Chongsheng Cheng

High-fidelity 3D reconstruction of bridge structures is crucial for creating accurate bridge digital twins, which serve as virtual representations of physical infrastructure for structural health monitoring, deformation analysis, and maintenance decision support. However, in practical field environments, data acquisition is often limited to sparse-view images due to safety, accessibility, and cost constraints, posing significant challenges to conventional reconstruction methods. To address this issue, we propose a vision-guided Gaussian splatting framework with confidence-driven geometric optimization for robust sparse-view 3D reconstruction tailored for bridge digital twin development. Specifically, our method first extracts structural geometric priors from pre-trained vision foundation models to enhance the perception of key structural features under limited viewpoints. We then introduce a confidence-guided Gaussian component selection and uncertainty sampling strategy to retain reliable regions while adaptively addressing uncertain areas, thereby improving geometric fidelity essential for engineering assessment. To further enforce geometric consistency and mitigate overfitting, we incorporate both depth-aware regularization and pseudo-view constraints. Experimental results on the LLFF benchmark and a real-world UAV bridge dataset demonstrate that our method outperforms state-of-the-art techniques in reconstruction accuracy and structural integrity metrics, providing a robust and practical solution for engineering applications such as intelligent bridge inspection and digital twin-based infrastructure monitoring.

Timely and accurate feedback on the segment installation pose during long-span arch bridge rib assembly is essential. Existing pose monitoring methods rely on visual observation with total-station point measurements, which are inefficient and prone to communication lag under complex site conditions. This study proposes a machine-vision-based real-time monitoring method to estimate the relative spatial pose of arch-bridge segments and to support assembly guidance during construction. The proposed approach features: (1) an enhanced recognition and detection pipeline for accurate identification and localization of small target markers in large-scale scenes; and (2) a monocular six-degree-of-freedom relative pose monitoring method that can continuously compute relative translations and rotations between segments during hoisting and docking. The method is validated through indoor and outdoor experiments and further demonstrated in a field deployment during segment assembly at a real bridge project, confirming its practicality for real-time dynamic construction monitoring.

Concrete, known for its high strength, durability, and flexibility, is a core material in construction. However, defects such as voids and honeycombing often occur due to improper pouring or vibration, weakening the concrete’s strength and affecting its long-term performance. These defects typically require costly repairs. Therefore, timely identification and repair of such early defects is crucial for improving construction quality. This paper proposes a method for non-destructive detection of honeycomb defects in concrete using infrared thermography (IR) during the hydration stage. By analyzing the temperature differences between defect and non-defect areas based on the temperature distribution generated during hydration, defects can be detected. Furthermore, the study uses the COMSOL finite element model to explore the relationship between defect size, ambient temperature, formwork thickness, and thermal contrast. The results show that IR technology can effectively and reliably detect honeycomb defects, especially during the hydration phase. As a convenient and feasible non-destructive testing method, IR technology has significant potential for application and development in concrete defect detection.

Debonding in concrete-filled steel tubes (CFSTs) is a common defect that often occurs during the construction phase of CFST structures, significantly reducing their load-bearing capacity. Current methods for detecting debonding in CFSTs using infrared thermography primarily rely on heat excitation. However, applying this method during the exothermic hydration phase presents considerable challenges. This paper proposes the innovative use of spray cooling as an excitation method during the exothermic hydration phase, providing quantitative insights into the heat conduction dynamics on steel plates for infrared debonding detection in CFSTs. The effects of atomization level, excitation distance, excitation duration, and water temperature in the tank on infrared debonding detection performance were examined. The timing of the maximum temperature difference under cooling excitation was analyzed, and the heat conduction characteristics on the surface of the steel plate during the cooling process were explored. A highly efficient and stable cooling excitation method, suitable for practical engineering detection, is proposed, providing a foundation for quantitative infrared debonding detection in CFSTs. This method does not require additional energy sources, features a simple excitation process, and results in a five-times increase in temperature difference in the debonded region after excitation.

Infrared thermography (IRT) is an effective nondestructive testing method for detecting delamination in concrete structures. However, erroneous data interpretation often diminishes its practical utility due to surface irregularities (e.g., color variations) during inspection. These “noisy conditions” alter the temperature distribution of the structure under solar heating cycles, making it challenging to quantify delamination based on the developed thermal contrast (ΔT). This study experimentally investigates the impact of different surface conditions (bare concrete vs. painted surfaces) on ΔT. Artificial delamination at varying depths was simulated and tested under natural environmental conditions, where the maximum ΔT values for shallow delamination were 9.40 °C (bare concrete), 7.35 °C (yellow paint), and 5.15 °C (white paint), respectively. This study measured and analyzed the absorptivity (bare concrete: 0.652, yellow paint: 0.538, and white paint: 0.369), emissivity, and the temperature difference (δT) between non-delaminated areas and air, revealing their correlation with ΔT variation. Based on the results, three typical scenarios are proposed to correlate δT with delamination detection. These findings contribute to a better understanding of the optimal detection window and present a new approach to quantifying delamination at different time windows. The conclusion also discusses the limitations of this study and future research directions.

Concrete delamination detection using unmanned aerial vehicle (UAV)-mounted infrared cameras has proved effective in recent research. However, most studies used expensive research-grade infrared cameras and proprietary software to acquire images, which is hard to implement in state departments of transportation (DOTs) due to the lack of specialty professionals. Some state DOTs started deploying lightweight UAV-based consumer-grade infrared cameras for delamination detection. Quantitative performance evaluation of such a camera in concrete delamination detection is lacking. To fill this gap, this study intends to conduct a comprehensive assessment of the consumer-grade camera benchmarked against the results of a research-grade camera to see the practicality of using the small and low-cost camera in concrete delamination detection. Data was collected for a slab with mimicked delamination and two in-service bridge decks. For the case of the slab, maximum detectability of 70–72% was achieved. A transient numerical simulation was conducted to provide a supplemental and noise-free dataset to explore detectability accuracy peaks throughout the day. The results of the in-service bridge decks indicated that the consumer-grade infrared camera provided adequate detection of the locations of suspected delamination. Results of both the slab and in-service bridge decks were comparable to those of a research-grade infrared camera.