_FLOW_EMA_ALPHA))
+            except (TypeError, ValueError):
+                alpha = DEFAULT_FLOW_EMA_ALPHA
+            if 0.0 < alpha < 1.0:
+                self._flow_ema_alpha = alpha
+        self._ema_flow = None
+
         if self.verbose:
             if self.calibration is not None and self.calibration.source_path is not None:
                 print(f"Force calibration: {self.calibration.source_path}")
@@ -182,6 +272,13 @@ class Sensor:
         self.valid_mask_raw = None
         self.valid_mask = None
         self.valid_mask_hhd = None
+        # Scratch buffers reused by _compute_flow_means / compute_hhd.
+        self._flow_mag_buf = None
+        self._flow_mask_u8 = None
+        self._hhd_vn_buf = None
+        self._hhd_vs_buf = None
+        self._hhd_flow_ds_buf = None
+        self._hhd_mask_f32 = None
         self.mask_stats = {
             "coverage": 0.0,
             "flow_mean_valid": 0.0,
@@ -194,10 +291,16 @@ class Sensor:
         self._last_capture_time = 0.0
         self._last_processing_time = 0.0
         self._last_stage_times = {
-            "extract_tiles": 0.0,
+            # Frame-post-processing roll-ups (seconds).
-            "stitch": 0.0,
+            "extract_tiles": 0.0,   # sensor units + tile extraction
-            "resize": 0.0,
+            "stitch": 0.0,          # feature/feather stitch of the extracted tiles
-            "mirror": 0.0,
+            "resize": 0.0,          # BGR->gray + resize to resolution_stitch + mirror
+            # Finer breakdown.
+            "store": 0.0,           # frame reference/copy
+            "units": 0.0,           # compound-eye unit (sub-image) extraction
+            "gray": 0.0,            # BGR->gray conversion
+            "mirror": 0.0,          # horizontal flip
+            "mask": 0.0,            # valid-mask resize/cache update
             "astype": 0.0,
         }
         
@@ -218,6 +321,7 @@ class Sensor:
         except (TypeError, ValueError):
             self._hhd_downsample = 1
         self._hhd_grid_shape = None
+        self._hhd_ref_shape = None
         cfg_backend = self.__config_tracker.get("backend", None)
         self.poisson_backend = cfg_backend if cfg_backend is not None else backend
         self.masked_poisson_solver = self.__config_tracker.get("masked_poisson_solver", "sparse")
@@ -244,6 +348,15 @@ class Sensor:
                 print("Sensor initialized in external-frame mode.")
         else:
             self._open_video_source(override, box)
+            if not self._is_live_camera:
+                # A file source is replayed at whatever speed the CPU manages,
+                # so wall-clock intervals do not reflect signal time: keep the
+                # configured camera fps for the force low-pass design.
+                self._lowpass_rate_auto = False
+                self._force_rate_source = "config (file)"
+                self._lowpass_sample_rate_hz = self._config_fps
+                if getattr(self, "_force_rate", None) is not None:
+                    self._force_rate.reset(self._config_fps)
 
         if self.verbose:
             print(f"  Video source: {vid_src}")
@@ -253,6 +366,14 @@ class Sensor:
             # print(f"  CUDA acceleration: {self.cuda}")
             print(f"  CuPy available: {self.CUPY_AVAILABLE}")
             print(f"  OpenCL available: {self.OPENCL_AVAILABLE}")
+            print(
+                "  Signal filters: "
+                f"ema_alpha={self._flow_ema_alpha} "
+                f"median={self._force_median_window} "
+                f"lowpass={self._lowpass_cutoff_hz}Hz@"
+                f"{self._lowpass_sample_rate_hz:.1f}Hz "
+                f"({self.force_sample_rate_source})"
+            )
             
             
 
@@ -313,17 +434,31 @@ class Sensor:
     def _compute_flow_means(self, flow):
         if flow is None:
             return
-        mag = np.linalg.norm(flow, axis=-1)
+        shape = flow.shape[:2]
+        mag = self._flow_mag_buf
+        if mag is None or mag.shape != shape or mag.dtype != np.float32:
+            mag = np.empty(shape, dtype=np.float32)
+            self._flow_mag_buf = mag
+        # cv2.magnitude + cv2.mean(mask=...) avoid the (H, W) temporaries and the
+        # boolean fancy-index gather that np.linalg.norm + mag[mask].mean() need.
+        cv2.magnitude(flow[:, :, 0], flow[:, :, 1], mag)
+
         mask = self.valid_mask
-        if mask is None or mask.shape != mag.shape:
+        if mask is None or mask.shape != shape:
-            self.mask_stats["flow_mean_valid"] = float(mag.mean()) if mag.size else 0.0
+            self.mask_stats["flow_mean_valid"] = float(cv2.mean(mag)[0]) if mag.size else 0.0
             self.mask_stats["flow_mean_invalid"] = 0.0
             return
 
-        valid = mask.astype(bool)
+        mask_u8 = self._flow_mask_u8
-        invalid = ~valid
+        if mask_u8 is None or mask_u8.shape != shape or mask_u8.dtype != np.uint8:
-        self.mask_stats["flow_mean_valid"] = float(mag[valid].mean()) if np.any(valid) else 0.0
+            mask_u8 = np.empty(shape, dtype=np.uint8)
-        self.mask_stats["flow_mean_invalid"] = float(mag[invalid].mean()) if np.any(invalid) else 0.0
+            self._flow_mask_u8 = mask_u8
+        np.copyto(mask_u8, mask, casting="unsafe")
+        np.multiply(mask_u8, 255, out=mask_u8)
+
+        self.mask_stats["flow_mean_valid"] = float(cv2.mean(mag, mask=mask_u8)[0])
+        np.subtract(255, mask_u8, out=mask_u8)
+        self.mask_stats["flow_mean_invalid"] = float(cv2.mean(mag, mask=mask_u8)[0])
 
     def get_img(self, frame=None, already_processed=False, valid_mask=None, already_gray=False):
         """
@@ -362,6 +497,7 @@ class Sensor:
         self.frame = frame if (already_processed and isinstance(frame, np.ndarray)) else (
             frame.copy() if isinstance(frame, np.ndarray) else frame
         )
+        t_after_store = time.perf_counter()
         if already_processed:
             img_bgr = frame
             gray = None
@@ -383,8 +519,6 @@ class Sensor:
             gray = None
         t_after_extract = time.perf_counter()
 
-        t_after_stitch = time.perf_counter()
-
         if gray is None:
             self.img_size_raw = img_bgr.shape
             self._img_bgr_raw = img_bgr
@@ -392,6 +526,8 @@ class Sensor:
         else:
             self.img_size_raw = gray.shape
             self._img_bgr_raw = None
+        t_after_gray = time.perf_counter()
+
         res = tuple(self._config_resolution_stitch)
         if self._img_gray_buf is None or self._img_gray_buf.shape != (res[1], res[0]):
             self._img_gray_buf = np.empty((res[1], res[0]), dtype=np.uint8)
@@ -400,15 +536,22 @@ class Sensor:
 
         if self.mirror:
             cv2.flip(self._img_gray_buf, 1, dst=self._img_gray_buf)
+        t_after_mirror = time.perf_counter()
 
         self.img = self._img_gray_buf
         self._prepare_valid_mask(valid_mask, gray.shape, self.img.shape)
-        
         t_processing_end = time.perf_counter()
+
         self._last_processing_time = t_processing_end - t_processing_start
-        self._last_stage_times["extract_tiles"] = t_after_extract - t_processing_start
+        self._record_stage_times(
-        self._last_stage_times["stitch"] = t_after_stitch - t_after_extract
+            t_processing_start=t_processing_start,
-        self._last_stage_times["resize"] = t_processing_end - t_after_stitch
+            t_after_store=t_after_store,
+            t_after_extract=t_after_extract,
+            t_after_gray=t_after_gray,
+            t_after_resize=t_after_resize,
+            t_after_mirror=t_after_mirror,
+            t_processing_end=t_processing_end,
+        )
 
         # FPS calculation
         self._fps = 1.0 / (time.perf_counter() - self.last_log_time)
@@ -416,6 +559,48 @@ class Sensor:
             
         return self.img.copy()
 
+    def _record_stage_times(
+        self,
+        *,
+        t_processing_start,
+        t_after_store,
+        t_after_extract,
+        t_after_gray,
+        t_after_resize,
+        t_after_mirror,
+        t_processing_end,
+    ):
+        """Record per-stage frame-post-processing timings (seconds).
+
+        ``extract_tiles``/``stitch`` come from the frame processor, which times
+        its own sub-steps; the remaining keys are measured here. The roll-ups
+        keep the historical key names while no longer collapsing ``stitch`` to
+        zero: previously ``t_after_stitch`` was sampled immediately after
+        ``t_after_extract``, so ``stitch`` was always ~0 s and ``resize``
+        silently absorbed the whole stitch cost.
+        """
+        stage = self._last_stage_times
+        processor_timings = getattr(self.frame_processor, "last_timings", None) or {}
+        units_s = float(processor_timings.get("units", 0.0))
+        extract_s = float(processor_timings.get("extract_tiles", 0.0))
+        stitch_s = float(processor_timings.get("stitch", 0.0))
+        processor_total_s = t_after_extract - t_after_store
+
+        stage["store"] = t_after_store - t_processing_start
+        stage["units"] = units_s
+        stage["gray"] = t_after_gray - t_after_extract
+        stage["resize"] = t_after_resize - t_after_gray
+        stage["mirror"] = t_after_mirror - t_after_resize
+        stage["mask"] = t_processing_end - t_after_mirror
+
+        if processor_timings:
+            stage["extract_tiles"] = units_s + extract_s
+            stage["stitch"] = stitch_s
+        else:
+            # Non-compound-eye processors are a single opaque step.
+            stage["extract_tiles"] = processor_total_s
+            stage["stitch"] = 0.0
+
     def _get_img_bgr(self):
         """Produce a resized+mirrored BGR image on demand (for display)."""
         if self._img_bgr_raw is None:
@@ -512,9 +697,73 @@ class Sensor:
         # flow = self.__tracker.track_raft(self.img)
         if hasattr(flow, 'download'):
             flow = flow.download()
+        flow = self._apply_flow_ema(flow)
         self.flow = flow
         self._compute_flow_means(self.flow)
-    
+
+    def _apply_flow_ema(self, flow):
+        """Temporally smooth the optical-flow field before HHD.
+
+        The frame-to-frame jitter of the estimated flow is spatially coherent
+        (a near-global shift: it survives ~40x less averaging than per-pixel
+        noise would, see the noise analysis), so it cannot be removed by
+        spatial smoothing, a coarser HHD grid or a different DIS setting - only
+        by averaging along time. Applying it here also stabilises
+        ``vnormal``/contact, which a force-level filter cannot reach.
+
+        ``flow_ema_alpha >= 1`` disables the stage.
+        """
+        alpha = getattr(self, "_flow_ema_alpha", 1.0)
+        if flow is None or alpha >= 1.0:
+            return flow
+        prev = self._ema_flow
+        if prev is None or prev.shape != flow.shape or prev.dtype != flow.dtype:
+            self._ema_flow = np.array(flow, copy=True)
+            return flow
+        prev += alpha * (flow - prev)
+        return prev
+
+    def _update_force_sample_rate(self):
+        """Track the achieved force update rate for the low-pass design.
+
+        A Butterworth designed for 30 Hz stops meaning the same thing at 60 Hz,
+        so when ``force_lowpass_sample_rate_hz`` is ``"auto"`` the rate actually
+        achieved is used. For sources whose wall-clock cadence does not equal
+        signal time (video files, offline replay) ``_lowpass_rate_auto`` is
+        turned off by whoever knows the source - ``__init__`` for a capture the
+        Sensor opened itself, and ``FingerRuntime.open`` for external frames -
+        and the configured camera fps is used instead.
+        """
+        if not getattr(self, "_lowpass_rate_auto", False):
+            return
+        estimator = getattr(self, "_force_rate", None)
+        if estimator is None:
+            return
+        hz = estimator.tick()
+        if not (1.0 <= hz <= 240.0):
+            return
+        self._force_rate_source = "measured"
+        used = self._lowpass_sample_rate_hz
+        if used > 0 and abs(hz - used) <= 0.1 * used:
+            return
+        self._lowpass_sample_rate_hz = hz
+        if self._lowpass_enabled:
+            self._force_filter.configure(
+                cutoff_hz=self._lowpass_cutoff_hz,
+                sample_rate_hz=hz,
+                order=self._lowpass_order,
+            )
+
+    @property
+    def force_sample_rate_hz(self) -> float:
+        """Sample rate currently used to design the force low-pass (Hz)."""
+        return float(self._lowpass_sample_rate_hz)
+
+    @property
+    def force_sample_rate_source(self) -> str:
+        """``config``, ``measured`` or ``config (replay)``."""
+        return str(getattr(self, "_force_rate_source", "config"))
+
     def compute_hhd(self):
 
         flow = self.flow
@@ -543,7 +792,11 @@ class Sensor:
         if k > 1:
             ds_w = max(1, orig_w // k)
             ds_h = max(1, orig_h // k)
-            flow_ds = cv2.resize(flow, (ds_w, ds_h), interpolation=cv2.INTER_AREA)
+            flow_ds = self._hhd_flow_ds_buf
+            if flow_ds is None or flow_ds.shape != (ds_h, ds_w, 2) or flow_ds.dtype != np.float32:
+                flow_ds = np.empty((ds_h, ds_w, 2), dtype=np.float32)
+                self._hhd_flow_ds_buf = flow_ds
+            cv2.resize(flow, (ds_w, ds_h), dst=flow_ds, interpolation=cv2.INTER_AREA)
             if mask_ds is not None and (
                 mask_ds.shape[1] != ds_w or mask_ds.shape[0] != ds_h
             ):
@@ -552,8 +805,13 @@ class Sensor:
             flow_ds = flow
 
         ds_shape = flow_ds.shape[:2]
+        ref_shape = (orig_h, orig_w)
         self.valid_mask_hhd = mask_ds
-        if self.__hhd is None or self._hhd_grid_shape != ds_shape:
+        if (
+            self.__hhd is None
+            or self._hhd_grid_shape != ds_shape
+            or self._hhd_ref_shape != ref_shape
+        ):
             spacings = (18 * k, 18 * k)
             self.__hhd = nHHD(
                 cuda=self.cuda,
@@ -561,6 +819,9 @@ class Sensor:
                 spacings=spacings,
                 poisson_backend=self.poisson_backend,
                 debug=self.debug,
+                # Rescale grid-summed force aggregates back onto the full-resolution
+                # flow grid so Sn/Stx/Sty/Stor stay comparable across hhd_downsample.
+                force_reference_grid=ref_shape,
                 masked_poisson_solver=self.masked_poisson_solver,
                 masked_poisson_max_boundary=self.masked_poisson_max_boundary,
                 masked_poisson_boundary_stride=self.masked_poisson_boundary_stride,
@@ -569,29 +830,46 @@ class Sensor:
                 masked_poisson_reg=self.masked_poisson_reg,
             )
             self._hhd_grid_shape = ds_shape
+            self._hhd_ref_shape = ref_shape
 
         _, forces = self.__hhd.get_force(flow_ds, valid_mask=mask_ds)
         fn, fx, fy, ftor = forces
         self._force_raw = (float(fn), float(fx), float(fy))
         self.ftor = float(ftor)
+        self._update_force_sample_rate()
         self._apply_force_filter()
 
         vnormal_ds = self.__hhd.get_normal()
         vshear_ds = self.__hhd.get_shear()
 
         if k > 1:
-            self.vnormal = cv2.resize(vnormal_ds, (orig_w, orig_h), interpolation=cv2.INTER_LINEAR)
+            # Upsample into reusable buffers; the solver keeps owning its own
-            self.vshear = cv2.resize(vshear_ds, (orig_w, orig_h), interpolation=cv2.INTER_LINEAR)
+            # arrays, so nothing downstream can alias solver state.
+            vn = self._hhd_vn_buf
+            vs = self._hhd_vs_buf
+            if vn is None or vn.shape != (orig_h, orig_w, 2) or vn.dtype != np.float32:
+                vn = np.empty((orig_h, orig_w, 2), dtype=np.float32)
+                vs = np.empty((orig_h, orig_w, 2), dtype=np.float32)
+                self._hhd_vn_buf = vn
+                self._hhd_vs_buf = vs
+            cv2.resize(vnormal_ds, (orig_w, orig_h), dst=vn, interpolation=cv2.INTER_LINEAR)
+            cv2.resize(vshear_ds, (orig_w, orig_h), dst=vs, interpolation=cv2.INTER_LINEAR)
+            self.vnormal = vn
+            self.vshear = vs
         else:
-            self.vnormal = vnormal_ds
+            self.vnormal = vnormal_ds.copy()
-            self.vshear = vshear_ds
+            self.vshear = vshear_ds.copy()
 
         if self.valid_mask is not None:
-            active = self.valid_mask.astype(bool)
+            # In-place multiply by a 0/1 float mask instead of
-            self.vnormal = self.vnormal.copy()
+            # ``x.copy(); x[~active] = 0`` (copy + boolean gather/scatter).
-            self.vshear = self.vshear.copy()
+            m3 = self._hhd_mask_f32
-            self.vnormal[~active] = 0
+            if m3 is None or m3.shape != (orig_h, orig_w, 1) or m3.dtype != np.float32:
-            self.vshear[~active] = 0
+                m3 = np.empty((orig_h, orig_w, 1), dtype=np.float32)
+                self._hhd_mask_f32 = m3
+            np.copyto(m3[:, :, 0], self.valid_mask, casting="unsafe")
+            np.multiply(self.vnormal, m3, out=self.vnormal)
+            np.multiply(self.vshear, m3, out=self.vshear)
 
         self.compute_deformation_valid = True
 
@@ -700,6 +978,9 @@ class Sensor:
         """Reset optical flow tracker and force-filter state."""
         self.__tracker.reset()
         self._force_filter.reset()
+        if getattr(self, "_force_median", None) is not None:
+            self._force_median.reset()
+        self._ema_flow = None
         if self.img is not None:
             self.initial_img = self.img.copy()
 
@@ -743,6 +1024,8 @@ class Sensor:
         lowpass_sample_rate_hz=None,
         lowpass_order=None,
         lowpass_enabled=None,
+        flow_ema_alpha=None,
+        force_median_window=None,
         hhd_downsample=None,
     ):
         """Update runtime-safe settings without reconnecting the camera.
@@ -754,10 +1037,18 @@ class Sensor:
             value enables filtering unless ``lowpass_enabled=False``.
         lowpass_sample_rate_hz : float, optional
             Assumed force sample rate for the Butterworth design (default 30).
+            Set this to the actual output rate of the deployment.
         lowpass_order : int, optional
             Butterworth order (default 2).
         lowpass_enabled : bool, optional
             Explicit on/off for the causal force filter.
+        flow_ema_alpha : float, optional
+            EMA coefficient applied to the optical-flow field before HHD.
+            ``1.0`` disables it; smaller values smooth more (0.5 is the default
+            and costs about one frame of delay at 30 fps).
+        force_median_window : int, optional
+            Causal sliding-median width applied to the raw force triple before
+            the low-pass. ``<= 1`` disables it; 3 is the default.
         hhd_downsample : int, optional
             Integer ``>= 1``. Rebuilds the HHD solver on the next frame.
         """
@@ -768,10 +1059,26 @@ class Sensor:
             if lowpass_enabled is None:
                 self._lowpass_enabled = self._lowpass_cutoff_hz > 0
         if lowpass_sample_rate_hz is not None:
-            rate = float(lowpass_sample_rate_hz)
+            # Accept a positive number to pin the rate, or "auto"/<=0 to track
-            if rate <= 0:
+            # the measured output rate (see _update_force_sample_rate).
-                raise ValueError("lowpass_sample_rate_hz must be > 0")
+            auto = False
-            self._lowpass_sample_rate_hz = rate
+            rate = 0.0
+            if isinstance(lowpass_sample_rate_hz, str):
+                auto = lowpass_sample_rate_hz.strip().lower() in ("auto", "", "measured")
+            else:
+                try:
+                    rate = float(lowpass_sample_rate_hz)
+                except (TypeError, ValueError):
+                    auto = True
+                else:
+                    auto = rate <= 0.0
+            self._lowpass_rate_auto = auto
+            if not auto:
+                self._lowpass_sample_rate_hz = rate
+            elif self._lowpass_sample_rate_hz <= 0:
+                self._lowpass_sample_rate_hz = self._config_fps
+            if getattr(self, "_force_rate", None) is not None:
+                self._force_rate.reset(self._config_fps)
             filter_changed = True
         if lowpass_order is not None:
             order = int(lowpass_order)
@@ -783,6 +1090,22 @@ class Sensor:
             self._lowpass_enabled = bool(lowpass_enabled)
             filter_changed = True
 
+        if flow_ema_alpha is not None:
+            alpha = float(flow_ema_alpha)
+            if not (0.0 < alpha <= 1.0):
+                raise ValueError("flow_ema_alpha must be in (0, 1]")
+            self._flow_ema_alpha = alpha
+            self._ema_flow = None
+
+        if force_median_window is not None:
+            try:
+                window = max(1, int(force_median_window))
+            except (TypeError, ValueError) as exc:
+                raise ValueError("force_median_window must be an integer >= 1") from exc
+            self._force_median_window = window
+            self._force_median.configure(window)
+            filter_changed = True
+
         if filter_changed:
             cutoff = self._lowpass_cutoff_hz if self._lowpass_enabled else 0.0
             self._force_filter.configure(
@@ -802,6 +1125,7 @@ class Sensor:
                 self._hhd_downsample = k
                 self.__hhd = None
                 self._hhd_grid_shape = None
+                self._hhd_ref_shape = None
                 self._update_hhd_mask_cache()
         return self
 
@@ -877,11 +1201,14 @@ class Sensor:
 
     def _apply_force_filter(self):
         raw = np.asarray(self._force_raw, dtype=np.float64)
+        # Median first: it deletes the heavy-tailed spikes that the flow chain
+        # produces, so the low-pass does not have to spread them over time.
+        median = getattr(self, "_force_median", None)
+        if median is not None and median.enabled:
+            raw = median.process(raw)
         if self._lowpass_enabled and self._lowpass_cutoff_hz > 0:
-            filtered = self._force_filter.process(raw)
+            raw = self._force_filter.process(raw)
-            fn, fx, fy = (float(v) for v in filtered)
+        fn, fx, fy = float(raw[0]), float(raw[1]), float(raw[2])
-        else:
-            fn, fx, fy = float(raw[0]), float(raw[1]), float(raw[2])
 
         # Apply loaded force_calibration.json when present; otherwise keep raw.
         if self.calibration is not None:

src/orisys/signal_processing.py

@@ -15,6 +15,8 @@ Prefer ``Sensor.calibration`` / ``read_info(FNORMAL, …)`` in new code.
 
 from __future__ import annotations
 
+import collections
+import time
 from dataclasses import dataclass
 
 import numpy as np
@@ -312,3 +314,115 @@ class LowpassFilter:
             self.reset(x)
         y, self._zi = sosfilt(self._sos, x[None, :], zi=self._zi, axis=0)
         return np.asarray(y[0], dtype=np.float64)
+
+
+class CausalMedianFilter:
+    """Causal sliding-median over the last ``window`` samples, one sample at a time.
+
+    The optical-flow force chain produces heavy-tailed jitter (rare multi-sigma
+    spikes). A linear low-pass spreads such a spike over several frames instead
+    of deleting it, whereas a median removes it outright - measured on idle
+    data, a 5-sample median cut the jitter 4x better than a moving average of
+    the same width.
+
+    ``window <= 1`` disables the filter (pass-through). Until ``window`` samples
+    have arrived the median of the available samples is returned, so the output
+    is well defined from the first frame.
+    """
+
+    def __init__(self, window: int = 1, n_channels: int = 3):
+        self.n_channels = int(n_channels)
+        self.window = 1
+        self._buf = None
+        self.configure(window)
+
+    @property
+    def enabled(self) -> bool:
+        return self.window > 1
+
+    def configure(self, window: int | None = None) -> None:
+        if window is not None:
+            try:
+                self.window = max(1, int(window))
+            except (TypeError, ValueError):
+                self.window = 1
+        self._buf = None
+
+    def reset(self, x0=None) -> None:
+        """Drop the window history (e.g. after a tracker reset)."""
+        self._buf = None
+
+    def process(self, values) -> np.ndarray:
+        """Filter one multi-channel sample. Returns float64 array of shape (n_channels,)."""
+        x = np.asarray(values, dtype=np.float64).reshape(-1)
+        if x.size != self.n_channels:
+            raise ValueError(f"expected {self.n_channels} channels, got {x.size}")
+        if not self.enabled:
+            return x.copy()
+        if self._buf is None or self._buf.shape[1] != x.size:
+            self._buf = x[None, :].copy()
+            return x.copy()
+        self._buf = np.vstack((self._buf, x[None, :]))[-self.window:]
+        return np.median(self._buf, axis=0)
+
+
+class SampleRateEstimator:
+    """Robust online estimate of the rate at which :meth:`tick` is called.
+
+    Uses the *median* of the most recent inter-call intervals, so one stall or
+    scheduling hiccup does not poison the estimate. :attr:`rate_hz` returns the
+    seed value until ``min_samples`` intervals have been observed.
+
+    This exists because a fixed floor filter designed for 30 Hz behaves
+    differently at 60 Hz: the cutoff stays put in Hz but the per-frame
+    smoothing halves. Measuring the achieved rate keeps the filter identical in
+    the time domain whatever the deployment runs at.
+    """
+
+    def __init__(
+        self,
+        initial_hz: float = 30.0,
+        window: int = 45,
+        min_samples: int = 8,
+        max_interval_s: float = 1.0,
+    ):
+        self.initial_hz = float(initial_hz) if initial_hz else 30.0
+        self.window = max(3, int(window))
+        self.min_samples = max(2, int(min_samples))
+        self.max_interval_s = float(max_interval_s)
+        self.reset()
+
+    def reset(self, initial_hz: float | None = None) -> None:
+        if initial_hz is not None:
+            self.initial_hz = float(initial_hz) if initial_hz else 30.0
+        self._dts: collections.deque = collections.deque(maxlen=self.window)
+        self._last = None
+        self._rate = self.initial_hz
+        self._measured = False
+
+    @property
+    def rate_hz(self) -> float:
+        return self._rate
+
+    @property
+    def measured(self) -> bool:
+        """True once the estimate comes from real intervals."""
+        return self._measured
+
+    def tick(self, now: float | None = None) -> float:
+        """Register one sample and return the current rate estimate."""
+        now = time.perf_counter() if now is None else float(now)
+        last, self._last = self._last, now
+        if last is None:
+            return self._rate
+        dt = now - last
+        if not (1e-5 < dt <= self.max_interval_s):
+            # Stalls, pauses and the first frame carry no rate information.
+            return self._rate
+        self._dts.append(dt)
+        if len(self._dts) >= self.min_samples:
+            dt_med = float(np.median(self._dts))
+            if dt_med > 0.0:
+                self._rate = 1.0 / dt_med
+                self._measured = True
+        return self._rate

src/orisys/tracker.py

@@ -94,13 +94,30 @@ class Tracker:
         return mask.astype(bool)
 
     def apply_valid_mask(self, flow, valid_mask, erode_iters=1):
-        """Zero flow outside the valid UV domain."""
+        """Zero flow outside the valid UV domain (in place when safe).
+
+        Multiplying by a 0/1 mask is a single streaming pass, whereas
+        ``flow.copy()`` followed by a boolean fancy-index assignment costs a
+        full copy plus a gather/scatter over the masked-out pixels.
+
+        Note: a masked-out *negative* component becomes ``-0.0`` rather than
+        ``+0.0``. The two compare, sum and magnitude identically; only the raw
+        bit pattern of those zeros differs from the previous implementation.
+        """
         if flow is None or valid_mask is None:
             return flow
         mask = self._prepare_valid_mask(valid_mask, flow.shape[:2], erode_iters=erode_iters)
-        flow_out = flow.copy()
+        if not getattr(self, "_Tracker__adaptive", False):
-        flow_out[~mask] = 0
+            # The non-adaptive path hands back the DIS state buffer, which feeds
-        return flow_out
+            # the next frame as its initial guess; never mutate it.
+            flow_out = flow.copy()
+            flow_out[~mask] = 0
+            return flow_out
+        if not flow.flags.writeable:
+            flow = flow.copy()
+        mask_f = mask.astype(np.float32, copy=False)[:, :, None]
+        np.multiply(flow, mask_f, out=flow)
+        return flow
 
     def track(self, frame, valid_mask=None):
         """Main tracking function that dispatches to CUDA or CPU implementation"""