NVIDIA-ISAAC-ROS / NVIDIA-ISAAC-ROS/isaac_ros_object_detection

Isuue with the sizes of bounding boxes

Open
#39 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
201
Forks
51
PR merge metrics
No merged PRs in 30d

Description

Hey! so when I publish images by the size 640x640 everything seems to be OK.
But when I publish an image with dimensions 1280x720 the bounding boxes get "smooshed" they don't fit not the 640x640 image nor do they fit 1280x720 image.
Of course I'm using the image dimension parameters in the launch file, but is there a hardcover dimensions somewhere? Except for the fact yolo works with 640x640..

In yolov5 issac ros I just used to push the 1280x720 image and it would get resized in the input of the yolonn

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.

Research direction

Start with the launch-file image dimension parameters and reproduce the reported 640x640 and 1280x720 cases. Trace the image resizing and bounding-box coordinate handling to determine where the boxes become misaligned; done means boxes fit the published image dimensions in both cases.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.