Differences

This shows you the differences between two versions of the page.

--- newsletters:2026-07 [2026/08/18 17:10] – [API redesign] osnr
+++ newsletters:2026-07 [2026/08/18 17:21] (current) – [Correction experiments] osnr
@@ Line 257: / Line 257: @@
 {{.:pasted:20260813-162034.png?400px}}
+All these pages have a 1-1 correspondence between registration page and object. You need to print multiple registration pages to track multiple objects in parallel. We might change this soon. (It is nice because you can just make the object ID from the registration page ID and point to the registration page to clear/hold state.)
 === Web UIs ===
 We have a few interesting web debugging UIs for SAM2 tracking.
-SAM2 per-object mask views:
+SAM2 per-object mask views, so you can see what SAM2 has locked onto if anything:
 {{newsletters:screenshot-2026-07-10-at-3.34.23-pm.png?300px}}
-Camera slice /camera-slice/VIEWPORT view -- this is what the camera sees, rewarped to make the viewport rectangular:
+Camera slice /camera-slice/ID view -- this is what the camera sees, rewarped to make the object ID you're slicing rectangular and axis-aligned (two slices side-by-side here: the viewport and a blank page inside the viewport):
-{{newsletters:screenshot-2026-07-10-at-3.56.20-pm.png?300px}}
 {{newsletters:screenshot-2026-07-24-at-2.50.55-pm.png?600px}}
@@ Line 296: / Line 294: @@
 == Camera-facing arc experiment ==
-Omar had the idea that we just look at where the object is relative to the camera and exclude the side that's likely to be distorted.
+Omar had the idea that we just look at where the object is relative to the camera and exclude the side that's likely to be distorted. Here, the camera is above and to the right of the viewport, so we cast rays from the camera to the convex hull of the contour of the object and take that green arc between the two tangent points:
 {{newsletters:screenshot-2026-07-24-at-5.11.38-am.png?400px}}
 {{newsletters:img_6973.mp4?350px}}
+That should get us the 'side' of the contour that is touching the viewport plane (should be unaffected by moving the cup further away or to different sides of the camera, unlike just finding centroid of contour), and then we fit a circle of the right diameter to it? More on this next month.
 === Issues ===