Integration of CenterPoseTrack (ICRA 2022) to isaac_ros_centerpose

Open
#70 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
5/5
Estimated time
Over a week
Newbie friendliness
25/100
Issue type
Feature
Clarity
Needs clarification
Activity status
Stale
Tech stack
cpp
Domain
computer-vision, machine-learning, robotics

Research direction

Start by reviewing the existing isaac_ros_centerpose package and the CenterPoseTrack project linked in the issue, then identify how tracking would fit into the current inference flow. Done means CenterPoseTrack is integrated and consecutive-frame CenterPose results have improved consistency, with appropriate validation of the inference behavior.

Written by the indexing model from the issue text.

Description

Since centerpose inference results have inconsistencies frame to frame (even for consecutive frames), could you please integrate CenterPoseTrack project (also from NVIDIA) published in ICRA 2022 to isaac_ros_centerpose?

Currently, isaac_ros_foundationpose also comes with two versions with and without tracking. As showcased in CenterPoseTrack webpage, integration of tracking could clearly increase the inference performance.

https://sites.google.com/view/centerposetrack

Dominant language
C++
Stars
501
Forks
57
No merged PRs in 30d

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from NVIDIA-ISAAC-ROS/isaac_ros_pose_estimation

All issues in NVIDIA-ISAAC-ROS/isaac_ros_pose_estimation

Similar issues

More C++ issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.