Skip to content

This is an unofficial Python demo of the Self-Supervised Label Generator (SSLG), presented in "Self-Supervised Drivable Area and Road Anomaly Segmentation using RGB-D Data for Robotic Wheelchairs. Our SSLG can be used effectively for self-supervised drivable area and road anomaly segmentation based on RGB-D data".

License

Notifications You must be signed in to change notification settings

ntkhoa95/Self-Supervised-Label-Generator

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Self-Supervised-Label-Generator

This is an unofficial Python demo of the Self-Supervised Label Generator (SSLG), presented in "Self-Supervised Drivable Area and Road Anomaly Segmentation using RGB-D Data for Robotic Wheelchairs". The SSLG can be used effectively for self-supervised drivable area and road anomaly segmentation based on RGB-D data.

The overview of SSLG method, which consists of (a) Input of RGB-D images (b) Processing pipeline of RGB-Dimages (c) Output of self-supervised labels. (b) is composed of RGB Processing Pipeline shown in the orange box, Depth Processing Pipeline shown in the green box and (VII) Final Segmentation Label Generator shown in the blue lines. The RGB Processing Pipeline consists of (I) Original RGB Anomaly Map Generator and (II) Generation of final RGB anomaly maps. The Depth Processing Pipeline consists of (III) Computation of original v-disparity maps, (IV) Filtering of original v-disparity maps, (V) Extraction of the drivable area and original depth anomaly maps as well as (VI) Generation of final depth anomaly maps. The figure is best viewed in color.

Self-supervised Label Generator

Thank Dr. Hengli Wang and his research team for a meaningful publication.

About

This is an unofficial Python demo of the Self-Supervised Label Generator (SSLG), presented in "Self-Supervised Drivable Area and Road Anomaly Segmentation using RGB-D Data for Robotic Wheelchairs. Our SSLG can be used effectively for self-supervised drivable area and road anomaly segmentation based on RGB-D data".

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages