Latest Publications & Patents on Augmented Reality (AR)

This week: 3D Object Detection, Style Transfer, Data Augmentation, CycleGAN, AR technology, interactive learning, 3D models, educational flashcards, UAV, defect detection, Transformer, feature extraction, Hybrid Convolutional Transformer, Dynamic Prompting, Image Restoration, Spatially Aware Attention, Variational Minimization, Visual Perception, Haze Removal, Intelligent Surface Vehicles, Monocular Depth Estimation, Self-Supervised Learning, Multi-Scale Feature Extraction, Artifact Suppression, policy-constrained, symbolic rendering, AI outputs, compliance, Cybersecurity, Risk Assessment, Machine-Readable Codes, AI-Powered Systems

11 月 12, 2025

增强现实（AR）, 深度学习, 触觉反馈, 人机交互, 互动设计, 机器学习, 用户体验（UX）, 可穿戴技术

提示： 在此基础上，您可以搜索和筛选我们的航空学：
* 免费出版物搜索工具按作者、主题、关键词、日期或期刊。
* 免费专利搜索工具从欧洲专利局申请英文专利。

This is our latest selection of worldwide publications and patents in english on Augmented Reality (AR), between many scientific online journals, classified and focused on augmented reality, mixed reality, computer vision, haptic feedback, AR headset, marker-based tracking, wearable AR, interactive experience and immersive technology.

Enhancing 3D Monocular Object Detection with Style Transfer for Nighttime Data Augmentation

Published on 2025-10-21 by Alexandre Evain, Firas Jendoubi, Redouane Khemmar, Sofiane Ahmedali, Mathieu Orzalesi @MDPI

Abstract: Monocular 3D object detection (Mono3D) is essential for autonomous driving and augmented reality, yet its performance degrades significantly at night due to the scarcity of annotated nighttime data. In this paper, we investigate the use of style transfer for nighttime data augmentation and evaluate its effect on individual components of 3D detection. Using CycleGAN, we generated synthetic night images from daytime scenes in the nuScenes dataset and trained a modular Mono3D detector under differe[...]

Our summary: This study explores using style transfer for augmenting nighttime data in monocular 3D object detection. Synthetic night images generated from daytime scenes improved certain detection metrics but degraded others. Combining style transfer with real nighttime data enhances detection robustness under low-light conditions.

3D Object Detection, Style Transfer, Data Augmentation, CycleGAN

Publication

SDN 06 Taluak IV Suku)

Published on 2025-10-20 by Zainatul Sirti, Neny Rosmawarni, Musthofa Galih Prada, Nunik Destria Arianti, Novita Widyaningrum @MDPI

Abstract: The solar system is a Basic Competency for grade VI students at SDN 06 Taluak IV Suku. This material encourages students to recognize planets and their characteristics in the solar system, thus requiring interactive learning media. This research develops solar system flashcard learning media based on AR technology to enhance learning interactivity. Using the MDLC method, the application was built with Unity Editor and Vuforia SDK for Android and iOS devices. The application utilizes marker-based[...]

Our summary: This research develops an AR-based flashcard application for teaching the solar system to grade VI students. The application features 3D models of planets and includes interactive quizzes for evaluation. Testing confirms its effectiveness in enhancing learning interactivity and engagement.

A Method for Defect Inspection of Power Transmission Lines

Published on 2025-10-20 by Jianing Chen, Xin Zhang, Dawei Feng, Jiahao Li, Liang Zhu @MDPI

Abstract: Unmanned Aerial Vehicle (UAV)-based computer vision has emerged as a crucial approach for transmission line defect detection. However, transmission lines contain multi-scale components in complex environments, thereby complicating the accurate extraction of multi-scale features and necessitating a careful balance between model complexity with detection accuracy. This paper proposes a Transformer-based framework called Power Line Defect Detection Transformer (PLD-DETR). To simultaneously capture [...]

Our summary: This paper presents a Transformer-based framework called PLD-DETR for defect detection in power transmission lines using UAVs. It introduces a dual-domain selection mechanism for collaborative feature extraction and an adaptive sparse self-attention mechanism to enhance critical feature processing. Experimental results show significant improvements in detection accuracy and efficiency compared to baseline models and other methods.

UAV, defect detection, Transformer, feature extraction

Publication

Hybrid Convolutional Transformer with Dynamic Prompting for Adaptive Image Restoration

Published on 2025-10-19 by Jinmei Zhang, Guorong Chen, Junliang Yang, Qingru Zhang, Shaofeng Liu, Weijie Zhang @MDPI

Abstract: High-quality image restoration (IR) is a fundamental task in computer vision, aiming to recover a clear image from its degraded version. Prevailing methods typically employ a static inference pipeline, neglecting the spatial variability of image content and degradation, which makes it difficult for them to adaptively handle complex and diverse restoration scenarios. To address this issue, we propose a novel adaptive image restoration framework named Hybrid Convolutional Transformer with Dynamic [...]

Our summary: The Hybrid Convolutional Transformer with Dynamic Prompting (HCTDP) is designed for adaptive image restoration. It introduces a Spatially Aware Dynamic Prompt Head Attention module for local restoration and a Gated Skip-Connection module for feature refinement. The framework shows superior performance in various restoration tasks while using fewer parameters than competitors.

Hybrid Convolutional Transformer, Dynamic Prompting, Image Restoration, Spatially Aware Attention

Hybrid Regularized Variational Minimization Method to Promote Visual Perception for Intelligent Surface Vehicles Under Hazy Weather Condition

Published on 2025-10-17 by Peizheng Li, Dayong Qiao, Caofei Luo, Desong Wan, Guilian Li @MDPI

Abstract: Intelligent surface vehicles, including unmanned surface vehicles (USVs) and autonomous surface vehicles (ASVs), have gained significant attention from both academic and industrial communities. However, shipboard maritime images captured under hazy weather conditions inevitably suffer from a blurred, distorted appearance. Low-quality maritime images can lead to negative effects on high-level computer vision tasks, such as object detection, recognition and tracking, etc. To avoid the negative inf[...]

Our summary: This work presents a novel method to enhance visual perception for intelligent surface vehicles operating in hazy conditions. It introduces a transmission map estimation and refinement framework to generate haze-free maritime images. Comprehensive experiments demonstrate that the proposed method outperforms existing dehazing techniques, improving navigation safety.

Variational Minimization, Visual Perception, Haze Removal, Intelligent Surface Vehicles

Publication

A Lightweight Self-Supervised Monocular Depth Estimation Framework with Multi-Scale Feature Extraction

Published on 2025-10-16 by Xinxing Tian, Zhilin He, Yawei Zhang, Fengkai Liu, Tianhao Gu @MDPI

Abstract: Monocular depth estimation is an essential component in computer vision that enables 3D scene understanding, with critical applications in autonomous driving and augmented reality. This paper proposes a lightweight self-supervised framework from single RGB images for multi-scale feature extraction and artifact elimination in monocular depth estimation (MsGf). The proposed framework first designs a Cross-Dimensional Multi-scale Feature Extraction (CDMs) module. The CDMs module combines parallel m[...]

Our summary: This paper presents a lightweight self-supervised framework for monocular depth estimation using multi-scale feature extraction. It introduces a Cross-Dimensional Multi-scale Feature Extraction module and a Sobel Edge Perception-Guided Filtering module to enhance feature representation and reduce artifacts. Experimental results show that the proposed method outperforms state-of-the-art techniques while maintaining a low parameter count.

Monocular Depth Estimation, Self-Supervised Learning, Multi-Scale Feature Extraction, Artifact Suppression

System and method for policy-constrained symbolic rendering of ai outputs

Patent published on the 2025-09-18 in US under Ref US2025294061 by ONESOURCE SOLUTIONS INT INCâ€‚[US] (Arkoff Haroldâ€‚[us], Jukic Vedranâ€‚[it])

Abstract: A computer-implemented system and method are provided for policy-constrained symbolic rendering of artificial intelligence (AI) outputs in regulated, high-stakes environments. The invention transforms conventional machine-generated inference outputs into semantically compressed symbolic glyphs, each visually encoding not only the inference result, but also the associated policy, provenance, user role, jurisdiction, and legal status. The system comprises a rendering controller that evaluates AI o[...]

Our summary: The system transforms AI outputs into symbolic glyphs that encode inference results and associated policies. It evaluates display eligibility based on real-time rules and user context, rendering approved glyphs while suppressing or substituting denied outputs. The architecture ensures lawful interaction with AI, enhancing trust and reducing cognitive load.

policy-constrained, symbolic rendering, AI outputs, compliance

Patent

Cybersecurity architectures for multi-contextual risk quantification

Patent published on the 2025-09-18 in US under Ref US2025294047 by QRSHIELD LLCâ€‚[US] (Brown Josephâ€‚[us], Rodriguez Anthonyâ€‚[us])

Abstract: The present disclosure relates to cybersecurity architectures and systems for assessing and quantifying security threats and risks associated with machine-readable codes, such as quick response codes, barcodes, data matrix codes, and other types of codes. A security application comprises a multi-context threat assessment system configured to analyze a broad spectrum of risk assessment attributes across multiple contexts. These contexts relate to the machine-readable code itself, target network r[...]

Our summary: The disclosure presents cybersecurity architectures for quantifying risks related to machine-readable codes. It features a multi-context threat assessment system analyzing various risk attributes. Additionally, it includes an API for integration and an AI-powered network for enhanced threat detection.

Cybersecurity, Risk Assessment, Machine-Readable Codes, AI-Powered Systems

Patent

Table of Contents

添加标题以开始生成目录

迎接新挑战
机械工程师、项目、工艺工程师或研发经理

可在短时间内接受新的挑战。
通过 LinkedIn 联系我
塑料金属电子集成、成本设计、GMP、人体工程学、中高容量设备和耗材、精益制造、受监管行业、CE 和 FDA、CAD、Solidworks、精益西格玛黑带、医疗 ISO 13485

我们正在寻找新的赞助商

您的公司或机构从事技术、科学或研究吗？
> 给我们发送消息 <

涵盖的主题： 增强现实、混合现实、计算机视觉、触觉反馈、增强现实头显、基于标记的跟踪、可穿戴增强现实、交互式体验、沉浸式技术、动态手势识别、基准数据集、预训练权重、ISO/IEC 30170、ISO 9241-210、ISO/IEC 25010、ISO/IEC 27001 和 ISO/IEC 25012。

历史背景

彩色电视用铕荧光粉

发现掺铕的钒酸钇（[latex]YVO_4:Eu^{3+}[/latex]）可以作为一种亮丽的红色荧光粉，是彩色电视的一个关键性突破。在此之前，红色荧光粉的发光强度较弱，导致色彩暗淡。[latex]Eu^{3+}[/latex] 离子发出的强烈窄带红色荧光使色彩显示明亮、鲜艳，极大地提高了彩色电视的质量，并为显示技术设定了标准。.

自上而下的纳米材料合成

自上而下的合成是指从较大的块体材料开始，将其分解或图案化至纳米尺度，从而创建纳米材料。关键技术包括球磨等机械方法和光刻方法，例如光刻、电子束光刻和纳米压印光刻。这些方法通常用于创建结构化表面和集成电路，但可能会受到表面缺陷的影响。

飞轮储能（FES）

飞轮储能（FES）的工作原理是将转子（飞轮）加速到非常高的速度，并将能量作为旋转动能保持在系统中。存储的能量与转速的平方成正比。当能量被提取出来时，飞轮的旋转速度会减慢。存储能量的计算公式为 [latex]E = \frac{1}{2}I \omega^2[/latex]，其中 I 是惯性矩，ω 是角速度。.

分子电子学

分子电子学探索利用单个分子或纳米级分子集合作为基本电子元件。该方法旨在构建微型化极限的电路，远远超越传统的硅基技术。关键元件包括分子线、开关和整流器，它们利用电子隧穿分子轨道等量子力学特性来实现功能。

锂离子嵌入机理

锂离子电池通过插层机制发挥作用，即离子可逆地插入层状主材料中。在放电过程中，锂离子（[latex]Li^+[/latex]）从负极（阳极）（通常是石墨）脱闰，并通过非水电解质闰入正极（阴极）（通常是金属氧化物）。电子穿过外部电路，产生电流。

蒸汽压增强因子

潮湿空气中液面上水的平衡蒸汽压（[latex]p^*_{H_2O,a}[/latex]）略大于纯水表面的平衡蒸汽压（[latex]p^*_{H_2O}[/latex]）。水蒸气增强因子 [latex]f_w[/latex] 可以量化这种差异，它取决于温度和潮湿空气的压力。其关系为 [latex]p^*_{H_2O,a} = f_w(T, p_{ms}) \cdot p^*_{H_2O}[/latex].

稀土磁铁

稀土磁铁是由稀土元素合金制成的强力永磁体。稀土磁铁开发于20世纪70年代和80年代，最常见的类型是钕磁铁（NdFeB）和钐钴磁铁（SmCo）。它们是目前已知的最强永磁体，产生的磁场比铁氧体或铝镍钴磁铁强得多，从而能够实现许多技术的小型化和性能提升。注意：“稀土元素”一词是历史上的误称。这些元素在地壳中并非极其稀有。铈是含量最丰富的元素，与铜相似，是第25位最丰富的元素。即使是含量最少的稳定稀土元素镥，其常见程度也比黄金高出近200倍。“稀有”标签的出现是因为它们难以分离。

1964

1970

1974-11-15

1980

1984

1963

1968

1970

1980

1984

互补金属氧化物半导体 (CMOS)

CMOS（互补金属氧化物半导体）是构建集成电路的主流技术。它使用互补的p型和n型MOSFET对来构建逻辑门。其主要优势是静态功耗极低，因为在稳定状态下，互补对中的一个晶体管始终处于关闭状态，因此除了开关转换期间外，电流流动极小。

贝塞尔曲线

UNISURF 由法国工程师皮埃尔·贝塞尔 (Pierre Bézier) 于 20 世纪 60 年代为雷诺 (Renault) 开发，是首批真正的 3D CAD/CAM 系统之一。其核心创新在于使用了如今被称为贝塞尔曲线和曲面的技术。这些曲线和曲面是由一组控制点定义的参数曲线，能够直观地以数学方式创建复杂的车身自由形状。

GPS三边测量原理

GPS 使用三边测量法确定接收器的位置。通过测量与至少三颗卫星的距离，接收器可以精确定位其在地球表面的位置。距离的计算方法是将信号传播时间乘以光速。需要第四颗卫星来同步接收器的时钟，以解决四个未知数：纬度、经度、海拔和时间。

超导磁能存储（SMES）

超导磁能储存（SMES）系统将能量储存在超导线圈中的直流电流所产生的磁场中。只要线圈保持在超导温度下，能量就可以无限存储，因为几乎不会因电阻而造成能量损失。存储的能量由 [latex]E = \frac{1}{2} 给出。L I^2[/latex].

故障物理学（PoF）

失效物理学（PoF）是一种可靠性工程方法，它利用材料科学和物理学知识来理解失效的根本原因机制并建立模型。它不单纯依赖过去故障的统计数据，而是通过分析导致退化和故障的物理过程（如疲劳、腐蚀、蠕变）来预测故障。

纳米材料的量子尺寸效应

量子尺寸效应描述的是当材料的尺寸接近纳米级时，其电子和光学特性发生变化的现象。当材料的尺寸与电子的德布罗格利波长相当时，就会产生量子约束。这将量子化电子能级，从而产生与尺寸相关的带隙，[latex]E_g(R) \approx E_{g,\b\u\lk} + \frac\{hb}.+ （\frac{1}{m_e^*} + \frac{1}{m_h^*}）[/latex]。