This paper introduces and implements an efficient training method for deep learning–based anomaly area detection in the depth image of a tire. A depth image of 16 bit integer size is used in various fields, such as manufacturing, industry, and medicine. In addition, the advent of the 4th Industrial Revolution and the development of deep learning require deep learning–based problem solving in various fields. Accordingly, various research efforts use deep learning technology to detect errors, such as product defects and diseases, in depth images. However, a depth image expressed in grayscale has limited information, compared with a three-channel image with potential colors, shapes, and brightness. In addition, in the case of tires, despite the same defect, they often have different sizes and shapes, making it difficult to train deep learning. Therefore, in this paper, the four-step process of (1) image input, (2) highlight image generation, (3) image stacking, and (4) image training is applied to a deep learning segmentation model that can detect atypical defect data. Defect detection aims to detect vent spews that occur during tire manufacturing. We compare the training results of applying the process proposed in this paper and the general training result for experiment and evaluation. For evaluation, we use intersection of union (IoU), which compares the pixel area where the actual error is located in the depth image and the pixel area of the error inferred by the deep learning network. The results of the experiment confirmed that the proposed methodology improved the mean IoU by more than 7% and the IoU for the vent spew error by more than 10%, compared to the general method. In addition, the time it takes for the mean IoU to remain stable at 60% is reduced by 80%. The experiments and results prove that the methodology proposed in this paper can train efficiently without losing the information of the original depth data.

This paper presents MetaTwin, a collaborative Metaverse platform that supports one-to-one spatiotemporal synchrony between physical and virtual spaces. The users can interact with other users and surrounding IoT devices without being tied to physical spaces. Resource sharing is implemented to allow users to share media, including presentation slides and music. We deploy MetaTwin in two different network environments (i.e., within the US, Korea-US international) and summarize users’ feedback about the experience.

This paper presents MetaTwin, a collaborative platform that enables seamless synchronization between physical and virtual realms for co-existing Extended Reality (XR) experiences. MetaTwin employs a hybrid decentralized server architecture to synchronize user interactions and environments within a shared space, allowing users to collaborate and socialize across physical locations while experiencing the convergence of real and virtual spaces. Integrated IoT devices act as both physical and virtual entities, supporting shared control and enabling resource sharing, such as presentation slides and music. We detail the configuration and deployability of MetaTwin as a solution for XR collaboration. To evaluate performance and feasibility, we compared MetaTwin with an existing XR platform and conducted an ablation study to identify the benefits and limitations of our approach. Additionally, a user study investigates the impact of spatial and temporal synchronization offsets on collaboration quality. Our findings inform the development of operational guidelines for future collaborative XR platforms.