Dies ist unsere neueste Auswahl an weltweiten Veröffentlichungen und Patenten in englischer Sprache zum Thema Augmented Reality (AR), die sich auf Augmented Reality, Mixed Reality, Computer Vision, haptisches Feedback, AR-Headset, markerbasiertes Tracking, Wearable AR, interaktive Erfahrung und immersive Technologie konzentrieren und in zahlreichen wissenschaftlichen Online-Zeitschriften veröffentlicht wurden.
A Feasibility Study Using Active Contours
Published on 2025-04-13 by Alper Yildirim, Samuel Bignardi, Christopher F. Barnes, Anthony Joseph Yezzi @MDPI
Abstract: Multi-view stereo techniques with traditional cameras have wide applications in robotics and computer vision for scene reconstruction. Their dependence on the visible spectrum, however, poses several limitations that radar sensing could overcome in obstructing conditions such as fog and smoke. We propose a new radar-based multi-view stereo method for scene reconstruction, which combines the power of multi-view stereo techniques with the advantages of radar sensing by extending upon our previous [...]
Our summary: Proposed radar-based multi-view stereo method using active contours for scene reconstruction, leveraging radar sensing to overcome limitations of traditional cameras, demonstrating success through simulated 2D experiments.
feasibility study, active contours, radar sensing, multi-view stereo
Publication
Curriculum-Guided Adversarial Learning for Enhanced Robustness in 3D Object Detection
Published on 2025-03-09 by Jinzhe Huang, Yiyuan Xie, Zhuang Chen, Ye Su @MDPI
Abstract: The pursuit of robust 3D object detection has emerged as a critical focus within the realm of computer vision. This paper presents a curriculum-guided adversarial learning (CGAL) framework, which significantly enhances the adversarial robustness and detection accuracy of the LiDAR-based 3D object detector PointPillars. By employing adversarial learning with prior curriculum expertise, this framework effectively resists adversarial perturbations generated by a novel attack method, P-FGSM, on 3D p[...]
Our summary: Enhanced robustness in 3D object detection through curriculum-guided adversarial learning, development of Pillar-RBFN, creation of Adv-KITTI dataset, adaptive focal loss formulation.
Curriculum-Guided Adversarial Learning, 3D Object Detection, PointPillars, Adversarial Robustness
Publication
Virtual and Real Occlusion Processing Method of Monocular Visual Assembly Scene Based on ORB-SLAM3
Published on 2025-03-06 by Hanzhong Xu, Chunping Chen, Qingqing Yin, Chao Ma, Feiyan Guo @MDPI
Abstract: Addressing the challenge of acquiring depth information in aero-engine assembly scenes using monocular vision, which complicates mixed reality (MR) virtual and real occlusion processing, we propose an ORB-SLAM3-based monocular vision assembly scene virtual and real occlusion processing method. The method proposes optimizing ORB-SLAM3 for matching and depth point reconstruction using the MNSTF algorithm. MNSTF can solve the problems of feature point extraction and matching in weakly textured and [...]
Our summary: Virtual and real occlusion processing method based on ORB-SLAM3 optimized with MNSTF algorithm for monocular vision assembly scenes, improving accuracy and real-time performance.
ORB-SLAM3, Monocular Vision, MNSTF, Mixed Reality
Publication
Equestrian leg training with user feedback and methods of using same
Patent published on the 2025-03-06 in WO under Ref WO2025049312 by GAUTESEN KYRA [US] (Gautesen Kyra [us])
Abstract: A system for providing feedback to a horseback rider may include a pressure sensor configured to be attached to a leg of the rider. The pressure sensor may be configured to be located between the leg of the rider and a horse. The pressure sensor may be configured to activate when subjected to a pressure that exceeds a threshold. A haptic feedback device may be configured to be coupled to the leg of the rider and electrically coupled to the pressure sensor. The haptic feedback device may be confi[...]
Our summary: System for providing feedback to horseback rider with pressure sensor and haptic feedback device.
Equestrian, leg training, feedback, pressure sensor
Patent
Systems and methods for trust-aware error detection, correction, and explainability in machine learning and computer vision
Patent published on the 2025-03-06 in WO under Ref WO2025049492 by AVAWATZ COMPANY [US] (Mckendry John [us], Iyer Rishabh [us], Anachi Rajini [us])
Abstract: Disclosed are methods, systems and non-transitory computer readable memory for trust-aware error detection, correction, and explainability. For instance, a method may include processing a test instance through a machine learning model to obtain a set of inferences; detecting errors in the set of inferences; automatically correcting the errors in the set of inferences and/or updating the machine learning model; determining post-hoc explanations into a cause of the errors; and outputting the post-[...]
Our summary: Systems and methods for trust-aware error detection, correction, and explainability in machine learning and computer vision. Methods, systems, and computer readable memory for trust-aware error detection, correction, and explainability. Processing test instances, detecting errors, correcting errors, updating machine learning model, determining post-hoc explanations, and outputting explanations to user.
error detection, correction, machine learning, computer vision
Patent
Microlens display apparatus for use in an augmented reality system
Patent published on the 2025-03-06 in WO under Ref WO2025049232 by APPLIED MAT INC [US] (Fu Jinxin [us], He Sihui [us])
Abstract: Embodiments of the present disclosure generally relate to augmented reality (AR) systems. More specifically, embodiments described herein provide for an AR projection system and AR devices having the projection system. In one or more embodiments, an augmented reality device includes a projection system. The projection system includes a light engine. The light engine includes a pixel. The pixel includes an emission surface. A microlens is coupled to the emission surface of the pixel. The projecti[...]
Our summary: Microlens display apparatus for augmented reality systems with projection system and light engine including pixel and emission surface, coupled with microlens and projection lens for light refraction.
microlens, display apparatus, augmented reality, projection system
Patent
Synthetic Image Data Generation for Wiring Harness Component Detection Using Machine Learning
Published on 2025-03-03 by Huong Giang Nguyen, Patrick Br�ndl, J�rg Franke @MDPI
Abstract: Machine learning is a powerful tool for computer vision tasks in manufacturing, as features are automatically extracted and a high variety of components or failures are reliably detected. A focal prerequisite for high-performing machine learning models is a database that is large in quantity as well as quality, and representative for the computer vision task in the manufacturing environment. In addition, manufacturing applications require a domain-specific dataset. Thus, we generated and integra[...]
Our summary: Synthetic image data generation for wiring harness component detection using machine learning. High-performing machine learning models require a large and representative database. We developed a synthetic data generation pipeline for object detection, specifically for wiring harness components, and achieved high-performance results.
Machine Learning, Synthetic Data Generation, Wiring Harness Component Detection, Convolutional Neural Networks
Publication
A Survey of Methods, Applications, and Challenges
Published on 2025-02-28 by Junjie Mai, Chongzhi Gao, Jun Bao @MDPI
Abstract: Domain generalization (DG) has become a pivotal research area in machine learning, focusing on equipping models with the ability to generalize effectively to unseen test domains that differ from the training distribution. This capability is crucial, as real-world data frequently exhibit domain shifts that violate the assumption of independent and identically distributed (i.i.d.) data, resulting in significant declines in model performance. Among the various strategies to address domain generaliz[...]
Our summary: A comprehensive survey of data augmentation in domain generalization, including methods, applications, and challenges. Detailed taxonomy of data augmentation techniques and comparative analysis of key methods. Exploration of domain-specific applications and analysis of effectiveness in enhancing generalization.
domain generalization, data augmentation, machine learning, challenges
Publication
DE 
EN 
FR 
ES 
IT