Skip to content

I
imagej-elphel
Switch branch/tag
  1. 25 Jun, 2026 17 commits
  3. 21 Jun, 2026 6 commits
    • Andrey Filippov's avatar
      Added logging · 95e25fcc
      Andrey Filippov authored
      95e25fcc
    • Andrey Filippov's avatar
      CLAUDE: -OFFSET in px (s-first, full-frame meta, s-gated NaN); curt_dnn_thresh... · 571ef32e
      Andrey Filippov authored 
      CLAUDE: -OFFSET in px (s-first, full-frame meta, s-gated NaN); curt_dnn_thresh viz-only (recurrent gets full field)

-OFFSET (remote) reordered to {s,Vx,Vy,dx,dy} (s first -> ImageJ auto-ranges on it); Vx,Vy converted cells->px/level-frame (/vel_decimate); full-frame ROI written to the file metadata (self-describes its extent); Vx,Vy,dx,dy NaN'd where s<curt_dnn_thresh (s kept). curt_dnn_thresh is now VISUALIZATION-ONLY: the local inferROI feeds Layer 2 the FULL field (sThresh=0) so the recurrent gets the weak sub-threshold signal it integrates (no premature threshold = the LReLU lesson); dialog label/tooltip/decl updated to say viz-only, do-not-use-for-computation.
Co-Authored-By: 's avatarClaude Opus 4.8 (1M context) <noreply@anthropic.com>
      571ef32e
    • Andrey Filippov's avatar
      CLAUDE: GenericJTabbedDialog - don't stretch checkboxes (fix accidental toggle) · 3c144146
      Andrey Filippov authored 
      Checkboxes were laid out with fill=HORIZONTAL, stretching the (text-less) JCheckBox across the half-width cell so its click target reached the scrollbar - a near-scrollbar miss-click silently toggled them (this flipped 'DNN remote' off mid-session). Anchor checkboxes WEST at natural size; the rest of the cell is now dead space. Applies to all tabbed dialogs.
Co-Authored-By: 's avatarClaude Opus 4.8 (1M context) <noreply@anthropic.com>
      3c144146
    • Andrey Filippov's avatar
      CLAUDE: Batch the DGX remote DNN path + on-GPU ghostbuster · 5bee1911
      Andrey Filippov authored 
      runDnnRemote requests each level's scenes in chunks (REQ=64) via CuasDnnRemote.inferBatch instead of per-scene; the DGX runs them continuously (production-representative ~100ms/scene full-res) and applies the ghostbuster on the GPU in decode, so BOTH the ROI 121-cell field and the full-frame -OFFSET {dx,dy,s,Vx,Vy} are ghostbusted (dropped the Java-side ghostbust). Validated: local vs remote on the same weighted9_pm_s model -> max |diff| ~1e-4 (ORT per-pixel vs PyTorch shift-and-stitch fp). Full-res ~100ms/scene is the oracle; RT would use the 1/4-res single forward (~4.4ms).
Co-Authored-By: 's avatarClaude Opus 4.8 (1M context) <noreply@anthropic.com>
      5bee1911
    • Andrey Filippov's avatar
      CLAUDE: Port ghostbuster to the remote DNN path (match CPU -HYPER-RECT) · 01a6e535
      Andrey Filippov authored 
      runDnnRemote() decoded the raw softmax*s field but skipped dnnGhostbust, so the untrained corner-velocity sidelobes (which the local CPU path zeros when curt_dnn_vmax>0) survived as background noise (~0.06 vs ~5e-4 on the MAX-all-v layer). Apply dnnGhostbust to the ROI field, mirroring the local path -> verified: ImageJ subtract of -HYPER-RECT MAX slices vs the CPU (17_UAS_REFACTORED) is exact zero. (Full-frame -OFFSET s is not yet ghostbusted - Java lacks the full 121-field; a DGX-side decode ghostbuster would cover that.)
Co-Authored-By: 's avatarClaude Opus 4.8 (1M context) <noreply@anthropic.com>
      01a6e535
    • Andrey Filippov's avatar
      CLAUDE: Add DGX remote DNN inference path (full-res shift-and-stitch) · 69753750
      Andrey Filippov authored 
      detectTargets() can offload the DNN front-end to the GB10 DGX (curt_dnn_remote): CuasDnnRemote uploads the LoG-conditioned stack once, the DGX builds the pyramid and runs full-res shift-and-stitch per (level,scene), returning the full-frame {dx,dy,s,Vx,Vy} (-OFFSET) + ROI 121-cell softmax*s (-RECT/-HYPER-RECT). Auto-launches the server if down (bundled cuas_dnn/ scripts, or curt_dnn_remote_srcdir local-repo override - mirrors the GPU-kernel default-vs-override). Synthetic targets are mixed into the upload stack so synth works on the remote path. 4 curt_dnn_remote_* dialog params, grouped with the model fields. Local CPU path unchanged (curt_dnn_remote=false) for Layer 2. Validated end-to-end; shift-and-stitch is fp64-exact vs per-pixel.
Co-Authored-By: 's avatarClaude Opus 4.8 (1M context) <noreply@anthropic.com>
      69753750
  5. 20 Jun, 2026 3 commits
    • Andrey Filippov's avatar
      CLAUDE: CUAS cleanup pt2 — scrub dead 3d3/MF leftover symbols · 5df977ab
      Andrey Filippov authored 
      Dead after the 3d3/matched-filter removal (predecessor at tag cuas-layer1):
render3d3Hyperstack, get3d3Radius + the 3d3 kernel state (kernel3d3_rad, indx_*_3d3)
with its constructor param/setup/call-site; TemporalKernelGenerator.generateKernelMatched/Direct;
CuasDetectRT SUFFIX_CONV3D3, CONV3D3_MODES, bilinearFrame. No live callers; build OK.
Co-authored-by: 's avatarClaude Opus 4.8 (1M context) <noreply@anthropic.com>
      5df977ab
    • Andrey Filippov's avatar
      CLAUDE: CUAS cleanup — remove pre-DNN/dead paths; LReLU -> linear · 4abf02b0
      Andrey Filippov authored 
      Layer-1 is DNN-only; predecessor code preserved at git tag cuas-layer1.
Removed: 3d3 coarse-velocity path (curt_3d3_*, rleak1, convolve3D3LReLU);
C5P matched-filter / Bayes-posterior / whitening (curt_c5_matched/en/post/.../white*/from_pix);
LReLU rectification (curt_rleak0/pyr -> linear alpha=1, LoG kept);
distribution-vote (-GVOTE/-GHEADS, voteScatterGrid); curt_dnn_t8frac.
28 dialog params dropped; dialogQuestions/dialogAnswers re-verified aligned (44 widgets = 44 getNext). ~1841 lines removed.
Deprecated (kept): curt_stage2_model, MF-S S convention.
Kept: DNN front-end, recurrent, synth-test, SUBAVG, pyramid, LoG (linear). Build OK.

Runtime-untested (dialog) — verify a run; restore point: tag cuas-layer1.
Co-authored-by: 's avatarClaude Opus 4.8 (1M context) <noreply@anthropic.com>
      4abf02b0
    • Andrey Filippov's avatar
      CLAUDE: CUAS Layer-1 — synth bg-avg fast path + Time-ROI window + MF-S head · 1d9ef9a8
      Andrey Filippov authored 
      - IntersceneMatchParameters: add curt_synth_bg_avg (synth quick-run: average N=2^LEV real
  frames per output frame and force a single level — restores the fast synthetic+background path).
- CuasDetectRT: that fast synth path (decimate-average to a short sequence + single level),
  honoring "Time ROI to" for the averaged-sequence length.
- CuasDnnInfer: MF-S head reads channel 0 as the raw matched-filter path-sum (clamp>=0, no sigmoid).

Validated: weighted model tracks the real UAS sub-pixel at LEV2/3; linear conditioning
(LReLU off) is dropout-free and matches the no-LReLU training. Checkpoint before Layer 2.
Co-authored-by: 's avatarClaude Opus 4.8 (1M context) <noreply@anthropic.com>
      1d9ef9a8
  7. 19 Jun, 2026 1 commit
  9. 18 Jun, 2026 12 commits
    • Andrey Filippov's avatar
      CLAUDE: v2 Stage-2 Hough-vote wiring + curt_c5_en flag + ORT log fix · a2a2a22d
      Andrey Filippov authored 
      - CuasStage2Infer: ONNX runner for the learned Stage-2 vote-refine (full-field conv).
- CuasDetectRT: voteScatter (s^2-weighted bilinear splat at tail T=P-V*(N-1)) + reg-branch
  wiring -> saves -VOTE heatmap + -REFINED detection when curt_stage2_model is set;
  curt_c5_en gates the heavy C5P convolve (DNN-only fast path).
- IntersceneMatchParameters: curt_c5_en + curt_stage2_model params (all 6 sites each).
- CuasDnnInfer: setSessionLogLevel(ERROR) to suppress benign ORT VerifyOutputSizes warnings.
Co-Authored-By: 's avatarClaude Opus 4.8 (1M context) <noreply@anthropic.com>
      a2a2a22d
    • Andrey Filippov's avatar
      CLAUDE: fopen_pose_compare.py — handle timestamp-named COLMAP images · 2f169094
      Andrey Filippov authored 
      parse_images_txt() now accepts both frame_NNN names and timestamp names
(e.g. 1763232419_474661.png). Introduces sort_key (float) so entries
sort correctly regardless of naming style. fno stays -1 for timestamp
images since no integer frame number is present.
Co-authored-by: 's avatarClaude <claude@elphel.com>
      2f169094
    • Andrey Filippov's avatar
      CLAUDE: Add printer_kvm.py — Ender 3 physical stylus control for phone touchscreen · 00a639ff
      Andrey Filippov authored 
      Serial (USB/CH340G, 115200 baud) G-code driver for Creality Ender 3.
Provides tap(), swipe(), home(), calibrate() over /dev/ttyUSB0.
Part of the NanoKVM + Ender 3 physical phone-control project.
Co-authored-by: 's avatarClaude <claude@elphel.com>
      00a639ff
    • Andrey Filippov's avatar
      CLAUDE: fopen_turn_finder.py — add lat/lon from *-ims.corr-xml · 9942ae46
      Andrey Filippov authored 
      *-ims.corr-xml in the scene root dir always has an INS-fused GPS fix
(did_ins_2-lla, fallback did_gps1_pos-lla) giving the representative
position of the sequence for map location.

Changes:
- find_xml_files: also yields ims_path (*-ims.corr-xml from scene root)
- parse_lla(): reads lat/lon from INS or GPS1 LLA entry
- lat/lon added to metrics, console tables, and TSV output
Co-authored-by: 's avatarClaude <claude@elphel.com>
      9942ae46
    • Andrey Filippov's avatar
      CLAUDE: fopen_turn_finder.py — add AGL from elevations_histogram.csv · 2b1e81b3
      Andrey Filippov authored 
      *-elevations_histogram.csv (row 2, col 1) gives flight altitude above
ground level for each sequence.  Low AGL (<25-50 m) correlates with
algorithm failures in dense-canopy areas.

Changes:
- find_xml_files: also yields hist_path (*-elevations_histogram.csv)
- parse_agl(): reads AGL from second row, first column (tab-separated)
- agl_m added to sequence metrics dict and TSV output
- --min_agl filter: hide sequences below given AGL from console output
- AGL column shown in console tables
Co-authored-by: 's avatarClaude <claude@elphel.com>
      2b1e81b3
    • Andrey Filippov's avatar
      CLAUDE: fopen_turn_finder.py — use _dt rates, add glitch filter · 1d5fdb15
      Andrey Filippov authored 
      Finite-diff vel1 was dominated by single-frame pose glitches from
algorithm failures (low altitude / dense canopy), giving 600+ deg/s
for sequences where _dt shows ~10 deg/s.

Changes:
- parse _dt entries (algorithm's smooth polynomial derivatives) as
  primary velocity metric — unaffected by pose glitches
- keep finite-diff as secondary; glitch = fd_max / dt_max
  (~1 = clean data, >>1 = pose jumps / algorithm failure)
- --max_glitch filter hides suspect sequences from console output
  (TSV always contains all rows for Calc analysis)
- removed windowed finite-diff (vel5) — _dt makes it redundant
Co-authored-by: 's avatarClaude <claude@elphel.com>
      1d5fdb15
    • Andrey Filippov's avatar
      CLAUDE: Add fopen_turn_finder.py — find sharpest turns across all INTERFRAME.corr-xml · b925f5dc
      Andrey Filippov authored 
      Scans all scene dirs under a linked data root, parses each
*-INTERFRAME.corr-xml (latest version subdir), and computes per-sequence
angular metrics for A/T/R axes:
  - range (max−min, deg)
  - vel1: max consecutive |Δangle|/Δt (deg/s) — fast, noise-sensitive
  - velW: max W-frame windowed |Δangle|/Δt (deg/s) — robust (default W=5)

A/T/R Cessna-nadir convention documented: R=heading, T=banking, A=pitch.
Sequence-length/altitude note documented: metrics are Δt-normalised.
Outputs ranked console tables and optional TSV.
Co-authored-by: 's avatarClaude <claude@elphel.com>
      b925f5dc
    • Andrey Filippov's avatar
      CLAUDE: fopen_pose_compare.py — clean CSV/TSV output for Calc analysis · 313276ef
      Andrey Filippov authored 
      - flat column names (no _x_y_z suffix, single comparison set)
- XML angles in degrees (not radians) — more useful for Calc plotting
- auto TSV when --out ends in .tsv, CSV otherwise
- column comment block documents layout in the source
Co-authored-by: 's avatarClaude <claude@elphel.com>
      313276ef
    • Andrey Filippov's avatar
      CLAUDE: fopen_pose_compare.py — add frame-numbering cross-reference docs · 3c05de2f
      Andrey Filippov authored 
      Documents the ImageJ (1-based slice:timestamp), INTERFRAME.corr-xml
(timestamp_microseconds key), and COLMAP (0-based frame_NNNN) conventions
in the module docstring so any frame can be cross-referenced across tools.
Also clarifies the underscore→dot timestamp conversion in parse_interframe_xml.
Co-authored-by: 's avatarClaude <claude@elphel.com>
      3c05de2f
    • Andrey Filippov's avatar
      CLAUDE: fopen_pose_compare.py — use timestamp as frame identity, drop scene_idx · 40bc3da4
      Andrey Filippov authored 
      Timestamps are unambiguous when using sub-sequences (e.g. 378 of 498
frames).  0-based sequential scene_idx was misleading.

- console top-N table: Scene column replaced with Timestamp
- CSV: scene_idx column removed, timestamp is the identity column
- parse_interframe_xml: drop scene_idx from returned dicts
Co-authored-by: 's avatarClaude <claude@elphel.com>
      40bc3da4
    • Andrey Filippov's avatar
      CLAUDE: fopen_pose_compare.py — remove egomotion.csv support, --xml only · 730211c2
      Andrey Filippov authored 
      *-egomotion.csv is a human-readable output file for Calc analysis, not
a machine input source.  *-INTERFRAME.corr-xml is the internal state
always present alongside processed data and is the correct programmatic
source for x/y/z/a/t/r poses.

- remove parse_egomotion_csv() and --ego argument
- --xml is now required
- remove IMS/PIMU col_specs (not in XML)
- rename CSV output columns: ego_* → xml_*, ers_*_rad → xml_*_rad
Co-authored-by: 's avatarClaude <claude@elphel.com>
      730211c2
    • Andrey Filippov's avatar
      CLAUDE: fopen_pose_compare.py — accept --xml (INTERFRAME.corr-xml) as pose source · 81f67ed0
      Andrey Filippov authored 
      --ego (egomotion.csv) was required but is not always present (it is an
optional output file).  --xml (*-INTERFRAME.corr-xml) is always written
by the pipeline and contains the same x/y/z/a/t/r values.

Changes:
- add parse_interframe_xml(): sorts timestamps → same frame order as COLMAP
- --xml is the new preferred input; --ego is optional and overrides --xml
  (it additionally provides IMS/PIMU columns)
- at least one of --xml or --ego is required
- IMS/PIMU [SKIP] messages suppressed when using XML (NaN is expected)
- verified: XML and egomotion.csv produce identical results
Co-authored-by: 's avatarClaude <claude@elphel.com>
      81f67ed0
  11. 17 Jun, 2026 1 commit
    • Andrey Filippov's avatar
      CLAUDE: Deploy continuous-velocity (reg) DNN head in Java (T7) · d345d6fc
      Andrey Filippov authored 
      CuasDnnInfer auto-detects reg from the ONNX output channels (6 = reg head
{det,Vx,Vy,logvar,dx,dy}, else grid) via getOutCh()/isReg(), and adds
inferROIReg() returning {S,Vx,Vy,sigma,dx,dy} per ROI pixel (S=sigmoid(det),
Vx/Vy model-bounded, sigma=exp(logvar/2)). CuasDetectRT branches: reg saves an
S-first {S,Vx,Vy,sigma} hyperstack (-VXYS) + -OFFSET (showArraysHyperstack,
channel x time x ROI), metadata-tagged; ghostbuster/grid renders/recurrent
skipped (no grid corners, |v|<=vmax baked in). Set curt_dnn_patch=32 for the
reg model; curt_dnn_vmax unused in reg mode.
Co-Authored-By: 's avatarClaude Opus 4.8 (1M context) <noreply@anthropic.com>
      d345d6fc