We propose a high-performance reflection-type augmented reality (AR) 3D display by using reflective polarizer (RP). The RP functions as imaging device well an image combiner that combines the real scenes and images reconstructed integral unit. Benefiting from flawless of RP, proposed AR system can achieve high-definition display. A prototype based on structure is developed, it presents good effects performances. developed very compact, thin 3.4 mm, which makes be potential candidate in...

Integral imaging salient object detection effectively extracts attention-grabbing information from complex visual scenes and accurately reconstructs objects in three-dimensional (3D). However, current methods face challenges such as difficulties extracting relationships between homologous pixels, the limitation of generating black-and-white images. These problems hinder accurate provision 3D color displays. In this paper, we propose a high-precision integral reconstruction method that...

Background and purposeCurrent methods, like treatment planning system algorithms (TPSDose), lack accuracy, whereas Monte Carlo dose distribution (MCDose) is accurate but computationally intensive. We proposed a deep learning (DL) model for rapid prediction of simulated in heavy ion therapy (HIT).Materials methodsWe developed DL − the Cascade Hierarchically Densely 3D U-Net (CHD U-Net) to predict MCDose using computed tomography images TPSDose 67 head-and-neck patients 30 thorax-and-abdomen...

In this paper, a locally controllable two-dimensional (2D)/ three-dimensional (3D) mixed display system and corresponding image generation method are proposed. The proposed is mainly composed of collimating backlight module (CBM) light control (LCM). CBM provides polarized light. LCM modulates part the to form point sources for 3D other scattered 2D display. states can be controlled by using pixelated mask loaded on polarization switching layer. addition, According observer's demand,...

Depth of field (DOF) is one the important parameters three-dimensional (3D) displays. A two-dimensional (2D)/3D switchable display that can both high-resolution 2D images and vivid 3D with large DOF an ideal purpose. In this paper, we propose a depth-enhanced 2D/3D integral imaging by using n-layer focusing control units (FCUs). Each layer FCU composed polarization switch polarization-dependent liquid crystal micro-lens array (LCMLA). According to state incident light switched switch, LCMLA...

This study discusses the technical requirements of line‐commutated converter‐based high‐voltage direct current (LCC‐HVDC) power transmission participating in a receiving end AC system's black start. The control and start‐up modes LCC‐HVDC suitable for start are discussed. Through short‐circuit capacity analysis frequency estimation, appropriate strength system to is studied. A reactive coordination strategy proposed reduce overvoltage caused by HVDC filter. An innovative additional at...

Two-dimensional (2D)/three-dimensional (3D) convertible or mixed display is one of the most important factors for fast penetration 3D into market. In this paper, we propose a 2D/3D frontal projection system that mainly contains liquid crystal micro-lens array (LCMLA) and quarter-wave retarding film with pinholes (QWRF-P). The LCMLA exhibits focusing effect no optical depending on polarization direction incident lights. forward lights pass through without any bending. After passing QWRF-P...

Deep learning-based hyperspectral image super-resolution (SR) methods have achieved great success recently. However, most existing models can not effectively explore spatial information and spectral between bands simultaneously, obtaining relatively low performance. To address this issue, in paper, we propose a novel spectral-spatial residual network for (SSRNet). Our method spatial-spectral by using 3D convolution instead of 2D convolution, which enables the to better extract potential...

Roads are traffic lifelines for emergency rescue and disaster relief. After major earthquakes, it is very significant to extract road damage rapidly accurately in areas by remote sensing rescue. Because caused earthquake ever-changing,there no common spectral characteristic of images. Meanwhile, there many phenomena "synonyms spectrums" "different spectrum characteristics with the same object" Thus, traditional methods usually low accuracy not universal. This paper proposes an automatic...

Integral imaging three-dimensional (3D) display provides quasi-continuous viewpoints within a certain viewing angle. A single human eye can obtain several parallax images corresponding to the viewpoints. In this paper, we studied effect of received by on accommodation response when 3D image reconstructed integral display. We analyzed distribution an and correspondence relationship between pixels information in elemental array. experiment, responses eyes with different viewpoint quantities...

Spatial-temporal modeling is crucial for action recognition in videos within the field of artificial intelligence. However, robustly extracting motion information remains a primary challenge due to temporal deformations appearances and variations frequencies between different actions. In order address these issues, we propose an innovative effective method called Motion Sensitive Network (MSN), incorporating theories neural networks key concepts autonomous system control decision-making....

In order to realize in-hand manipulation of unknown objects, we introduce an extension our previously developed framework, such that long sequences, involving finger regrasping, become feasible. To this end, propose a novel feedback controller, which searches for locally optimal contact points (suitable regrasping), employing online exploration process on the object surface. The method autonomously estimates and follows gradient smooth objective function. More concretely, dynamically switch...

Under the framework of computational integral imaging, an optical 3D objects security and high-quality reconstruction method based on pixel-evaluating mapping (PEM) algorithm is proposed. In this method, pixel crosstalk caused by noneffective overlap effectively reduced a pixel-evaluated mask, which can improve image quality reconstructed objects. Meanwhile, compared with other imaging methods, our proposed PEM obtain more accurate weight parameters, thereby provide higher quality. addition,...

In this paper, we propose a reflective augmented reality (AR) display system based on integral imaging (II) using mirror-based pinhole array (MBPA). The MBPA, obtained by punching pinholes mirror, functions as three-dimensional (3D) device, well an image combiner. of MBPA can realize array-based II display, while the mirror real objects, so to combine images objects with reconstructed 3D images. structure proposed AR is very simple, and only projection or two-dimensional screen needed MBPA....

In this paper, we present a 2D/3D mixed system with high image quality based on integral imaging and switchable diffuser element. The proposed comprises liquid crystal display screen, lens array, element projector. can be controlled to images or 2D 3D independently, reduce the Moire fringe black grid. addition improved quality, has advantages of simple structure is low cost, which contribute portability practicability.

Remote sensing technology plays an important role in gathering information of social infrastructure damage which is crucial for relief and reconstruction work after strike. Comparatively speaking, radar sensors are capable observing the ground irrespective weather conditions or time day, therefore have been gaining prominence as a reliable tool grasping overall picture from disasters. In this paper, we propose improved algorithm that enables us to combine GIS data SAR image seismic...

UHF-RFID (Ultra High Frequency Radio Identification), with the feature of reliable, accurate and fast, has been used in vehicular traffic management system to relief urban congestion, air pollution etc. To strengthen security improve performance tag, a secure, high tag is designed implemented this paper. Authentication authorization between reader are performed ensure legal identities both sides. Identity information hidden prevent unauthorized tracking. Low power circuit technology as well...

Power line segmentation is very important to ensure the safe and stable operation of unmanned aerial vehicles in intelligent power inspection. Although algorithm based on deep learning has made some progress, it still quite difficult achieve accurate due complex changeable background images small targets, existing models too large not suitable for edge deployment. This paper proposes a lightweight algorithm—G-UNets. The uses improved U-Net Lei Yang et al. (2022) as basic network (Y-UNet)....

Potent usage of the multi-scale light field information for salient object detection (SOD) is essential requirement three-dimensional (3D) SOD. On this basis, a 3D-SOD scheme proposed that employs pixel mapping algorithm to achieve more distinct representation spatial and angular in four-dimensional (4D) field, collaboratively mining global saliency cues via co-salient (CoSOD) network. Compared with previous method, our filters out most noise by thoroughly leveraging dependence 4D offering...

Integral imaging, as an excellent light-field three-dimensional (3D) imaging technique, is considered one of the most important technologies for 3D encryption because its obvious advantages high robustness, security, and computational feasibility. However, to date, there no effective cryptanalysis technology cryptosystem. In this Letter, a algorithm based on deep learning cryptosystem presented. The image can be optically retrieved by trained network model without keys. experimental results...

Abstract Rationale: Familial hemophagocytic lymphohistiocytosis (FHL) is a fatal autosomal recessive immunodeficiency disease whose rapid and accurate diagnosis paramount for appropriate treatment. Mutations in STXBP2 gene have been associated with FHL type 5 (FHL-5). Here, we report the first Tibetan Chinese patient diagnosed FHL-5 caused by novel compound heterozygous mutation . Patient concerns: A 9-year-old girl who presented recurrent fever, splenomegaly, pancytopenia,...