Three-dimensional measurement of precise shaft parts based on line structured light and deep learning

Yang, Guowei; Wang, Yizhong

doi:10.1016/j.measurement.2022.110837

Cited by 43 publications

(12 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…G.W. Yang et al [12] combined structured light and deep learning algorithms for measuring shaft components, resulting in sub-0.017 mm precision. However, this method's high costs and intensive initial workload limit its applicability for rapid production measurements.…”

Section: Related Workmentioning

confidence: 99%

Vision-based measurement method for geometric dimensions of PVC pipe end faces

Yu,

Zhao,

Hou

et al. 2024

J. Inst.

View full text Add to dashboard Cite

This study introduces a vision-based expedited methodology for assessing various geometric circular dimensions on the termini of PVC conduits. The process commences with delineating pipe profiles using the EDPF algorithm for edge detection. Successive steps employ a radius-constrained weighted circular approximation algorithm to form provisional circular profiles from closed-edge segments. These profiles are refined using a rapid circle arc fitting algorithm for multiple open-edge sections. Noise circles are sifted out with the Number of False Alarms algorithm, and upon calibration with actual dimensions, these profiles are quantified into physical sizes of the conduit's terminal geometries. Empirical evidence from the methodology demonstrates an ability to measure the circular dimensions with a mean accuracy rate surpassing 99.2%.

show abstract

Section: Related Workmentioning

confidence: 99%

Vision-based measurement method for geometric dimensions of PVC pipe end faces

Yu,

Zhao,

Hou

et al. 2024

J. Inst.

View full text Add to dashboard Cite

show abstract

“…The pose measurement experiments were performed without the polarizing device being mounted. We used the homography-based pose measurement method [13,23] to solve the pose of the target non-iteratively with the intrinsic parameters calibrated by Approach 1, Approach 2, Approach 3, and Approach 4. Then we got the rotating angle between the current and initial locations (0 • ).…”

Section: Assessing the Calibrated Intrinsic Parameters With Pose Meas...mentioning

confidence: 99%

“…We used the homography-based pose measurement method [13,23] to solve the pose of the target non-iteratively with the intrinsic parameters calibrated by Approach 1, Approach 2, Approach 3, and Approach 4. Figure 24 displays the mean re-projection errors.…”

Section: Experiments With Targets Placed Randomlymentioning

confidence: 99%

Camera calibration approach using polarized light based on high-frequency component variance weighted entropy for pose measurement

Zhang

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

The camera’s intrinsic parameters calibration directly affects monocular pose measurement accuracy. To improve the calibration accuracy of the camera’s intrinsic parameters, the polarizing device is used to eliminate the high-brightness areas in the images collected for camera calibration. However, an unsuitable polarizing angle will reduce the image’s contrast. This causes the texture information of the image to be lost or makes the extracted feature change in the direction of grayscale value decline, ultimately affecting the feature extraction. Aiming at this issue, this paper proposed a camera calibration approach using polarized light based on high-frequency component variance weighted entropy. We determined the suitable polarizing angle according to the 2D homography matrix describing the mapping between the target plane and normalized imaging plane for each calibration location. Under the suitable polarizing angle, we determined the optimal exposure time according to the high-frequency component variance weighted entropy. The images collected under suitable polarizing angles and the optimal exposure time were used to finish the camera calibration. The suitable polarizing angles and optimal exposure time can ensure the image’s contrast and texture information. The experimental findings demonstrate that our approach can increase the camera calibration accuracy and thus pose measurement accuracy. In the -45° to +45° range, the average pose measurement error is less than 0.05° and lowered by 0.08° (62%) compared to that performed using the intrinsic parameters calibrated with the images collected under no polarizing device. In the 0 to 20 mm range, the average pose measurement error is less than 0.028 mm and lowered by 0.05 mm (64%) compared to that performed using the intrinsic parameters calibrated with the images collected under no polarizing device.

show abstract

“…For the first time, VD was applied to laser stripes, which can not only extract the centerline of line laser stripes with subpixel accuracy but also speckle noise has strong robustness, and the calculation amount of the proposed VD method is very time-consuming. Yang and Wang 30 proposed an algorithm for extracting streak centers based on deep learning. This algorithm uses a convolutional neural network to extract the overall distribution and bending characteristics of laser streaks.…”

Section: Introductionmentioning

confidence: 99%

High-efficiency flatness detection method for medium-thick steel plates based on multiline parallel laser vision

Xia,

Wang,

Wang

et al. 2023

Opt. Eng.

View full text Add to dashboard Cite

.To resolve the disparity between accuracy and speed in the current surface flatness detection of medium and thick steel plates, which predominantly relies on the single-line laser vision method, we propose a high-efficiency flatness detection method for medium-thick steel plates based on multiline parallel laser vision. On the basis of building a flatness detection system, we present the adaptive cropping algorithm and improved variable threshold Otsu thresholding segmentation algorithm (IVT-Otsu) for image preprocessing. Then, the centerline of subpixel-level laser stripes is accurately extracted using a weighted quadratic grayscale center of gravity method. Meanwhile, a pruning algorithm-based multiline laser stripe center extraction method is proposed to address the phenomenon of spotting and branching in the center of multiline parallel laser, to efficiently obtain the surface depth information and flatness index of medium-thick steel plate. Results of the experiment indicate that the proposed method better fulfills the accuracy and efficiency requirements for online inspection when extracting the laser centers and calculating the flatness.

show abstract

Three-dimensional measurement of precise shaft parts based on line structured light and deep learning

Cited by 43 publications

References 20 publications

Vision-based measurement method for geometric dimensions of PVC pipe end faces

Vision-based measurement method for geometric dimensions of PVC pipe end faces

Camera calibration approach using polarized light based on high-frequency component variance weighted entropy for pose measurement

High-efficiency flatness detection method for medium-thick steel plates based on multiline parallel laser vision

Contact Info

Product

Resources

About