Segmentation network for unstructured environments

HIGHLIGHTS

• who: Edge-Guided LiDAR Semantic and colleagues from the School of Instrument Science and Engineering, Southeast University, Nanjing, China have published the article: Segmentation Network for Unstructured Environments, in the Journal: (JOURNAL)
• what: To address the above issues, the authors propose a novel real-time edge-guided semantic segmentation network to simultaneously improve the accuracy and adaptation of semantic segmentation in unstructured environments, especially for drivable areas and static obstacles with large areas in it. The authors design an edge segmentation module which contains three edge attention blocks. The authors design an edge guided fusion . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.