人工智能
激光器
干扰(通信)
计算机视觉
多边形(计算机图形学)
分割
计算机科学
光学
图像分割
特征提取
特征(语言学)
材料科学
物理
计算机网络
电信
频道(广播)
语言学
哲学
帧(网络)
作者
Chuan Ye,Yunhan Li,Chao Wang,Yuanyao Hu
出处
期刊:IEEE Sensors Journal
[Institute of Electrical and Electronics Engineers]
日期:2023-07-01
卷期号:23 (13): 15188-15198
标识
DOI:10.1109/jsen.2023.3279855
摘要
A deep learning line laser 3-D measurement method based on feature fusion and attention mechanism is proposed to address the impact of reflective workpieces on the extraction of laser stripe centers. First, a UNet segmentation model based on feature fusion and attention mechanism is established. The deep learning model can effectively solve the interference caused by reflection and can segment the overall distribution and bending characteristics of laser stripes. Second, the Steger algorithm is used to roughly extract the center of the laser stripe, and the contour polygon segmentation method is used to adaptively obtain the segmentation points of the laser stripe. Finally, polynomial fitting is performed based on segmented points to obtain a smoother laser stripe centerline. The experimental results show that the proposed method can effectively overcome the interference caused by reflective workpieces and generate a smoother 3-D model, and the measurement repeatability error is less than 0.37 mm, and the relative error is less than 0.03 mm.
科研通智能强力驱动
Strongly Powered by AbleSci AI