Hand Segmentation for Augmented Reality System

Lu, Yan; Zhao, Zhimin; Zhou, Yiqi; Liu, Jie

doi:10.1109/dmamh.2007.39

Cited by 8 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wearable augmented reality devices that meet the requirements of complex external field conditions include augmented reality glasses, portable computing terminals and data exchange accessories [5]. The underlying hardware architecture of augmented reality smart glasses needs to include various sensors such as IMU, RGB, fisheye and voice, which are required for system recognition.…”

Section: Overall Hardware Architecture Of the Systemmentioning

confidence: 99%

Research on Operation Training of Large Vehicle Based on Augmented Reality Technology

Wu¹,

An²,

Sun³

et al. 2023

Atlantis Highlights in Computer Sciences

View full text Add to dashboard Cite

With the continuous development of new technologies such as virtual reality, augmented reality and mixed reality, its application in the field of large vehicle operation training is becoming more and more extensive. Based on the practice of smoking vehicle operation and training, this paper designs an intelligent interactive training system based on the integration of artificial intelligence technology and augmented reality technology, and researches and demonstrates the key technologies of its implementation. It realizes the superposition and interaction of virtual equipment, such as virtual animation and model, and real installation and real scene, provides a good virtual interactive experience of augmented reality, meets the training needs under complex conditions in the field, and provides technical support for the improvement of training quality and benefit.

show abstract

Section: Overall Hardware Architecture Of the Systemmentioning

confidence: 99%

Research on Operation Training of Large Vehicle Based on Augmented Reality Technology

Wu¹,

An²,

Sun³

et al. 2023

Atlantis Highlights in Computer Sciences

View full text Add to dashboard Cite

show abstract

“…In particular, first-person vision [23], which captures interactions from the user's point of view by utilizing body-worn cameras, is gaining interest. Analyzing firstperson videos offers the opportunity for assisting in people's daily life and is useful in various applications, such as assistive technology [26], augmented reality [63], visual lifelogging [6], and human-robot interaction [59].…”

Section: Introductionmentioning

confidence: 99%

Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation

et al. 2021

View full text Add to dashboard Cite

Hand segmentation is a crucial task in first-person vision. Since first-person images exhibit strong bias in appearance among different environments, adapting a pre-trained segmentation model to a new domain is required in hand segmentation. Here, we focus on appearance gaps for hand regions and backgrounds separately. We propose (i) foreground-aware image stylization and (ii) consensus pseudolabeling for domain adaptation of hand segmentation. We stylize source images independently for the foreground and background using target images as style. To resolve the domain shift that the stylization has not addressed, we apply careful pseudo-labeling by taking a consensus between the models trained on the source and stylized source images. We validated our method on domain adaptation of hand segmentation from real and simulation images. Our method achieved state-of-the-art performance in both settings. We also demonstrated promising results in challenging multi-target domain adaptation and domain generalization settings.

show abstract

“…But it has not been applied in the AR environment. In paper [4], the problems on segmentation of hand models in AR environment have been researched. Some interactive AR workbenches have been realized in paper [5].…”

Section: Introductionmentioning

confidence: 99%

A Virtual and Real HCI System Based on Artificial Immune System

Chen

Yao

2008

2008 Second International Conference on Genetic and Evolutionary Computing

View full text Add to dashboard Cite

This paper researches and implements a virtual and real moving objects interaction system in augmented reality (AR) environment based on artificial immune system. A custom artificial immune algorithm is applied in this paper in order to solve the collision detection problems with virtual and real objects. System mainly realized a fast collision detection algorithm to detect the process of actual moving hands and virtual objects, collision. System implements mainly processes as follows: The segmentation of hand images and identification of gestures; the process of transformation coordinate system; rough collision detection process; accurate collision detection; the reactive moving images response. The design of immune algorithm are described and implemented as follows: The identification of antigens aims at solving problems in data input; the initial generation of antibodies; the measurement of antibodies; the selection of concentration; the generation of memory cells; the promotion and suppressor of the antibodies.

show abstract

Hand Segmentation for Augmented Reality System

Cited by 8 publications

References 11 publications

Research on Operation Training of Large Vehicle Based on Augmented Reality Technology

Research on Operation Training of Large Vehicle Based on Augmented Reality Technology

Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation

A Virtual and Real HCI System Based on Artificial Immune System

Contact Info

Product

Resources

About