Industrial defect segmentation is important to ensure product quality and production safety. The main challenges in industrial applications are insufficient defect samples, large intraclass variation, and the interference of background information. However, most current texture defect segmentation methods rely on large-scale datasets and can only deal with one specific type of texture defect, which reduces the application efficiency and application scope of defect segmentation algorithms. To this end, we propose an optimal bilateral feature transport network (OBFTNet) for few-shot texture defect segmentation, which can accurately segment texture defects in multiple unseen materials (domains), such as steel, wood, and leather. OBFTNet can perform bilateral prediction for background and defect regions of unseen material by dynamically predicting task-specific semantic correspondences conditioned on a small guidance set. Specifically, we introduce background images (defect-free images) as supplementary learning information for reverse prediction and model the semantic correspondence between the guidance (support and background images) and the query images in few-shot segmentation as an optimal bilateral feature transport problem and generate a set of optimal bilateral correlation tensors. Using 4-D and 2-D convolutions, the model gradually reduces optimal bilateral correlation tensors to precise segmentation masks. Experimental results show that our proposed method outperforms several state-of-the-art techniques with very few labeled samples and the method generalizes well to industrial defects on unseen materials.

Bayer filter color cameras are more and more widely used in the field of aerospace remote sensing, but the Bayer filter causes great degradation in image quality; therefore, obtaining a means of achieving the high-precision measurement of the modulation transfer function (MTF) of Bayer filter color cameras is an urgent problem. In order to solve this problem, this paper develops a slanted-edge method via three steps: the detection of the slanted edge, the acquisition and processing of the edge spread function (ESF), and the acquisition and processing of the line spread function (LSF). A combination of the Canny operator and Hough transform is proposed for the detection of the slanted edge, which improves the fitting accuracy and anti-interference ability of the algorithm. Further, the Canny operator is improved by constructing an adaptive filter function and introducing the Otsu method, which can more effectively smooth the image and remove its false edges. A method of processing ESF data by combining cubic spline interpolation and Savitzky–Golay (SG) filtering is proposed, which reduces the effects of noise and the non-uniform sampling of ESF on MTF. A method of LSF processing using Gaussian function fitting is proposed to further reduce the effect of noise on MTF. The improved algorithm is verified by the MTF measurement test applied to a specific type of Bayer filter color space camera. The simulation and test results show that the improved slanted-edge method discussed in this paper has greater precision and a better anti-interference ability, and it can effectively solve the difficult problem associated with MTF detection in Bayer filter color space cameras.

Structural vibration has always been a major concern in the engineering field. A dynamic vibration absorber in the form of contacts with adjustable stiffness (CDVA) offers effective vibration suppression and can improve conventional dynamic vibration absorbers with high sensitivity to frequency deviation and difficulty in adjusting the frequency. In this research, first, based on the theoretical model of the contact between a rubber ball and an inner cone, the feasibility of changing the axial contact state to change the structure’s natural frequency was verified using an ANSYS simulation. A theoretical model of the static contact stiffness between the ball and the inner cone was constructed using Hertzian contact theory and Hooke’s law, and a theoretical model of the cubic nonlinear elastic restoring force was used to characterize the stiffness properties of the rubber ball during compressive rebound. The steady-state frequency response equations of the main vibration structure were derived using the averaging method in conjunction with the two-degree-of-freedom dynamics model, and the stability of the solutions to the frequency response equations was obtained in conjunction with the stability determination criterion. Then, the impact of the CDVA’s design parameters on the nonlinear dynamic response of the primary vibration structure was simulated and analyzed. The resulting findings can serve as guidance for designing dynamic vibration absorber parameters. Based on the principles of ball-inner cone contact, a dynamic vibration absorber structure was proposed. A design test was conducted to verify the correctness of the contact stiffness model, and an experimental study was carried out to investigate the law of change in the dynamic stiffness and damping of the principle structure of CDVA under dynamic excitation conditions. Finally, the vibration test platform of the solidly supported beam structure was constructed, and vibration suppression tests of the CDVA in different compression states were conducted to investigate the tunability and feasibility of CDVA vibration suppression. The results showed that the dynamic vibration absorber had good vibration absorption characteristics and could be used for single-mode vibration suppression of multimodal main structures.