Single- Frame Background Reconstruction Based on Image Semantic Propagation

Yang Zhang, Peize Li, Yuan Xu, Qunxiong Zhu, Yanlin He, Mingqing Zhang

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

Abstract

Image background recognition and reconstruction is an important research content in the field of computer vision. Instead of paying attention to all the targets in the image, this paper only focuses on the static background in the scene. Therefore, an adaptive semantic propagation method is proposed to reconstruct the complete background of static images. It executes single-connected region division and edge detection on a single frame. Experimental results demonstrate the robustness and adaptability of the method, achieving convincing performance under both simple and complex road conditions.

Original languageEnglish
Title of host publication2024 18th International Conference on Control, Automation, Robotics and Vision, ICARCV 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages763-768
Number of pages6
ISBN (Electronic)9798331518493
DOIs
Publication statusPublished - 2024
Externally publishedYes
Event18th International Conference on Control, Automation, Robotics and Vision, ICARCV 2024 - Dubai, United Arab Emirates
Duration: 12 Dec 202415 Dec 2024

Publication series

Name2024 18th International Conference on Control, Automation, Robotics and Vision, ICARCV 2024

Conference

Conference18th International Conference on Control, Automation, Robotics and Vision, ICARCV 2024
Country/TerritoryUnited Arab Emirates
CityDubai
Period12/12/2415/12/24

Keywords

  • Background reconstruction
  • Occluded region
  • Region propagation
  • Semantic information

Fingerprint

Dive into the research topics of 'Single- Frame Background Reconstruction Based on Image Semantic Propagation'. Together they form a unique fingerprint.

Cite this