- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi. I am using Realsense D435 and Matlab wrapper to create the point cloud of my target object.
I can successfully detect and tracking the object from the streaming if I convert the depth_frame object into a grayscale image. However, even though I can find the exact location of the object in the image, it is hard for me to create the point cloud out of a grayscale image.
I found out that the MATLAB wrapper has a class realsense.pointcloud, which can calculate the point cloud out of a depth_frame object. I am wondering if it is possible to directly crop out the ROI from the depth_frame, or create a depth_frame object from a cropped grayscale image using the SDK.
If it is not possible, can I crop out a certain part of the point cloud by giving the coordinate?
Thank you for the help.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hey Eliza,
Thank you for the solution. I somehow didn't figure out how should I create the roi_sensor object. However, the problem has been solved. I managed to use get_distance function to find the depth range of the ROI, then the approximate region of the target object's points in the point cloud can be cropped out using select() function.
I am still curious how should I use the roi_sensor. It will be lovely if you can offer me some examples or references.
Thank you again for your kind help and patience.
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hey Eliza,
Thank you for the solution. I somehow didn't figure out how should I create the roi_sensor object. However, the problem has been solved. I managed to use get_distance function to find the depth range of the ROI, then the approximate region of the target object's points in the point cloud can be cropped out using select() function.
I am still curious how should I use the roi_sensor. It will be lovely if you can offer me some examples or references.
Thank you again for your kind help and patience.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Dear Eliza,
I would like to see some examples that contain roi_sensor class in MatLab to set the region of interest directly in the Intel RealSense camera (I have D415 and D435) Are still not available?
Please, let me know. Chiara
![](/skins/images/7B0AB6865064EAE32B30EC9A4E94B48A/responsive_peak/images/icon_anonymous_message.png)
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page