- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hello, I would like to describe the work I am doing.
I need pose data for my own dataset (not KITTI dataset), when I run rs-data-collect tool https://github.com/IntelRealSense/librealsense/tree/master/tools/data-collect it generates pose file but if I want it for my images how to work it, do we need to change something in code.
Could you please help me to find pose data for my own dataset .
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Only the T265 Tracking Camera model has pose support built in. Though pose support is not built in to the 400 Series depth cameras like it is for the T265 Tracking Camera, RealSense users have found workarounds to get pose with the 400 Series using OpenCV or with 'inference' in ROS.
A user who was using a robot arm for bin picking got pose with a D435 with an OpenCV SolvePnP algorithm.
https://github.com/IntelRealSense/librealsense/issues/3569#issuecomment-475896784
The link below, meanwhile, has an approach to getting object pose with D435 and ROS.
https://github.com/NVlabs/Deep_Object_Pose/issues/10
If you have a T265, the link below has a sample program for getting pose.
https://github.com/IntelRealSense/librealsense/tree/master/examples/pose

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page