Lane-Level Three-Dimensional Semantic Mapping Based on Stereo Vision

Ruirong Wang*, Chunlei Song, Yuwei Zhang, Jianhua Xu

*Corresponding author for this work

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

Abstract

Autonomous vehicles need to clarify their position and recognize objects in the urban scene, making it increasingly rely on maps to provide them with prior semantics for advanced tasks such as positioning and navigation or planning control. Semantic segmentation and geometric reconstruction techniques required for mapping have gradually developed. They have been combined to a certain extent for applications such as generating semantic maps. Still, they are rarely refined to the lane level, even if the lane can be used as a necessary constraint for vehicles to maneuver on the road. Important clues. This paper proposes a three-dimensional lane-level semantic mapping system that utilizes stereo vision and use the scrolling grid representation to save computing time and memory. We use the deep neural network to obtain the stereo disparities and lane-level semantics and then combined pose and depth to transmit the semantics into the three-dimensional space. Experiments on the KITTI data sequence show that our system can continuously identify and reconstruct objects on the road, even if their strong structure prior or few appearance clues.

Original languageEnglish
Title of host publicationProceedings of the 33rd Chinese Control and Decision Conference, CCDC 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1176-1180
Number of pages5
ISBN (Electronic)9781665440899
DOIs
Publication statusPublished - 2021
Event33rd Chinese Control and Decision Conference, CCDC 2021 - Kunming, China
Duration: 22 May 202124 May 2021

Publication series

NameProceedings of the 33rd Chinese Control and Decision Conference, CCDC 2021

Conference

Conference33rd Chinese Control and Decision Conference, CCDC 2021
Country/TerritoryChina
CityKunming
Period22/05/2124/05/21

Keywords

  • Deep Neural Network
  • Lane-Level
  • Semantic Mapping
  • Stereo Vision

Fingerprint

Dive into the research topics of 'Lane-Level Three-Dimensional Semantic Mapping Based on Stereo Vision'. Together they form a unique fingerprint.

Cite this