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

We suggest a design method of graded-refractive-index (GRIN) antireflection (AR) coating for s-polarized or p-polarized light at off-normal incidence. The spectrum characteristic of the designed antireflection coating with a quintic effective refractive-index profile for a given state of polarization has been discussed. In addition, the genetic algorithm was used to optimize the refractive index profile of the GRIN antireflection for reducing the mean reflectance of s- and p-polarizations. The average reflectance loss was reduced to only 0.04% by applying optimized GRIN AR coatings onto BK7 glass over the wavelength range from 400 to 800 nm at the incident angle of θ0 = 70°.

Design of wideband graded-index antireflection coatings at oblique light incidence

Hyperspectral imagery often suffers from the degradation of spatial, spectral, or temporal resolution due to the limitations of hyperspectral imaging devices. To address this problem, hyperspectral recovery from a single red-green-blue (RGB) image has recently achieved significant progress via deep learning. However, current deep learning-based methods are all learned in a supervised way under the availability of RGB and correspondingly hyperspectral images, which is unrealistic for practical applications. Hence, we propose to recover hyperspectral images from a single RGB image in an unsupervised way. Moreover, based on the statistical property of hyperspectral images, a customized loss function is proposed to boost the performance. Extensive experiments on the BGU iCVL Hyperspectral Image Dataset demonstrate the effectiveness of the proposed method.

Unsupervised learning for hyperspectral recovery based on a single RGB image.

Infrared small target detection plays a key role in infrared precision guidance and infrared early-warning system. It has been a difficult problem for researchers to study on how to detect targets accurately at a long distance as early as possible. Most of the existing algorithms can detect small targets in simple backgrounds, but they would fail on the detection when the background clutters are chaotic and the signal to clutter ratio (SCR) is low. Therefore, we propose a new infrared small target detection method which called a directional-progressive search (DPS) method. Our method derives from a fact that a small target is an isotropic Gaussian distribution at a long distance, while clutters show different characteristics in different directions. Based on this difference, we decompose the original image into first-order sub-images with different directions by using a first-order directional derivative (FODD) filter. Then zero-crossing points are detected in each direction step by step to distinguish small targets and background clutters. After screening progressively, the positions where existing zero-crossing points in every sub-image can be confirmed as targets. Experimental results show that our method acquires higher detection rates and lower false alarm rates compared with other methods. At the same time, our method can still keep better performance under various complex backgrounds. The robustness of our method is strong.

A Directional-Progressive Search Method for Infrared Small Target Detection

An image interpolation model based on sparse representation is proposed. Two widely used priors including sparsity and nonlocal self-similarity are used as the regularization terms to boost the performance of the interpolation model. Meanwhile, we incorporate nonlocal linear regression into this model, since nonlocal similar patches could provide a better approximation to a given patch. Moreover, we propose a new approach to learn an adaptive sub-dictionary online instead of clustering. For each patch, similar patches are grouped to learn the adaptive sub-dictionary, generating a more sparse and accurate representation. Finally, weighted encoding is introduced to suppress tailing of fitting residuals in data fidelity. Abundant experimental results show that our proposed method achieves better performance compared to several state-of-the-art methods in terms of subjective and objective evaluations.

Weighted-encoding-based image interpolation with the nonlocal linear regression model

thin films at various cathode power and substrate bias voltages were deposited by pulsed DC reactive magnetron sputtering of a metallic Nb target in a pure oxygen atmosphere. The characteristics of the films have been studied using spectrometer, atomic force microscopy (AFM), field emission scanning electron microscopy (FE-SEM). Laser damage tests at 1064 nm wavelength with pulse duration of 12 ns we re conducted on the single-layer systems. Results indicate that the cathode power may not be an im portant impact-factor of the LIDT of Nb

Junchao Zhang

Papers

Design of wideband graded-index antireflection coatings at oblique light incidence

Unsupervised learning for hyperspectral recovery based on a single RGB image.

A Directional-Progressive Search Method for Infrared Small Target Detection

Weighted-encoding-based image interpolation with the nonlocal linear regression model

Properties of niobium oxide films deposited by pulsed DC reactive magnetron sputtering