Research on Teleoperated Virtual Reality Human–Robot Five-Dimensional Collaboration System

Zhang, Qinglei; Liu, Qinghao; Duan, Jianguo; Qin, Jiyun

doi:10.3390/biomimetics8080605

Cited by 2 publications

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Human action recognition technology has been widely used in the fields of bionic robots, medical care, video surveillance, intelligent transportation, and human–robot interaction [ 1 , 2 , 3 , 4 , 5 , 6 , 7 , 8 ]. Skeletons are made up of a variety of different shapes, with complex internal and external structures, which play a role in supporting and protecting the human body.…”

Section: Introductionmentioning

confidence: 99%

Multi-Modal Enhancement Transformer Network for Skeleton-Based Human Interaction Recognition

Hu,

Liu

2024

Biomimetics

View full text Add to dashboard Cite

Skeleton-based human interaction recognition is a challenging task in the field of vision and image processing. Graph Convolutional Networks (GCNs) achieved remarkable performance by modeling the human skeleton as a topology. However, existing GCN-based methods have two problems: (1) Existing frameworks cannot effectively take advantage of the complementary features of different skeletal modalities. There is no information transfer channel between various specific modalities. (2) Limited by the structure of the skeleton topology, it is hard to capture and learn the information about two-person interactions. To solve these problems, inspired by the human visual neural network, we propose a multi-modal enhancement transformer (ME-Former) network for skeleton-based human interaction recognition. ME-Former includes a multi-modal enhancement module (ME) and a context progressive fusion block (CPF). More specifically, each ME module consists of a multi-head cross-modal attention block (MH-CA) and a two-person hypergraph self-attention block (TH-SA), which are responsible for enhancing the skeleton features of a specific modality from other skeletal modalities and modeling spatial dependencies between joints using the specific modality, respectively. In addition, we propose a two-person skeleton topology and a two-person hypergraph representation. The TH-SA block can embed their structural information into the self-attention to better learn two-person interaction. The CPF block is capable of progressively transforming the features of different skeletal modalities from low-level features to higher-order global contexts, making the enhancement process more efficient. Extensive experiments on benchmark NTU-RGB+D 60 and NTU-RGB+D 120 datasets consistently verify the effectiveness of our proposed ME-Former by outperforming state-of-the-art methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Multi-Modal Enhancement Transformer Network for Skeleton-Based Human Interaction Recognition

Hu,

Liu

2024

Biomimetics

View full text Add to dashboard Cite

show abstract

Radiological Crossroads: Navigating the Intersection of Virtual Reality and Digital Radiology through a Comprehensive Narrative Review of Reviews

Lastrucci,

Giansanti

2024

Robotics

View full text Add to dashboard Cite

The integration of Virtual Reality with radiology is the focus of this study. A narrative review has been proposed to delve into emerging themes within the integration of Virtual Reality in radiology by scrutinizing reviews gathered from PubMed and Scopus. The proposed approach was based on a standard narrative checklist and a qualification process. The selection process identified 20 review studies. Integration of Virtual Reality (VR) in radiology offers potential transformative opportunities also integrated with other emerging technologies. In medical education, VR and AR, using 3D images from radiology, can enhance learning, emphasizing the need for standardized integration. In radiology, VR combined with Artificial Intelligence (AI) and Augmented Reality (AR) shows promising prospectives to give a complimentary contribution to diagnosis, treatment planning, and education. Challenges in clinical integration and User Interface design must be addressed. Innovations in medical education, like 3D modeling and AI, has the potential to enable personalized learning, but face standardization challenges. While robotics play a minor role, advancements and potential perspectives are observed in neurosurgery and endovascular systems. Ongoing research and standardization efforts are crucial for maximizing the potential of these integrative technologies in healthcare. In conclusion, the synthesis of these findings underscores the opportunities for advancements in digital radiology and healthcare through the integration of VR. However, challenges exist, and continuous research, coupled with technological refinements, is imperative to unlock the full potential of these integrative approaches in the dynamic and evolving field of medical imaging.

show abstract

Research on Teleoperated Virtual Reality Human–Robot Five-Dimensional Collaboration System

Cited by 2 publications

References 42 publications

Multi-Modal Enhancement Transformer Network for Skeleton-Based Human Interaction Recognition

Multi-Modal Enhancement Transformer Network for Skeleton-Based Human Interaction Recognition

Radiological Crossroads: Navigating the Intersection of Virtual Reality and Digital Radiology through a Comprehensive Narrative Review of Reviews

Contact Info

Product

Resources

About