auto: the long labels requalified as analyses like the others, <STATION>_<start>_<end>/ with request.json (ex long-labels/<STATION>/); their labels carry the analysis; work/ out of git

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
maximeandClaude Opus 5.5 committed 2026-11-18 07:16:59 +01:00
1 parent ddb17c2189
commit 764af7d8ec
132 files changed
+125 -9256

No files matched your search

+5 -5
View File
@@ -1,8 +1,8 @@
{"id": "SNCF01-1", "start": "2026-10-04T00:00Z", "end": "2026-11-01T00:00Z", "family": "Target issue", "description": "BG.1: all its measurements are rejected, from the start of the data to the end of the batch; its curve is missing entirely. Its recognition error stays above the threshold, by day and by night, whatever the weather; on the night image its spot appears doubled. Target permanently poorly seen (orientation, installation or configuration to be checked): act on the target; no curve to read.", "review": "2026-11-17"}
{"id": "SNCF01-2", "start": "2026-10-04T00:00Z", "end": "2026-11-01T00:00Z", "family": "Target issue", "description": "F4.1: all its measurements are rejected over the batch; its curve is missing entirely. Its recognition error stays above the threshold permanently; on the images its spot is small and faint. Target permanently poorly seen: act on the target; no curve to read.", "review": "2026-11-17"}
{"id": "SNCF01-3", "start": "2026-10-04T00:00Z", "end": "2026-11-01T00:00Z", "family": "Target issue", "description": "CV.7: most of its measurements are rejected over the whole batch, its recognition error oscillating around the threshold; its curve has only scattered points, and the last ones accepted, at the end of the batch, move strongly away from its level without anything else moving. Target permanently poorly seen (by day, its spot touches the edge of a bright structure on the image): act on the target; ignore its curve.", "review": "2026-11-17"}
{"id": "SNCF01-4", "start": "2026-10-04T00:00Z", "end": "2026-11-01T00:00Z", "family": "Target issue", "description": "F4.4: most of its measurements are rejected over the whole batch, its recognition error staying stuck to the threshold; its curve has only scattered, noisy points. Faint, doubled spot on the night image. Target permanently poorly seen: act on the target; ignore its curve.", "review": "2026-11-17"}
{"id": "SNCF01-7", "start": "2026-10-04T00:00Z", "end": "2026-11-01T00:00Z", "family": "Displacement", "description": "Over the whole batch, as one single episode, the corrected curves of many targets drift slowly, with no return: corr_y rises on BG.2, F4.5, F4.6, P4, CV.8, F4.3, P5, and drops on P1, P7, CV.1; corr_x drops on P2, P3, P4, F4.6; the drift flattens at the end of the month; part of the drop of P7, CV.1 comes from the jump of 15/10 in the morning, labelled separately. At the same time, the camera rotation drops and its tilt rises slowly, the reprojection error of the references increases and, relative to the overall movement of the targets, the positions of the targets relative to one another change more and more over the month (P1, P7, F4.5, BG.2 especially), like those of the references: the whole scene slowly deforms in the image, while the camera tilts. No temperature is available for this station (empty metrics); the cause is not established (seasonal cooling, incomplete compensation of the camera tilt, a reference that moves, or a movement of the wall). The movement of the structure is not established: to be watched.", "review": "2026-11-17"}
{"id": "SNCF01-1", "start": "2026-10-04T00:00Z", "end": "2026-11-01T00:00Z", "family": "Target issue", "description": "BG.1: all its measurements are rejected, from the start of the data to the end of the batch; its curve is missing entirely. Its recognition error stays above the threshold, by day and by night, whatever the weather; on the night image its spot appears doubled. Target permanently poorly seen (orientation, installation or configuration to be checked): act on the target; no curve to read.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-11-01T0000"}
{"id": "SNCF01-2", "start": "2026-10-04T00:00Z", "end": "2026-11-01T00:00Z", "family": "Target issue", "description": "F4.1: all its measurements are rejected over the batch; its curve is missing entirely. Its recognition error stays above the threshold permanently; on the images its spot is small and faint. Target permanently poorly seen: act on the target; no curve to read.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-11-01T0000"}
{"id": "SNCF01-3", "start": "2026-10-04T00:00Z", "end": "2026-11-01T00:00Z", "family": "Target issue", "description": "CV.7: most of its measurements are rejected over the whole batch, its recognition error oscillating around the threshold; its curve has only scattered points, and the last ones accepted, at the end of the batch, move strongly away from its level without anything else moving. Target permanently poorly seen (by day, its spot touches the edge of a bright structure on the image): act on the target; ignore its curve.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-11-01T0000"}
{"id": "SNCF01-4", "start": "2026-10-04T00:00Z", "end": "2026-11-01T00:00Z", "family": "Target issue", "description": "F4.4: most of its measurements are rejected over the whole batch, its recognition error staying stuck to the threshold; its curve has only scattered, noisy points. Faint, doubled spot on the night image. Target permanently poorly seen: act on the target; ignore its curve.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-11-01T0000"}
{"id": "SNCF01-7", "start": "2026-10-04T00:00Z", "end": "2026-11-01T00:00Z", "family": "Displacement", "description": "Over the whole batch, as one single episode, the corrected curves of many targets drift slowly, with no return: corr_y rises on BG.2, F4.5, F4.6, P4, CV.8, F4.3, P5, and drops on P1, P7, CV.1; corr_x drops on P2, P3, P4, F4.6; the drift flattens at the end of the month; part of the drop of P7, CV.1 comes from the jump of 15/10 in the morning, labelled separately. At the same time, the camera rotation drops and its tilt rises slowly, the reprojection error of the references increases and, relative to the overall movement of the targets, the positions of the targets relative to one another change more and more over the month (P1, P7, F4.5, BG.2 especially), like those of the references: the whole scene slowly deforms in the image, while the camera tilts. No temperature is available for this station (empty metrics); the cause is not established (seasonal cooling, incomplete compensation of the camera tilt, a reference that moves, or a movement of the wall). The movement of the structure is not established: to be watched.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-11-01T0000"}
{"id": "SNCF01-39", "start": "2026-10-14T07:15Z", "end": "2026-10-15T01:15Z", "family": "Thermal displacement", "description": "Daytime thermal cycle (14/10): from the morning, the pan and the tilt of the camera drop and its scale rises, then they slowly come back in the afternoon, the evening and the night, until the camera comes to rest around one in the morning; the two-in-the-morning gap and the camera jump of the early morning, labelled separately, come after this rest. The corrected curves follow the same cycle, poorly compensated: corr_x of P7, P5, P6 and corr_y of P5, P6, P7, P4 move away from their night level during the day then come back, partly all at once at nightfall, when the recognition error also comes back (the lighting plays a part). Deduced cause: the camera and its mount move with the heat of the day (camera pose); the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-98", "start": "2026-10-14T09:30Z", "end": "2026-10-14T16:30Z", "family": "Visibility", "description": "By day (14/10), in the sun (hard shadows on the wall on the image of 13:00): the corrected curves of the low targets fluctuate much more than at night, from one measurement to the next, with one-measurement jumps that come back at once, mostly CV.4, CV.2, F4.3, CV.6, F4.2, BG.2, F4.5 and F4.6, and CV.2 and CV.4 are rejected at times; the night before and the evening after are calm. Deduced cause: heat shimmer from the air heated above the tracks (a fast noise over the scene, by sunny day only), not visible as such on the images; some rejections of CV.2 and CV.4, low targets, may also come from passages, not seen. Do not trust the small movements of these curves by day; this is not a movement of the structure.", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-99", "start": "2026-10-14T10:30Z", "end": "2026-10-14T11:00Z", "family": "Obstruction", "description": "One single measurement: CV.2, CV.4 and CV.8 are rejected, their curves are missing, the recognition error of the reference BG.3.1 jumps strongly while staying under its threshold, and CV.6, F4.2 and F4.6 make a corr jump that comes back at the next measurement. Cause: a passage in front of the bottom of the scene and of BG.3.1, deduced from the signature (several low targets and a reference hit together for one measurement; no image at that minute, the station takes one per hour). The structure is not moving: point to ignore, nothing to do.", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}