Related Experiment Video
Updated: Jan 7, 2026
05:57
Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
Published on: April 8, 2019
7.2K
Weld Seam ROI Detection and Segmentation Method Based on Active-Passive Vision Fusion.
Ming Hu1, Xiangtao Hu1, Jiuzhou Zhao2
1School of Electrical Engineering and Automation, Anhui University, Hefei 230601, China.
Sensors (Basel, Switzerland)
|December 31, 2025
Summary
This study introduces a novel method for accurately detecting and segmenting weld seams using fused vision techniques. This approach enhances robotic grinding precision by improving region of interest identification.
Area of Science:
- Robotics and Automation
- Computer Vision
- Manufacturing Technology
Background:
- Accurate weld seam detection and segmentation are critical for intelligent robotic grinding.
- Existing methods face challenges in achieving high precision and speed.
Purpose of the Study:
- To propose a robust method for weld seam region of interest (ROI) detection and segmentation.
- To enhance the accuracy and efficiency of weld seam identification for robotic applications.
Main Methods:
- A two-stage approach combining image instance segmentation (enhanced YOLOv8n-seg with attention) and 3D point cloud segmentation.
- Spatial alignment of 3D point clouds to 2D planes, followed by coarse screening using bounding boxes.
- Precise weld seam ROI point cloud extraction via grayscale matrix construction and point-wise discrimination.
Main Results:
- The enhanced segmentation network improved localization accuracy and mask quality for weld seam regions.
- The point cloud segmentation effectively filtered redundant data and precisely extracted the weld seam ROI.
- The fused vision method demonstrated high-quality segmentation of the weld seam region.
Conclusions:
- The proposed method offers a reliable foundation for robotic automated grinding by providing precise weld seam segmentation.
- Fusion of active and passive vision techniques effectively addresses the challenges in weld seam ROI detection.
- This work contributes to advancing intelligent manufacturing processes through improved robotic capabilities.
