期刊
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
卷 17, 期 3, 页码 1882-1891出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2020.2991458
关键词
Exposure selection; image enhancement; industrial metrology; reflective surface measurement; structured light (SL); three-dimensional (3-D) point cloud
类别
资金
- Natural Sciences and Engineering Research Council of Canada
- Canada Research Chairs program
- Ontario Research Fund-Research Excellence program
This article introduces a new SL-based method for measuring parts with highly reflective surfaces in industrial metrology, which significantly reduces measurement time. A new quantitative metric is defined for optimal camera exposure selection, and a SP-CAN network is proposed for image enhancement. Experimental results show that the new method has lower time cost and high measurement accuracy.
Three-dimensional structured light (SL) measurement of highly reflective surface is a challenge faced in industrial metrology. The high dynamic range (HDR) technique provides a solution by fusing images under multiple exposures; however, the process is highly time-consuming. This article reports a new SL-based method to measure parts with highly reflective surfaces from only a single exposure. A new quantitative metric is defined to optimally select camera exposure for capturing input single-exposure images. Different from existing image gradient or entropy-based metrics, the new metric incorporates both intensity modulation and overexposure. A skip pyramid context aggregation network (SP-CAN) is proposed to enhance the single exposure-captured images. Compared with existing image enhancement methods, SP-CAN effectively preserves detailed encoded phase information near edges and corners during enhancement. Experiments with various industrial parts demonstrated that the average time cost of the proposed method was 0.6 s, which was only one tenth of the HDR method (ten exposures), and the two methods achieved similar coverage rates (97.6% versus 98.0%) and measurement accuracy (0.040 mm versus 0.038 mm).
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据