Dongwei Qiu

Sequential renewal of historic courtyard compounds requires coordinated decisions on heritage character conservation, liveability enhancement, and long-term operation and maintenance, while interventions made at one stage can alter subsequent renewal conditions and scheme selection. To address this issue, this paper proposes a multidimensional dynamic simulation method based on state evolution. The method structures renewal into three successive stages and develops a multi-objective dynamic simulation model integrating cultural continuity, structural performance, liveability, and smartness level within a unified evaluation system. Stage-wise state transfer and a state-change penalty capture the continuing effects of earlier interventions, enabling sequential evaluation and scheme selection across stages. The method is applied to a typical courtyard compound in the Fayuan Temple Historic and Cultural District, Beijing, China, where alternative schemes are simulated and comprehensively assessed. The results show that stage-specific scheme selection reflects distinct objective trade-offs and that scheme benefits depend on both current-stage performance and the building state inherited from earlier interventions. Parameter sensitivity analysis indicates that the proposed method exhibits good robustness. The proposed method represents path dependence and interstage relationships and provides practical support for scheme comparison, interstage coordination, and sequential decision-making in the renewal and long-term management of historic courtyard buildings.

High-rise residential buildings have complex structures and long evacuation routes, which further exacerbate the challenges in fire safety. Existing fire evacuation studies rarely pay attention to the influence of smoke diffusion and building layout on the visibility of evacuees and also ignore the modeling of heterogeneous human behavior based on composite factors such as psychological, social, and group dynamics. In this study, we construct a multiagent evacuation model for high-rise building fires that integrates environmental conditions, individual cognition, mobility, and information dissemination. First, we employ agent-based modeling and categorize agents into strong cognitive, weak cognitive, altruistic, and self-oriented types to model their internal drives. Second, we establish a vision loss model based on fire environment perception to depict the vision field of the agents. Furthermore, a mobility evolution model is proposed to represent behavioral decisions and movement speed under the influence of internal drives and vision fields. Finally, an information dissemination model is developed based on the decision-making patterns of the agents in complex scenarios. The evacuation model is ultimately formed through the combination of the mobility evolution model and the information dissemination model. In the experimental design, by simulating the combination ratio of different internal drive agents, different vision conditions, and information dissemination methods, the impact of the proposed model on the fire evacuation performance is analyzed. Results indicate that the internal drive model of the agents significantly impacts evacuation efficiency. The vision loss model and the mobility evolution model are the core elements for agents’ precise environmental perception and accurately feedback. Accurate and immediate coordination between official broadcasts and social dissemination can increase the evacuation efficiency by 13%. Therefore, this model provides a theoretical basis for the design of smoke exhaust in high-rise buildings, the development of intelligent evacuation systems, and the optimization of information dissemination strategies.

The quality and feature representation of crack images are critical for crack detection. Traditional RGB-based methods are intuitive but highly susceptible to environmental interferences. Multispectral imaging enhances detection robustness through spectral stability and band complementarity. Although fusing RGB with infrared or other multispectral bands has been applied to crack detection, existing methods often select fixed bands, lacking an adaptive band selection strategy that generalizes across environments. Additionally, most fusion approaches focus on mitigating environmental interferences under specific crack conditions, leading to poor model transferability and difficulty handling compound interferences such as illumination, temperature, occlusions, and complex backgrounds. Moreover, the superposition of environmental interferences poses greater challenges for feature extraction, boundary enhancement, image stabilization, and resolution improvement in sensitive area fusion. This paper proposes a multispectral fusion approach based on adaptive band selection and multi-level decomposition (MFAM). First, a multi-criteria adaptive band selection algorithm is proposed to extract the most discriminative spectral bands using environment-aware weighting. Second, the dual-scale transform-domain dual-nested decomposition strategy mitigates feature loss and fusion instability caused by poor environmental transferability, establishing hierarchical representation spaces via multi-level frequency band decomposition to precisely integrate multi-scale information. Finally, to mitigate boundary blurring and small-scale feature loss due to low spatial resolution, a spectral-guided enhancement re-fusion method is proposed. By re-fusing the preliminary fused image with the optimal band, edge details are refined, and spatial resolution and clarity enhanced. Experiments on some multispectral crack datasets demonstrate the superior environmental adaptability and image detail enhancement of the proposed MFAM.

This study presents a multimodal data fusion framework for road damage detection and prediction, integrating RGB images, LiDAR point clouds, and GPR (Ground Penetrating Radar) data to enable high-precision detection of surface cracks, potholes, and underground voids, as well as dynamic trend forecasting. By leveraging Deep Mapping 2.0 and the RAFT algorithm, the alignment accuracy between RGB and LiDAR data was significantly improved, reducing registration error to 2.3 mm. Concurrently, the spatial mapping accuracy of GPR data was enhanced to 4.8 mm, ensuring precise multimodal data fusion. A Cross-Attention Transformer combined with a Feature Pyramid Network (FPN) was used for dynamic feature weighting, achieving a crack detection IoU of 97.3% and an AP@0.5 of 93.7% for underground void detection, thereby substantially enhancing the model's performance in detecting complex road damage. Moreover, a trend prediction model integrating ConvLSTM and a spatiotemporal attention mechanism achieved an MAE of 8.7% in a six-month damage trend prediction experiment, reducing prediction error by 34% compared to existing methods, underscoring the model's effectiveness in forecasting damage progression.The experimental results demonstrate that the proposed framework exhibits strong adaptability and stability across diverse road damage detection tasks, particularly excelling in the joint detection of cracks and underground voids with high accuracy. Furthermore, the framework is readily extendable to infrastructure health monitoring applications, such as bridges and tunnels, providing robust technological support for intelligent road maintenance and offering data-driven insights for the long-term optimization and sustainability of urban transportation infrastructure.

In multispectral image fusion, edge distortion, spectral loss, and geometric mismatch seriously affect the fusion accuracy, especially in complex road scenes with shadows or occlusions. Multispectral image fusion aims to preserve surface details and spectral data. In order to solve the problems of edge distortion and spectral loss in image fusion, this paper proposes a multispectral and hyperspectral fusion method based on edge chromatic aberration. Swin Transformer is used for multi-scale feature extraction, and the GRDB module is added to preserve edge details, which improves the clarity and accuracy of diseased edges in road scene fusion images. In addition, saliency weight mapping can identify and highlight key disease areas, ensuring that they are prominent in the fused image.Experiments show that the multispectral image fusion method based on edge color difference significantly improves the performance of road damage analysis on the self-built BUCEA-MS-Road-Damage dataset: the edge IoU in the detection task is increased to 80.1% (+1.3%), and the target detection accuracy is 92.3% (+3.6%); the accuracy and recall of the classification task are increased to 91.3% (+3.0%) and 89.8% (+3.0%) respectively; the Dice coefficient of the segmentation task is 83.3% (+3.0%). In the cross-sensor test, the fusion result is still robust (SSIM=0.93, SAM=2.7°), and the edge color difference index (ECD-Index=6.3) is 25.9% lower than the baseline. This method effectively solves the problems of multi-scale feature extraction and texture distortion of cracks through adaptive color difference correction and spectral consistency constraints, providing high-precision data support for intelligent road maintenance.

To address the issues of uneven feature point distribution, environmental interference, and insufficient real-time performance in UAV image stitching in complex urban environments, this paper proposes an improved ORB algorithm based on Gaussian scale-space optimization and dynamic grid division, combined with a global geometric consistency optimization strategy. First, local adaptive noise filtering and bilateral filtering are applied to enhance image quality. Then, multi-scale feature detection is achieved using a Gaussian scale-space pyramid, and dynamic grid division is employed to balance feature point distribution. Finally, a global energy function, including reprojection error and smoothness constraints, is constructed to iteratively optimize the homography matrix and suppress stitching distortions. Experimental results show that the proposed method achieves high processing speed on low-performance hardware platforms, improves feature point distribution uniformity to 0.89, and achieves stitching accuracy (RMSE) of 3.5 pixels, significantly outperforming ORB and SIFT algorithms, while remaining robust in dynamic occlusion and lighting variation scenarios. This method provides a lightweight and efficient solution for UAV image stitching in urban environments, supporting applications such as urban planning and disaster assessment. Future work will explore lightweight deep learning integration and edge computing acceleration to further improve dynamic scene adaptability.

The accurate recording of high-quality underwater cultural heritage images is crucial for archeological research. However, underwater images frequently suffer from color distortion and reduced clarity, which compromises image quality. Existing underwater image enhancement methods often lead to either over-enhancement or under-enhancement, thereby obscuring artifact details and hindering archeological research. This study proposes a method for enhancing quality and restoring color in underwater cultural heritage images, based on an underwater physical imaging model. First, a different background light estimation algorithm based on brightness segmentation (DBE-BS) is developed to enable adaptive multi-region background light estimation, thereby mitigating the impact of uneven lighting on the image. Next, the depth-saturation fusion transmission (DSFT) map estimation algorithm integrates depth information with the inverse saturation map, improving transmission map accuracy. Finally, the Depth-integrated Color Compensation Model (DICC) is introduced to optimize color correction using image depth data, enhancing the image’s visual quality.

Environmental changes and ground subsidence along railway lines are serious concerns during high-speed railway operations. It is worth noting that AutoRegressive Integrated Moving Average (ARMA), Long Short-Term Memory (LSTM), and other prediction methods may present limitations when applied to predict InSAR time series results. To address this issue, this study proposes a prediction method that decomposes the nonlinear settlement time series of feature points obtained through InSAR technology using Ensemble Empirical Mode Decomposition (EEMD). Subsequently, multiple Intrinsic Mode Functions (IMFs) are generated, and each IMF is individually predicted using the Prophet forecasting model. Finally, we employ an equal-weight superimposition method to combine the results, resulting in the prediction of the InSAR settlement time series. The predicted values of each component are subsequently weighted equally and combined to derive the final prediction outcome. This paper selects InSAR monitoring data along a high-speed railway in inland China and uses the proposed method and ARMA and Prophet models to carry out comparative experiments. The experimental results show that compared with the ARMA and Prophet models, the method in this paper improves the root mean square error by 58.01% and 32.3%, and increases the mean absolute error by 62.69% and 33.78%, respectively. The predicted settlement values generated by our method exhibit better agreement with the actual InSAR monitoring values.