Skip to content
New issue

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

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

Already on GitHub? Sign in to your account

How to convert 2D coordinates to 3D coordinates ? #2311

Closed
BnHassan1998 opened this issue Apr 5, 2022 · 6 comments
Closed

How to convert 2D coordinates to 3D coordinates ? #2311

BnHassan1998 opened this issue Apr 5, 2022 · 6 comments
Labels

Comments

@BnHassan1998
Copy link

I am using yolov3 with darknet to train and test my project. how I can convert 2D coordinates to 3D coordinates to know the Z
(depth ) . because I have to do localization for the objects

@MartyG-RealSense
Copy link
Collaborator

MartyG-RealSense commented Apr 5, 2022

Hi @BnHassan1998 As you are using darknet, the darknet_ros_3d package that can calculate a 3D bounding box with a 3D position for each detected object may be an appropriate solution.

https://github.com/IntelligentRoboticsLabs/gb_visual_detection_3d

IntelligentRoboticsLabs/gb_visual_detection_3d#15 discusses using a RealSense D435 camera with darknet_ros_3d, with the comment IntelligentRoboticsLabs/gb_visual_detection_3d#15 (comment) in that discussion being particularly useful.

@BnHassan1998
Copy link
Author

I have changed to Yolo v4. but is it ok if I use the normal images for my dataset, I am using only a software project so I don't have images taken by realsense camera so is it possible to do the conversion? to get the Z (depth) to do the localization

@BnHassan1998
Copy link
Author

Hi @BnHassan1998 As you are using darknet, the darknet_ros_3d package that can calculate a 3D bounding box with a 3D position for each detected object may be an appropriate solution.

https://github.com/IntelligentRoboticsLabs/gb_visual_detection_3d

IntelligentRoboticsLabs/gb_visual_detection_3d#15 discusses using a RealSense D435 camera with darknet_ros_3d, with the comment IntelligentRoboticsLabs/gb_visual_detection_3d#15 (comment) in that discussion being particularly useful.

conversion

@MartyG-RealSense
Copy link
Collaborator

MartyG-RealSense commented Apr 5, 2022

It sounds as though the task that you are trying to achieve with yolov4 and darknet (and ordinary RGB image files?) is similar to the one that somebody was asking in the link below about how to do (but had not yet achieved).

https://stackoverflow.com/questions/67640416/how-to-calculate-length-breadth-2d-dimensions-of-an-objet-using-darknet-and-r

Does the above case accurately describe your own project goals, please?

@MartyG-RealSense
Copy link
Collaborator

Hi @BnHassan1998 Do you require further assistance with this case, please? Thanks!

@MartyG-RealSense
Copy link
Collaborator

Case closed due to no further comments received.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

2 participants