Skip to content

ardimou/target_segmentation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Target segmentation

This code keeps track of a target's segmentation mask, manipulating data of pushing actions. Initially mask-RCNN is implemented to segment the scene. The produced masks and the pushing actions are used as input for U-Net, that will output the final target's mask.

Data Format:

S_{t}, S_{t+1}: segmentation masks of the t, t+1 step. (200x200 images) (same format as the pybullet segmentation)

p12: pushing action scaled to [0, 199]

target_t, target_t+1: target masks, at t, t+1 step

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published