FusionFormer: An Off-Road Sence Semantic Segmentation Network Based on Data Fusion and Hierarchical Transformer

An Zhi Duan, Yue Ma*, Yun Feng Wang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The off-road environment poses significant challenges and obstacles to the further development of environmental perception due to the irregularity of its objects and the randomness of their distribution. In order to pursue higher precision of semantic segmentation in complex and unordered environments with irregular objects and uneven quantities, the FusionFormer is raised, which is based on image data fusion, hierarchical Transformer and Focal Loss. The network has strong learning capabilities by fusing depth and image information, using Transformer hierarchical to obtain multi-scale features, adopting Focal Loss to address class imbalance issues. The experiment corroborate that FusionFormer is Extremely capable to improve the precision and multi-class semantic segmentation capabilities in off-road scene semantic segmentation tasks.

Original languageEnglish
Title of host publicationProceedings of 2024 Chinese Intelligent Systems Conference
EditorsYingmin Jia, Weicun Zhang, Yongling Fu, Huihua Yang
PublisherSpringer Science and Business Media Deutschland GmbH
Pages75-83
Number of pages9
ISBN (Print)9789819786572
DOIs
Publication statusPublished - 2024
Event20th Chinese Intelligent Systems Conference, CISC 2024 - Guilin, China
Duration: 26 Oct 202427 Oct 2024

Publication series

NameLecture Notes in Electrical Engineering
Volume1285 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference20th Chinese Intelligent Systems Conference, CISC 2024
Country/TerritoryChina
CityGuilin
Period26/10/2427/10/24

Keywords

  • Data fusion
  • Focal loss
  • Off-road scenes
  • Semantic segmentation
  • Transformer

Cite this