Digital holographic microscopy (DHM), a quantitative phase-imaging technology, has been widely used in various applications. Phase-aberration compensation in off-axis DHM is vital to reconstruct topographical images with high precision, especially for microstructures with a small background or a dense phase distribution. We propose a numerical method based on deep learning combined with DHM. First, a convolutional neural network (CNN) recognizes and segments the sample and the background area of the hologram. Zernike polynomial fitting is then executed on the extracted background area. Finally, the whole process of phase-aberration compensation is automatically performed. To obtain a robust and accurate deep-learning model for hologram segmentation, we collected many holograms corresponding to several samples that had different morphological characteristics. The experimental results confirm that the trained CNN can accurately segment the sample from the background area of the hologram, and that this method is applicable and effective in off-axis DHM.

Based on the hologram inpainting via a two-stage Generative Adversarial Network (GAN), we present a precise phase aberration compensation method in digital holographic microscopy (DHM). In the proposed methodology, the interference fringes of the sample area in the hologram are firstly removed by the background segmentation via edge detection and morphological image processing. The vacancy area is then inpainted with the fringes generated by a deep learning algorithm. The image inpainting finally results in a sample-free reference hologram containing the total aberration of the system. The phase aberrations could be deleted by subtracting the unwrapped phase of the sample-free hologram from our inpainting network results, in no need of any complex spectrum centering procedure, prior knowledge of the system, or manual intervention. With a full and proper training of the two-stage GAN, our approach can robustly realize a distinct phase mapping, which overcomes the drawbacks of multiple iterations, noise interference or limited field of view in the recent methods using self-extension, Zernike polynomials fitting (ZPF) or geometrical transformations. The validity of the proposed procedure is confirmed by measuring the surface of preprocessed silicon wafer with a Michelson interferometer digital holographic inspection platform. The results of our experiment indicate the viability and accuracy of the presented method. Additionally, this work can pave the way for the evaluation of new applications of GAN in DHM.

The fusion of visual and inertial odometry has matured greatly due to the complementarity of the two sensors. However, the use of high-quality sensors and powerful processors in some applications is difficult due to size and cost limitations, and there are also many challenges in terms of robustness of the algorithm and computational efficiency. In this work, we present VIO-Stereo, a stereo visual-inertial odometry (VIO), which jointly combines the measurements of the stereo cameras and an inexpensive inertial measurement unit (IMU). We use nonlinear optimization to integrate visual measurements with IMU readings in VIO tightly. To decrease the cost of computation, we use the FAST feature detector to improve its efficiency and track features by the KLT sparse optical flow algorithm. We also incorporate accelerometer bias into the measurement model and optimize it together with other variables. Additionally, we perform circular matching between the previous and current stereo image pairs in order to remove outliers in the stereo matching and feature tracking steps, thus reducing the mismatch of feature points and improving the robustness and accuracy of the system. Finally, this work contributes to the experimental comparison of monocular visual-inertial odometry and stereo visual-inertial odometry by evaluating our method using the public EuRoC dataset. Experimental results demonstrate that our method exhibits competitive performance with the most advanced techniques.

This paper presents a theoretical model, based on the Rayleigh-Ritz method, to analyze the dynamic response of circular micro-diaphragms in contact with a fluid. The fluid is assumed to be incompressible, inviscid, and irrotational. In the model, a linear combination of polynomials is utilized to construct the mode shapes, and the Rayleigh quotient for fluid-structure coupling system is implemented to obtain the dynamic characteristics of pre-stressed diaphragms. Theoretical calculations are well validated by a finite element model. The relationships of the natural frequencies and quality factors to the mode shape are systematically investigated. The investigation proves that it is necessary to adopt exact mode shapes, instead of approximate mode shapes, to ensure the accuracy in the theoretical evaluation of the vibration of the diaphragm in the fluid. Furthermore, the quality factor associated with acoustic radiation losses is mode dependent, and its dependency on the mode number shows plate, membrane, and plate-membrane transition behaviors as pre-stress varies. These findings can be useful in the applications of diaphragm-based resonators.