What is missing: A mechanism to detect custom or rare objects that are not part of the standard ZED SDK models, implemented using a flexible open-vocabulary engine (YOLO-World) and custom 3D mapping.
Where:src/engines/open_vocab.cc/h.
Observable effect: When configured, the node detects arbitrary objects defined by a text vocabulary. It manually fuses the generated 2D bounding boxes with the ZED point cloud to calculate accurate 3D positions for non-standard items.
**What is missing:** A mechanism to detect custom or rare objects that are not part of the standard ZED SDK models, implemented using a flexible open-vocabulary engine (YOLO-World) and custom 3D mapping.
**Where:** `src/engines/open_vocab.cc/h`.
**Observable effect:** When configured, the node detects arbitrary objects defined by a text vocabulary. It manually fuses the generated 2D bounding boxes with the ZED point cloud to calculate accurate 3D positions for non-standard items.
cristhian
added this to the v0.1.0 - Reusable Vision Engine milestone 2026-03-24 20:44:50 +00:00
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
What is missing: A mechanism to detect custom or rare objects that are not part of the standard ZED SDK models, implemented using a flexible open-vocabulary engine (YOLO-World) and custom 3D mapping.
Where:
src/engines/open_vocab.cc/h.Observable effect: When configured, the node detects arbitrary objects defined by a text vocabulary. It manually fuses the generated 2D bounding boxes with the ZED point cloud to calculate accurate 3D positions for non-standard items.