Perspectives on oblique angle deposition of thin films: From fundamentals to devices

Abstract With the advances in scientific foundations and technological implementations, optical metrology has become versatile problem-solving backbones in manufacturing, fundamental research, and engineering applications, such as quality control, nondestructive testing, experimental mechanics, and biomedicine. In recent years, deep learning, a subfield of machine learning, is emerging as a powerful tool to address problems by learning from data, largely driven by the availability of massive datasets, enhanced computational power, fast data storage, and novel training algorithms for the deep neural network. It is currently promoting increased interests and gaining extensive attention for its utilization in the field of optical metrology. Unlike the traditional “physics-based” approach, deep-learning-enabled optical metrology is a kind of “data-driven” approach, which has already provided numerous alternative solutions to many challenging problems in this field with better performances. In this review, we present an overview of the current status and the latest progress of deep-learning technologies in the field of optical metrology. We first briefly introduce both traditional image-processing algorithms in optical metrology and the basic concepts of deep learning, followed by a comprehensive review of its applications in various optical metrology tasks, such as fringe denoising, phase retrieval, phase unwrapping, subset correlation, and error compensation. The open challenges faced by the current deep-learning approach in optical metrology are then discussed. Finally, the directions for future research are outlined. 

/pdf/deep-learning-in-optical-metrology-a-review-2ggtgtrp.pdf

Deep learning in optical metrology: a review

Global terrorist threats and illegal migration have intensified concerns for the security of citizens, and every effort is made to exploit all available technological advances to prevent adverse events and protect people and their property. Due to the ability to use at night and in weather conditions where RGB cameras do not perform well, thermal cameras have become an important component of sophisticated video surveillance systems. In this paper, we investigate the task of automatic person detection in thermal images using convolutional neural network models originally intended for detection in RGB images. We compare the performance of the standard state-of-the-art object detectors such as Faster R-CNN, SSD, Cascade R-CNN, and YOLOv3, that were retrained on a dataset of thermal images extracted from videos that simulate illegal movements around the border and in protected areas. Videos are recorded at night in clear weather, rain, and in the fog, at different ranges, and with different movement types. YOLOv3 was significantly faster than other detectors while achieving performance comparable with the best, so it was used in further experiments. We experimented with different training dataset settings in order to determine the minimum number of images needed to achieve good detection results on test datasets. We achieved excellent detection results with respect to average accuracy for all test scenarios although a modest set of thermal images was used for training. We test our trained model on different well known and widely used thermal imaging datasets as well. In addition, we present the results of the recognition of humans and animals in thermal images, which is particularly important in the case of sneaking around objects and illegal border crossings. Also, we present our original thermal dataset used for experimentation that contains surveillance videos recorded at different weather and shooting conditions.

/pdf/thermal-object-detection-in-difficult-weather-conditions-2xebrqlnbj.pdf

Thermal Object Detection in Difficult Weather Conditions Using YOLO

https://www.tandfonline.com/doi/pdf/10.1088/1468-6996/12/6/064709

Material design and structural color inspired by biomimetic approach

/pdf/deep-learning-in-optical-metrology-a-review-1etdbnzu.pdf

Division of focal plane (DoFP) polarimeters operate by integrating micro-polarizer elements with a focal plane. These polarization imaging sensors reduce spatial resolution output and each pixel has a varying instantaneous field of view (IFoV). These drawbacks can be mitigated by applying proper interpolation methods. In this paper, we present a new interpolation method for DoFP polarimeters by using intensity correlation. We employ the correlation of intensity measurements in different orientations to detect edges and then implement interpolation along edges. The performance of the proposed method is compared with several previous methods by using root mean square error (RMSE) comparison and visual comparison. Experimental results showed that our proposed method can achieve better visual effects and a lower RMSE than other methods.

Image interpolation for division of focal plane polarimeters with intensity correlation

The interferometry technique is commonly used to obtain the phase information of an object in optical metrology. The obtained wrapped phase is subject to a 2π ambiguity. To remove the ambiguity and obtain the correct phase, phase unwrapping is essential. Conventional phase unwrapping approaches are time-consuming and noise sensitive. To address those issues, we propose a new approach, where we transfer the task of phase unwrapping into a multi-class classification problem and introduce an efficient segmentation network to identify classes. Moreover, a noise-to-noise denoised network is integrated to preprocess noisy wrapped phase. We have demonstrated the proposed method with simulated data and in a real interferometric system.

/pdf/phase-unwrapping-in-optical-metrology-via-denoised-and-2qciul3ws7.pdf

Phase unwrapping in optical metrology via denoised and convolutional segmentation networks

Spaceborne synthetic aperture radar (SAR) real-time imaging is especially important for disaster emergencies and real-time monitoring applications with highly desired real-time requirements. Therefore, the continuous improvement of real-time imaging efficiency is an important development trend. At present, traditional real-time imaging algorithms based on constant pulse repetition frequency (PRF) have low accuracy when processing spaceborne SAR data with nonlinear trajectory. For this problem, the existing methods usually introduce some complex signal processing steps, such as scaling or interpolation processing, to improve the accuracy of the real-time imaging, but this will reduce its efficiency. Therefore, this article proposes a new real-time imaging algorithm based on variable PRF for nonlinear trajectory spaceborne SAR. By introducing the variable PRF, the proposed algorithm is equivalent to complete the complex signal processing steps in the radar signal transmission stage, which can greatly improve the efficiency of real-time imaging. Simulation experiments verify the effectiveness of the algorithm.

Real-Time Processing of Spaceborne SAR Data With Nonlinear Trajectory Based on Variable PRF

Division of focal plane (DoFP) polarization image sensors capture polarization properties of light at every imaging frame. However, these imaging sensors capture only partial polarization information, resulting in reduced spatial resolution output and a varying instantaneous field of overview (IFoV). Interpolation methods are used to reduce the drawbacks and recover the missing polarization information. In this paper, we propose residual interpolation as an alternative to normal interpolation for division of focal plane polarization image sensors, where the residual is the difference between an observed and a tentatively estimated pixel value. Our results validate that our proposed algorithm using residual interpolation can give state-of-the-art performance over several previously published interpolation methods, namely bilinear, bicubic, spline and gradient-based interpolation. Visual image evaluation as well as mean square error analysis is applied to test images. For an outdoor polarized image of a car, residual interpolation has less mean square error and better visual evaluation results.

Residual interpolation for division of focal plane polarization image sensors.

We propose a polarization demosaicing convolutional neural network to address the image demosaicing issue, the last unsolved issue in microgrid polarimeters. This network learns an end-to-end mapping between the mosaic images and full-resolution ones. Skip connections and customized loss function are used to boost the performance. Experimental results show that our proposed network outperforms other state-of-the-art methods by a large margin in terms of quantitative measures and visual quality.

Junchao Zhang

Papers

Image interpolation for division of focal plane polarimeters with intensity correlation

Phase unwrapping in optical metrology via denoised and convolutional segmentation networks

Real-Time Processing of Spaceborne SAR Data With Nonlinear Trajectory Based on Variable PRF

Residual interpolation for division of focal plane polarization image sensors.

Learning a convolutional demosaicing network for microgrid polarimeter imagery.