Files
aimsight-libredesk/snippets/textes/one-target-is-no-longer-being-measured-what-should-i-check.md
T
maximeandClaude Opus 5.5 10ed887417 Noms plus clairs : snippets/, scripts de test numérotés, verifier_ollama.py
- base_connaissances/ → snippets/ (corpus/ → textes/, instructions.md → consignes_redaction.md, decoupage.py → fichiers.py, importer.py → envoyer.py) ; python3 -m snippets.envoyer.
- instance-de-test/ : 1_demarrer.sh, 2_creer_boite_et_cle.py, 3_brancher_ia.py, 4_essayer_brouillons.py, voir_empreintes.sh, connexion_admin.py.
- ollama/verifier.py → ollama/verifier_ollama.py ; tests, tâches VS Code et docs alignés.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 10:27:06 +01:00

31 lines
1.6 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# One target is no longer being measured. What should I check?
First inspect the corresponding camera image and the target’s Error Value.
Check:
• whether the target is still visible;
• whether the target is still inside its processing area;
• whether the Error Value has increased above the configured Error Threshold;
• whether the target is partially or completely obstructed;
• whether the target is dirty, damaged, or covered by water, dust, snow, vegetation, or
another object;
• whether a reflective target or prism has changed orientation;
• whether illumination conditions have changed significantly;
• image focus and exposure;
• whether the camera itself has moved significantly;
• whether the physical target has undergone a displacement larger than the configured
processing area.
If several targets become invalid simultaneously, also check:
• camera movement;
• focus or contamination of the camera window;
• illumination conditions;
• communication with the camera;
• the reference-network fit and sigma0.
If the Error Value exceeds the threshold, the measurement is normally rejected rather than
interpreted as a valid displacement.
The current image, the target-recognition metrics, Camera Movement, and sigma0 are generally
the fastest way to distinguish an optical or visibility problem, camera instability, referencenetwork deformation, and an actual displacement. When AIMsight Cloud is included, a
measurement can be opened together with its corresponding archived image, making it easier to
identify the cause of an abnormal value without first retrieving image files separately.
Source : AIMsight FAQ, rév. 1.5