Wavefront coding (WFC) techniques, including optical coding and digital image processing stages, enable significant capabilities for extending the depth of field of imaging systems. In this study, we demonstrated a deeply learned far-infrared WFC camera with an extended depth of field. We designed and optimized a high-order polynomial phase mask by a genetic algorithm, exhibiting a higher defocus consistency of the modulated transfer functions than works published previously. Additionally, we trained a generative adversarial network based on a synthesized WFC dataset for the digital processing part, which is more effective and robust than conventional decoding methods. Furthermore, we captured real-world infrared images using the WFC camera with far, middle, and near object distances. Their results after wavefront coding/decoding showed that the model of deeply learned networks improves the image quality and signal-to-noise ratio significantly and quickly. Therefore, we construct a novel artificial intelligent method of deeply learned WFC optical imaging by applying infrared wavelengths, but not limited to, and provide good potential for its practical application in “smart” imaging and large range target detection.

Simultaneous localization and mapping (SLAM) is widely used in autonomous driving and intelligent robot positioning and navigation. In order to overcome the defects of traditional visual SLAM in rapid motion and bidirectional loop detection, we present a feature-based PAL-SLAM system for a panoramic-annular-lens (PAL) camera in this paper. We use a mask to extract and match features in the annular effective area of the images. A PAL-camera model, based on precise calibration, is used to transform the matched features onto a unit vector for subsequent processing, and a prominent inlier-checking metric is designed as an epipolar constraint in the initialization. After testing on large-scale indoor and outdoor PAL image dataset sequences, comprising of more than 12,000 images, the accuracy of PAL-SLAM is measured as typically below 1 cm. This result holds consistent in conditions when the camera rotates rapidly, or the Global Navigation Satellite System (GNSS) signals are blocked. PAL-SLAM can also detect unidirectional and bidirectional loop closures. Hence it can be used as a supplement or alternative to expensive commercial navigation systems, especially in urban environments where there are many signal obstructions such as buildings and bridges.

Phase measuring deflectometry is a powerful measuring method for complex optical surfaces, which captures the reflected fringe images encoded on the screen under the premise of focusing the measured specular surface. Due to the limited depth of field of the camera, the captured images and the measured surface cannot be focused at the same time. To solve the position-angle uncertainty issue, in this Letter, the wavefront coding technology is used to modulate the imaging wavefront of the deflectometry, thereby making the measuring system insensitive to the defocus and other low-order aberration including astigmatism, field curvature, and so on. To obtain the accurate phase, the captured fringe images are deconvoluted using the modulated point spread function to reduce the phase error. Demonstrated with a highly curved spherical surface, the measurement accuracy can be improved by four times. Experiments demonstrate that the proposed method can successfully reconstruct the complex surfaces defocusing the captured images, which can greatly release the focusing requirement and improve measurement accuracy. (C) 2022 Optica Publishing Group

In semiconductor manufacturing, defect inspection in non-patterned wafer production lines is essential to ensure high-quality integrated circuits. However, in actual production lines, achieving both high efficiency and high sensitivity at the same time is a significant challenge due to their mutual constraints. To achieve a reasonable trade-off between detection efficiency and sensitivity, this paper integrates the time delay integration (TDI) technology into dark-field microscopy. The TDI image sensor is utilized instead of a photomultiplier tube to realize multi-point simultaneous scanning. Experiments illustrate that the increase in the number of TDI stages and reduction in the column fixed pattern noise effectively improve the signal-to-noise ratio of particle defects without sacrificing the detecting efficiency.

Recent years have seen great advances in the area of semantic segmentation. However, general methods are targeted at pinhole images and tend to underperform when directly adopted to panoramic images. And with the wide applications of panoramic cameras, it is important to develop feasible approaches to train segmentation models for their real-time applications. To address this problem, we propose a novel method using self-training and achieve comparable results on DensePASS dataset. Namely, we propose a deformable merge module tailored for panoramic images by efficiently and accurately incorporating features of different levels. We design a novel prototype adaptation term that aids the model to better learn the class-wise feature embeddings of distorted objects. Finally, we use a simple and valid evaluation method to achieve real-time and improved inference performance. All combined, we can reach 58.27% of mIoU scores on DensePASS dataset and achieve new state of the art results.