newsletters:2026-08
Differences
This shows you the differences between two versions of the page.
| Both sides previous revisionPrevious revisionNext revision | Previous revision | ||
| newsletters:2026-08 [2026/09/22 14:17] – [Localization] osnr | newsletters:2026-08 [2026/09/22 14:20] (current) – [Object tracking] osnr | ||
|---|---|---|---|
| Line 130: | Line 130: | ||
| * Raw centroid of contour | * Raw centroid of contour | ||
| * Compute centroid transform by registering centers at a few different points | * Compute centroid transform by registering centers at a few different points | ||
| - | * Same-side arc contour | + | * Same-side arc contour |
| - | * Opposite-side arc contour | + | * {{.: |
| + | * This was most promising for a while and felt most principled | ||
| Interpolation (SAM2 is pretty slow, 60-100ms per frame)? | Interpolation (SAM2 is pretty slow, 60-100ms per frame)? | ||
| Line 208: | Line 209: | ||
| - Successful RN16 response from tag, we decode it correctly, send the correct RN16 back, then get an EPC from tag, then decode it incorrectly and fail checksum | - Successful RN16 response from tag, we decode it correctly, send the correct RN16 back, then get an EPC from tag, then decode it incorrectly and fail checksum | ||
| - Successful RN16, decode correctly, send correct RN16 back, get EPC from tag, decode correctly, checksum succeeds. We have a valid EPC from the tag! | - Successful RN16, decode correctly, send correct RN16 back, get EPC from tag, decode correctly, checksum succeeds. We have a valid EPC from the tag! | ||
| + | |||
| + | (These are tiers for an individual hop. There' | ||
| We're starting to break these tiers out into the PC UI. | We're starting to break these tiers out into the PC UI. | ||
newsletters/2026-08.1790086650.txt.gz · Last modified: by osnr
