WeldLight: A Lightweight Weld Classification and Feature Point Extraction Model for Weld Seam Tracking

To address the issues of intense image noise interference and computational intensity faced by traditional vision-based weld tracking systems, we propose WeldLight, a lightweight and noise-resistant convolutional neural network for precise classification and positioning of welding seam feature point...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Ang Gao, Anning Li, Fukang Su, Xinqi Yang, Wenping Liu, Fuxin Du, Chao Chen
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2025-09-01
coleção:	Sensors
Assuntos:	feature point extraction laser vision sensor lightweight network seam tracking welding seam classification
Acesso em linha:	https://www.mdpi.com/1424-8220/25/18/5761
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!