Weld Feature Extraction Based on Semantic Segmentation Network

Article Chemistry, Analytical

Online Color Classification System of Solid Wood Flooring Based on Characteristic Features

Zilong Zhuang et al.

Summary: The study focuses on using machine vision and deep learning methods to classify the colors of solid wood flooring, aiming to improve production efficiency and reduce labor costs. By collecting a large amount of solid wood flooring image data and using XGBoost method to filter features, a color classification accuracy of 97.22% was achieved.

SENSORS (2021)

Add to Collection

Article Engineering, Electrical & Electronic

A Robust Weld Seam Tracking Method by Using Intensity-Modulated Structured Light

Wenjun Shao et al.

Summary: To address the issue of light noise interference in the welding process, we proposed a seam tracking method that modulates the intensity of structured light at a high frequency using an acoustic-optic modulator and extracts the modulated frequency from multiple seam images through Fourier transformation. By directly removing noises such as sparks in the frequency domain, the method demonstrates robustness in detecting seams in noisy welding conditions.

IEEE SENSORS JOURNAL (2021)

Add to Collection

Review Computer Science, Information Systems

Attention Mechanisms in CNN-Based Single Image Super-Resolution: A Brief Review and a New Perspective

Hongyu Zhu et al.

Summary: With the advancement of deep learning, single image super-resolution (SR) has seen notable improvements through CNN-based methods. However, the increased depth of CNNs presents difficulties in training, hindering greater success for SR networks. Various mechanisms have been introduced recently to help these networks converge faster and perform better, with attention mechanisms being a key focus from different perspectives.

ELECTRONICS (2021)

Add to Collection

Article Automation & Control Systems

Additive seam tracking technology based on laser vision

Zhuang Zhao et al.

Summary: This paper studies the additive weld seam tracking technology based on laser vision and designs a welding seam tracking system, demonstrating high robustness and strong adaptability to meet practical welding requirements.

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY (2021)

Add to Collection

Article Chemistry, Analytical