Skip to content
New issue

Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? # to your account

feat: ✨ yolov8-obb support and OrientedBoxAnnotator added for obb #770

Merged
merged 8 commits into from
Jan 24, 2024

Conversation

onuralpszr
Copy link
Collaborator

@onuralpszr onuralpszr commented Jan 23, 2024

Description

This pull request introduces two significant features:

YOLOv8 Oriented Bounding Box (OBB) Support: This feature extends the capabilities of the YOLOv8 model to detect objects in images and provide oriented bounding boxes as output. This is particularly useful in scenarios where the orientation of the object matters, such as detecting vehicles or buildings from aerial images. The support for OBB allows the model to provide more precise and detailed information about the detected objects.

OrientedBoxAnnotator: This new class provides functionality for annotating images with oriented bounding boxes. This can be used to visually verify the output of the YOLOv8 model with OBB support or to create new training data. The OrientedBoxAnnotator makes it easy to draw oriented bounding boxes on images, which can be a complex task due to the need to handle the orientation of the boxes.

These features enhance the capabilities of the library in handling object detection tasks where object orientation is important. They also provide users with easy-to-use tools for working with oriented bounding boxes, both in terms of model output and data annotation.

List any dependencies that are required for this change.

Type of change

Please delete options that are not relevant.

  • New feature (non-breaking change which adds functionality)
  • This change requires a documentation update

How has this change been tested, please provide a testcase or example of how you tested the change?

Collab link: https://colab.research.google.com/drive/1DzXhkECpLbeWgGwDMsaY4h8pUzsfsFsE?usp=sharing

YOUR_ANSWER

Any specific deployment considerations

For example, documentation changes, usability, usage/costs, secrets, etc.

Docs

  • Docs updated? What were the changes:

Resolve #749
Resolve #757

@onuralpszr onuralpszr added enhancement New feature or request api:annotator Annotators api:detection labels Jan 23, 2024
@onuralpszr onuralpszr added this to the version: 0.18.0 milestone Jan 23, 2024
@onuralpszr onuralpszr self-assigned this Jan 23, 2024
Signed-off-by: Onuralp SEZER <thunderbirdtr@gmail.com>
@SkalskiP
Copy link
Collaborator

@onuralpszr I decided to drop visual examples from docs for now. I need to think about a good place to show it. And I really need to wrap this PR before release. ;) But we will definitely add it in upcomming days.

@SkalskiP SkalskiP merged commit 35d5738 into develop Jan 24, 2024
8 checks passed
@onuralpszr onuralpszr deleted the yolov8-obb branch September 23, 2024 15:09
# for free to join this conversation on GitHub. Already have an account? # to comment
Labels
api:annotator Annotators api:detection enhancement New feature or request
Projects
None yet
Development

Successfully merging this pull request may close these issues.

OrientedBoxAnnotator - allowing to draw OBB Extend Detections.from_ultralytics to support OBB
2 participants