arXiv subjects

Zhenzhong Hu

Publications and source records attributed to Zhenzhong Hu.

3 recordsLinked to original sources

arXiv2024

A Multi-Server Information-Sharing Environment for Cross-Party Collaboration on A Private Cloud

Interoperability remains the key problem in multi-discipline collaboration based on building information modeling (BIM). Although various methods have been proposed to solve the technical issues of interoperability, such as data sharing and data consistency; organizational issues, including data ownership and data privacy, remain unresolved to date. These organizational issues prevent different stakeholders from sharing their data due to concerns regarding losing control of the data. This study proposes a multi-server information-sharing approach on a private cloud after analyzing the requirements for cross-party collaboration to address the aforementioned issues and prepare for massive data handling in the near future. This approach adopts a global controller to track the location, ownership and privacy of the data, which are stored in different servers that are controlled by different parties. Furthermore, data consistency conventions, parallel sub-model extraction, and sub-model integration with model verification are investigated in depth to support information sharing in a distributed environment and to maintain data consistency. Thus, with this approach, the ownership and privacy of the data can be controlled by its owner while still enabling certain required data to be shared with other parties. Application of the multi-server approach for information interoperability and cross-party collaboration is illustrated using a real construction project of an airport terminal. Validation shows that the proposed approach is feasible for maintaining the ownership and privacy of the data while supporting cross-party data sharing and collaboration at the same time, thus avoiding possible legal problems regarding data copyrights or other legal issues.

cs.CR↗

arXiv2024

Fine-tuning vision foundation model for crack segmentation in civil infrastructures

Large-scale foundation models have become the mainstream deep learning method, while in civil engineering, the scale of AI models is strictly limited. In this work, a vision foundation model is introduced for crack segmentation. Two parameter-efficient fine-tuning methods, adapter and low-rank adaptation, are adopted to fine-tune the foundation model in semantic segmentation: the Segment Anything Model (SAM). The fine-tuned CrackSAM shows excellent performance on different scenes and materials. To test the zero-shot performance of the proposed method, two unique datasets related to road and exterior wall cracks are collected, annotated and open-sourced, for a total of 810 images. Comparative experiments are conducted with twelve mature semantic segmentation models. On datasets with artificial noise and previously unseen datasets, the performance of CrackSAM far exceeds that of all state-of-the-art models. CrackSAM exhibits remarkable superiority, particularly under challenging conditions such as dim lighting, shadows, road markings, construction joints, and other interference factors. These cross-scenario results demonstrate the outstanding zero-shot capability of foundation models and provide new ideas for developing vision models in civil engineering.

cs.CV↗

arXiv2018

Non-Invasive Imaging Method of Microwave Near Field Based on Solid State Quantum Sensing

In this paper, we propose a non-invasive imaging method of microwave near field using a diamond containing nitrogen-vacancy centers. We applied synchronous pulsed sequence combined with charge coupled device camera to measure the amplitude of the microwave magnetic field. A full reconstruction formulation of the local field vector, including the amplitude and phase, is developed by measuring both left and right circular polarizations along the four nitrogen-vacancy axes. Compared to the raster scanning approach, the two dimensional imaging method is promising for application to circuit failure analysis. A diamond film with micrometer thinness enables high-resolution near field imaging. The proposed method is expected to have applications in monolithic-microwave-integrated circuit chip local diagnosis, antenna characterization, and field mode imaging of microwave cavities and waveguides.

physics.ins-det↗