logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Model-aware ellipse detection via parametric correlation learning

delete2025-07-08
delete0
PRE
AI
Q
Qi Jia
Z
Z. Liu
Y
Yu Liu *
王羿 cover
王羿 (Yi Wang)
X
Xinwei Xue
W
Weimin Wang
DOI：10.1016/j.sigpro.2025.110142delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• We concentrate on the geometric characteristics of ellipse detection via our specially designed LoG-like Edge Detection Module (LEDM) and Edge Guided Module (EGM), leveraging multi-scale features around ellipse boundaries rather than relying on internal textures only. • We design an auxiliary head for the estimation of four ellipse vertices, invoking additional feature attention on these pivotal points. It effectively addresses the issue of missed detections caused by incomplete or occluded boundaries. • We establish the relations between the error and geometric characteristics of the ellipse by a specially designed model-aware loss function, rendering an integrated measurement for each parameters.

Journal

Signal Processing cover
Signal Processing
IF:
3.6
Papers:
9.9K
Citations:
1.7W

Organization

No organization information available