This study presents YOLOv8‐ES + DeepSORT‐GE, a jointly optimized detection‐tracking framework integrating deformable feature modeling and geometry‐aware association, achieving 73.6% fewer identity switches and real‐time worker monitoring in power grid construction environments. ABSTRACT Continuous worker localization and identity‐consistent tracking at
Lingwen Meng +4 more
wiley +1 more source
Deep Learning Predicts Hematopoietic Stem Cell Aging From 3D Chromatin Images
Deep learning identifies age‐associated chromatin architecture signatures in 3D images of hematopoietic stem cell nuclei, providing an interpretable imaging biomarker that distinguishes young from aged cells and detects chromatin rejuvenation after treatment.
Pablo Iáñez Picazo +5 more
wiley +1 more source
Boosting Embodied Visual Localisation Through Multi‐Granular Semantics and Multi‐Robot Consensus
ABSTRACT Achieving high accuracy and synergy remains extremely difficult for multi‐robot embodied visual localisation, which suffers from persistent real‐world challenges such as viewpoint ambiguity, appearance variation and dynamic occlusion. Conventional optimisation‐based methods often lead to incorrect feature matching without domain adaptation ...
Wenshuai Wang +4 more
wiley +1 more source
A Fisheye Image Matching Method Boosted by Recursive Search Space for Close Range Photogrammetry
Close range photogrammetry (CRP) with large field-of-view images has become widespread in recent years, especially in terrestrial mobile mapping systems (TMMS).
Mariana Batista Campos +4 more
doaj +1 more source
Observing Electrical Discharge With High 3D Spatial Resolution
ABSTRACT This study introduces an application of binocular stereo vision technology to achieve high‐resolution 3D visualisation of submillimeter discharge channels. The proposed method can capture the depth information of weak luminous discharges and provide 3D discharge trajectories, providing new insights into the discharge mechanism.
Zhicheng Wu +5 more
wiley +1 more source
RAUM-VO: Rotational Adjusted Unsupervised Monocular Visual Odometry
Unsupervised learning for monocular camera motion and 3D scene understanding has gained popularity over traditional methods, which rely on epipolar geometry or non-linear optimization.
Claudio Cimarelli +3 more
doaj +1 more source
Efficient method for outlier removal in SAR image matching based on epipolar geometry
A method is proposed for removing falsely matched points after sparse matching in synthetic aperture radar (SAR) images. This method uses epipolar geometry as well as random sample consensus (RANSAC) to automatically remove false matches (outliers) among
M. A. Ghannadi, M. Saadatseresht
semanticscholar +1 more source
Survey on AI‐Enabled Computer Vision Technologies and Applications for Space Robotic Missions
ABSTRACT This survey provides a comprehensive overview of recent advancements and challenges in Artificial Intelligence (AI)‐enabled computer vision (CV) techniques for space robotic missions, spanning critical phases such as Entry, Descent, and Landing (EDL), orbital operations, and planetary surface exploration.
Maciej Quoos +6 more
wiley +1 more source
Optical Flow Enables Hand Tracking With EyeGlove Low‐Cost Cameras in Confined Environments
A cost‐effective (<£150) hand‐wearable stereo vision system, EyeGlove, is proposed to support visual inspection in confined environments. The system integrates disjointed low‐cost cameras to enable dexterous camera manipulation and wearable display unit for real‐time interaction.
Erhui Sun +3 more
wiley +1 more source
Spatial Side Information Reconstruction Algorithm Based on Image Registration of DMVC System
:This paper proposed a novel method based on the inherent epipolar geometry relationship between different views to generate the spatial side information of distributed multi-view video coding system.
Yue Hong +3 more
doaj

