Results 151 to 160 of about 286,668 (294)

DBF‐Net: A Deep Bidirectional Fusion Network for 6D Object Pose Estimation with Sparse Linear Transformer

Advanced Intelligent Systems, EarlyView.
6D object pose estimation is a critical component in computer vision domain. A deep bidirectional fusion network is developed, DBF‐Net, which achieves accurate 6D object pose estimation using a single RGB‐D image. DBF‐Net effectively extracts and fuses geometric and appearance features from input data.
Xuan Fan, Tao An, Hongbo Gao, Tao Xie, Lijun Zhao, Ruifeng Li   +5 more
wiley   +1 more source

Waveguide‐Based Retinal Projection Near‐Eye Display with Bidirectional Eyebox Expansion

Advanced Intelligent Systems, EarlyView.
A waveguide‐type retinal projection display system with bidirectional extended eyebox is proposed. The two‐layer holographic optical elements (HOEs), with two eye reliefs of 11 and 12 mm in the axial direction, serve as the image combiner, and each layer of HOEs generates two viewpoints with a horizontal spacing of 5 mm. Based on the mechanism of human
Yujing Fu, Lijun Jiang, Jiafu Lin, Yuang Chen, Huan Deng   +4 more
wiley   +1 more source

Flight of the Future: An Experimental Analysis of Event‐Based Vision for Online Perception Onboard Flapping‐Wing Robots

Advanced Intelligent Systems, EarlyView.
A thorough analysis of event‐based vision for flapping‐wing robots is presented, with emphasis on hardware integration, suitability under challenging flight conditions, and real‐time performance. Theoretical and experimental studies demonstrate how these sensors enable robust and efficient onboard perception for ornithopters, thereby advancing autonomy
Raul Tapia, Javier Luna‐Santamaria, Ivan Gutierrez Rodriguez, Juan Pablo Rodríguez‐Gómez, José Ramiro Martínez‐de Dios, Anibal Ollero   +5 more
wiley   +1 more source

Design of Compact Liquid Crystal on Silicon Projection Optics Utilizing a Common Freeform Optical Path for Augmented Reality Displays

Advanced Intelligent Systems, EarlyView.
This study presents a compact freeform projection optics using dual wedge prisms for waveguide displays. Unlike previous designs that separate illumination and imaging paths, a freeform optical path integrates both. The system achieves a 32º field of view, 37.5 pixels per degree, and a total volume of less than 2 cm3.
Ximeng Wang, Dewen Cheng, Yuefan Shan, Da Wang, Tong Yang, Yongtian Wang   +5 more
wiley   +1 more source

Adapting Image‐Based Models for 1D Data via Spider Plot Transformation and Transfer Learning

Advanced Intelligent Systems, EarlyView.
A novel method enables the use of pretrained image‐based neural networks for complex 1D data, including Raman and mid‐infrared spectra, electrocardiograms, and mass spectrometry. 2D spider plots with false‐color fill enable transfer lerning, therefore enhancing data augmentation and model explainability across diverse spectral and time series datasets.
Azadeh Mokari, Oleg Ryabchykov, Thomas Bocklitz   +2 more
wiley   +1 more source

Hi‐LabSpermTracking: A Novel and High‐Quality Sperm Tracking Dataset with an Advanced Ensemble Detection and Tracking Approach for Real‐World Clinical Scenarios

Advanced Intelligent Systems, EarlyView.
This study presents Hi‐LabSpermTracking, a long‐duration, expert‐annotated sperm motility dataset for detection and tracking. It evaluates You Only Look Once version 8, Real‐Time Detection Transformer, and Simple Online and Realtime Tracking with a Deep Association Metric in three scenarios. The mean ensemble method improves tracking performance. Sperm
Abdulsamet Aktas, Gorkem Serbes, Hakkı Uzun, Merve Huner Yigit, Nizamettin Aydin, Hamza Osman Ilhan   +5 more
wiley   +1 more source

Exploring the Effects of 3D Gaze Stimulation and Color Performance in Augmented Reality‐Based Steady‐State Visual Evoked Potential

Advanced Intelligent Systems, EarlyView.
This study investigates how gaze mode and stimulus brightness affect augmented reality‐based steady‐state visual evoked potentials (AR‐SSVEP) brain‐computer interface (BCI) performance. Experiments with 20 participants show that binocular gaze improves recognition accuracy and stimulus luminance impacts performance.
Yiting Geng, Banghua Yang, Mengao Guo, Yuan Yao, Yonghuai Zhang, Luting Chen, Xinxing Xia   +6 more
wiley   +1 more source

Large Language Model‐Embedded Intelligent Robotic Scrub Nurse with Multimodal Input for Enhancing Surgeon–Robot Interaction

Advanced Intelligent Systems, EarlyView.
A large language model (LLM)‐powered multimodal robotic scrub nurse control framework is proposed for enhancing human–robot interaction. Inside, the vision module gives out instrument class, location, and occlusion relationship. Speech module captures and converts user's speech commands.
Wing Yin Ng, Wanyu Ma, Pheng Ann Heng, Philip Wai Yan Chiu, Zheng Li   +4 more
wiley   +1 more source

Haptic Perception via the Dynamics of a Flexible Body Inspired by an Ostrich's Neck

Advanced Intelligent Systems, EarlyView.
Inspired by avian anatomy, this study uses a flexible robotic neck to investigate haptic perception driven by musculoskeletal dynamics. By applying physical reservoir computing, the robot encodes external force interactions into its body dynamics, allowing effective object classification.
Kazashi Nakano, Katsuma Inoue, Yasuo Kuniyoshi, Kohei Nakajima   +3 more
wiley   +1 more source

Multitarget Recognition of Flower Images Based on Lightweight Deep Neural Network and Transfer Learning

Advanced Intelligent Systems, EarlyView.
This article proposes a lightweight YOLOv4‐based detection model using MobileNetV3 or CSPDarknet53_tiny, achieving 30+ FPS and higher mAP. It also presents a ShuffleNet‐based classification model with transfer learning and GAN‐augmented images, improving generalization and accuracy.
Qingyang Liu, Yanrong Hu, Hongjiu Liu
wiley   +1 more source