Hi Everyone!
I was hoping if I can get some pointer for the problem below.
I have recorded .SVO file. Using the (x,y) coordinates of the object of interest, I have been able to get the depth at that particular (x,y). Is it possible to also get the position, velocity or 3D bounding boxes coordinates for the particular (x,y) coordinates?
Thanks!
Hi @Navraj09
Welcome to the Stereolabs community.
The SVO can be used as an input of the ZED SDK in the same way you use a standard live camera, so you can process it by using the ZED SDK API.
The Object Detection examples and tutorials can guide you.
Hi @Myzhar. I have been using the SVO file as input to get the Depth value for (x,y) pixel coordinates. I looked into tutorial and demos but couldn’t understand how I can use the (x,y) of object to get information like 3D position, Velocity. Given (x,y,h,w) of a bounding box how can I get 3D position information for the bounding box?
The 3D information is available in the Object data structure:
C++: ObjectData Class Reference | API Reference | Stereolabs
Python: ObjectData Class Reference | API Reference | Stereolabs