The video shows our current progress for the subsystem. As you can see we first define a Region on interest in first video for the raw point cloud. After preprocessing and removing noisy data, we use techniques such as RANSAC to segment out the ground planar surface and then cluster the different segmented objects as seen in the 3rd video. Major work was done to make this whole pipeline real- time and integrate it with ROS.
-
Notifications
You must be signed in to change notification settings - Fork 1
License
laavanyebahl/3D-Object-Detection-with-Point-Clouds
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
No description, website, or topics provided.
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published