Live Semantic 3D Perception for Immersive Augmented Reality

Han, Lei; Zheng, Tian; Zhu, Yinheng; Xu, Lan; Fang, Lü

doi:10.1109/tvcg.2020.2973477

Cited by 52 publications

(16 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Four D uses 4 simple special stages, namely (1) Define the product, which in this case is augmented reality that is ready to be used through a series of tests, then (2) Discover which contains the design of the project being developed, including the framework and wireframes of AR programming; (3) Develop is the process of developing AR products based on the layout of the project framework; and finally the final stage (4). It is a demonstration and dissemination through the Google Playstore and Appstore to see how users respond to the learning concepts that have been developed [12], [20] The 4 steps of Four D in detail can be seen in Figure 3.…”

Section: Sub Instrument Developmentmentioning

confidence: 99%

“…Preliminary research also concluded that MOOC's users who were sampled through programming courses (Preliminary Test and Final Test) provided a statement through a questionnaire that the role of MOOC's integrated with Augmented Reality gave a percentage of about 84% as the main supplement of learning, by using this combination students' understanding increased. inline with what is captured by students through the learning process [10], [12], with a mechanism like this students will be student centered and creative [13], [14].…”

Section: Introductionmentioning

confidence: 96%

See 1 more Smart Citation

Integration of Augmented Reality into MOOC’s in Vocational Education to Support Education 3.0

Nidhom

Putra

Smaragdina

et al. 2022

Int. J. Interact. Mob. Technol.

View full text Add to dashboard Cite

This research discoverable (1) the development of a MOOC (Massive Open Course Online) learning innovation that incorporates Augmented Reality; (2). The use of the concept of AI Injected e-Learning (The Future of Online Education) in Vocational High Schools, which supports the idea of Education 3.0. This study employs a quantitative method to educational research and development, with research sample vocational students. The findings of this research lead to the following conclusions: (1) The efficacy and efficiency of MOOC's learning innovation integrated Augmented Reality was evaluated to be 87.3 percent in a usability test; (2). The application of the concept of Education 3.0 proved to have a significant impact on learning comfort, as evidenced by a questionnaire instrument that revealed that around 85.4% of users believed that online and face-to-face learning provided flexibility in learning, 12.2% felt that learning was normal, and 10% felt that learning was not required; (3). The results of the correct hypothesis are acquired from the quantitative data with a significance value of greater than 0.5, indicating that MOCC's integrated learning utilizing Augmented Reality has resulted in a significant increase in the learning outcomes of vocational high school students by 38 percent

show abstract

Section: Sub Instrument Developmentmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 96%

Integration of Augmented Reality into MOOC’s in Vocational Education to Support Education 3.0

Nidhom

Putra

Smaragdina

et al. 2022

Int. J. Interact. Mob. Technol.

View full text Add to dashboard Cite

show abstract

“…The application of VR technology in the ERP experiment is a revolutionary teaching method. Our study is to apply the VR technology of panoramic image, 3D-reconstruction and other algorithm technologies, adding an immersive experience in the ERP teaching, to create a virtual and interactive ERP learning environment [6]. In the virtual environment, students can truly experience the content and process of professional work [7].…”

Section: Current Status Of Erp Immersive Experimentsmentioning

confidence: 99%

Immersive ERP Experiment Based on 3D-Reconstruction Model of Panoramic Images

Huang

Kong

2022

Modern Management Based on Big Data III

View full text Add to dashboard Cite

This study extends the application field of VR technology, and studies on the physical image problem of inventory management in ERP immersive experiment under VR technology, using the SSD block matching algorithm and the panoramic image in-depth information extraction algorithm to extract the two-dimensional in-depth information in the panoramic images. Then we reconstructed the object in 3D. The results show that the image reconstructed in 3D is clearer, more stereoscopic, and interactive, which solve the problems of low resolution, distortion, and low interaction in ERP virtual teaching environment, while using multimedia and camera roaming to enhance students’ immersive experience, achieve high-precision, real scene, better virtual teaching environment interaction. It can be seen that the immersive ERP experiment based on VR technology is conducive to improving students ’professional ability and docking ability, as well as improving students’ overall cognitive ability and operation ability of the ERP system.

show abstract

“…Semantic segmentation is an important research area, which has been widely and successfully adopted in many mission-critical applications, such as autonomous driving (Siam et al, 2018;Zhang et al, 2020; and augmented reality (Zhang et al, 2019;Huang et al, 2019;Han et al, 2020). As such, its security is of great significance and worth further considerations.…”

Section: Introductionmentioning

confidence: 99%

Hidden Backdoor Attack against Semantic Segmentation Models

Li¹,

Li²,

Lv³

et al. 2021

Preprint

View full text Add to dashboard Cite

Deep neural networks (DNNs) are vulnerable to the backdoor attack, which intends to embed hidden backdoors in DNNs by poisoning training data. The attacked model behaves normally on benign samples, whereas its prediction will be changed to a particular target label if hidden backdoors are activated. So far, backdoor research has mostly been conducted towards classification tasks. In this paper, we reveal that this threat could also happen in semantic segmentation, which may further endanger many mission-critical applications (e.g., autonomous driving). Except for extending the existing attack paradigm to maliciously manipulate the segmentation models from the image-level, we propose a novel attack paradigm, the fine-grained attack, where we treat the target label (i.e., annotation) from the object-level instead of the image-level to achieve more sophisticated manipulation. In the annotation of poisoned samples generated by the fine-grained attack, only pixels of specific objects will be labeled with the attacker-specified target class while others are still with their ground-truth ones. Experiments show that the proposed methods can successfully attack semantic segmentation models by poisoning only a small proportion of training data. Our method not only provides a new perspective for designing novel attacks but also serves as a strong baseline for improving the robustness of semantic segmentation methods. * indicates equal contribution.

show abstract

Live Semantic 3D Perception for Immersive Augmented Reality

Cited by 52 publications

References 38 publications

Integration of Augmented Reality into MOOC’s in Vocational Education to Support Education 3.0

Integration of Augmented Reality into MOOC’s in Vocational Education to Support Education 3.0

Immersive ERP Experiment Based on 3D-Reconstruction Model of Panoramic Images

Hidden Backdoor Attack against Semantic Segmentation Models

Contact Info

Product

Resources

About