Shiyang Zhou

To solve the problem of high mismatching rate in traditional three-dimensional (3D) stereo matching algorithms in uneven light and weak textures, an enhanced cross-based cost aggregation semi-global block matching (ECCA-SGBM) algorithm is proposed for the 3D reconstruction of aluminum alloy casting with weak textures and reflective surfaces. First, an experimental binocular-vision platform is constructed. Subsequently, a fusion cost calculation method based on Scharr operator and an enhanced adaptive cross-based cost aggregation method are introduced to compute disparity and depth map. Finally, the depth map is converted into point cloud data, which is used to reconstruct the 3D structure of aluminum alloy casting. Experimental results demonstrate that the proposed ECCA-SGBM matching algorithm reduces the mismatching rate in the areas with uneven light effectively. The average error in the aperture diameter of the reconstructed 3D point cloud of the aluminum alloy casting is less than 5%, which can serve as a useful reference for the rapid size measurement of other machine parts.

Accurate and efficient white-spot defects detection for the surface of galvanized strip steel is one of the most important guarantees for the quality of steel production. It’s a fundamental but “hard” small target detection problem due to its small pixel occupation in low-contrast images. By fully exploiting the low-rank and sparse prior information of surface defect image, a Schatten-p norm-based low-rank tensor decomposition (SLRTD) method is proposed to decomposes the defect image into low-rank background, sparse defect, and random noise. Firstly, the original defect images are transformed into a new patch-based tensor mode through data reconstruction for mining valuable information of defect image. Then, considering the over-shrinkage problem in low-rank component estimation caused by vanilla nuclear norm and weighted nuclear norm, a nonlinear reweighting strategy based on Schatten p-norm is incorporated to improve the decomposition performance. Finally, a solution framework is proposed via a well-designed alternating direction method of multipliers to obtain the white-spot defect target image by a simple segmenting algorithm. The white-spot defect dataset from real-world galvanized strip steel production line is constructed, and the experimental results demonstrate that the proposed SLRTD method outperforms existing state-of-the-art methods qualitatively and quantitatively.

During the production process of steel plate, surface defect detection is crucial for high-quality products. For the existing defect detection method based on machine vision, there are various types of problems, such as large model calculations, low detection accuracy and difficulties of recognizing small defect targets. To reduce and solve these issues, the paper proposes a new defect detection model, simplified kernel and squeeze on a you only look once network (SKS-YOLO), which can achieve rapid and effective defect detection on steel plate. Firstly, it adopts EfficientNetv2 as the backbone, significantly reducing model calculations and accelerating training speed while maintaining accuracy. Subsequently, the atrous spatial pyramid pooling (ASPP) module is utilized to obtain a larger receptive field, extracting more feature information from surface defects. The integration of the squeeze excitation network (SE-Net) attention mechanism enhances capabilities of feature extraction furtherly. Then, the K-means algorithm is applied to cluster and obtain more suitable anchor frames for defect targets. It not only increases the number of positive samples, but also expedites model convergence. Finally, the loss function of simplified intersection over union (SIoU) is used to enhance the ability of model to locate and detect surface defect targets. The experimental results show that the mean average precision (mAP) is 89.40% at a detection speed of 55 frames per second (FPS), which is better than the state-of-the-art (SOTA) detection models.

Weighted least-squares (WLS) phase unwrapping is widely used in optical engineering. However, this technique still has issues in coping with discontinuity as well as noise. In this paper, a new WLS phase unwrapping algorithm based on the least-squares orientation estimator (LSOE) is proposed to improve phase unwrapping robustness. Specifically, the proposed LSOE employs a quadratic error norm to constrain the distance between gradients and orientation vectors. The estimated orientation is then used to indicate the wrapped phase quality, which is in terms of a weight mask. The weight mask is calculated by post-processing, including a bilateral filter, STDS, and numerical relabeling. Simulation results show that the proposed method can work in a scenario in which the noise variance is 1.5. Comparisons with the four WLS phase unwrapping methods indicate that the proposed method provides the best accuracy in terms of segmentation mean error under the noisy patterns.