Year: 2022
Type: article
Abstract: Saturated highlights on metal surfaces reduce the detection accuracy of fuel nozzles. In this paper, we propose an image inpainting method with a saturated highlight based on the statistics of similar patches used in prior segmentation of the subregion. The sequence image acquisition is based on the shape from focus in the five-axis platform. By our method, the focus measure (FM) operator and the window size are evaluated using the sharpness evaluation curve and calculating time. We observe that the detection accuracy is improved when the highlight area is filled by the highlight-free area within the same segmentation region. There are fewer deviation points in the three-dimensional (3D) point cloud that are extracted from the sequence images. The inlet circle and the outlet circle of the fuel nozzle are both detected by the two-dimensional (2D) Hough Transform (HT) method. Our experiments show that the method yields better results in 3D detection of the key parameters of fuel nozzles with the saturated highlight characteristics.
Source: Sensors
DOI: 10.3390/s22155661
Authors: Yeni Li, Liang Hou, Yun Chen
Institutions: Xiamen University, Xiamen University of Technology
Language: English
Subfield: Media Technology
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,513
Awards: G2721936358, G8274140041
OpenAlex ID: W4288717974