The recent large-scale fire incidents on construction sites in South Korea have highlighted the need for computer vision technology to detect fire risks before an actual occurrence of fire. This study developed a proactive fire risk detection system by detecting the coexistence of an ignition source (sparks) and a combustible material (urethane foam or Styrofoam) using object detection on images from a surveillance camera. Statistical analysis was carried out on fire incidences on construction sites in South Korea to provide insight into the cause of the large-scale fire incidents. Labeling approaches were discussed to improve the performance of the object detectors for sparks and urethane foams. Detecting ignition sources and combustible materials at a distance was discussed in order to improve the performance for long-distance objects. Two candidate deep learning models, Yolov5 and EfficientDet, were compared in their performance. It was found that Yolov5 showed slightly higher mAP performances: Yolov5 models showed mAPs from 87% to 90% and EfficientDet models showed mAPs from 82% to 87%, depending on the complexity of the model. However, Yolov5 showed distinctive advantages over EfficientDet in terms of easiness and speed of learning.

For the last ten years, the number of cases of large‐scale fires which occur on bridges, tunnels, and underpasses has increased. Such fires cause primary and secondary damage, including loss of human life, traffic congestion, and extensive financial damage. Therefore, a risk grade model and effective response plan need to be established for such cases in order to minimize the social and economic costs of bridge fires. In this study, the hazard factors contributing to bridge fires were selected to apply a risk grade model. A total of 144 bridge fire simulations were performed to calculate a surface temperature based on time by using Fire Dynamics Simulation (FDS). A risk grade in accordance with the degree of surface damage state caused by temperature of bridges was presented, and the mobilization time criteria for fire suppression were proposed. The surface temperatures based on time can be classified according to the vertical clearance and mobilization time criteria for fire suppression. Through the classified maximum surface temperatures based on time for bridges, the risk grade can be estimated according to the degree of surface damage state caused by temperature. In order to evaluate the applicability of the established risk grade model to the actual bridge, the arrival time taken from the bridge to the fire station was calculated through a Geographic Information System (GIS) network analysis, and the grades for actual bridge cases were assessed. The purpose of this bridge fire risk grade model is to establish a disaster prevention strategy based on risk grades and to minimize the subsequent social damage by determining a priori the disaster scale.

Automated crack segmentation is a prerequisite for scalable, objective condition assessment of civil infrastructure, yet conventional methods rely exclusively on visual features and remain vulnerable to low‐contrast surfaces, shadows, and background clutter encountered in routine inspections. This study introduces a text‐guided vision–language segmentation framework in which short, inspection‐style descriptions of crack type and surface condition, the kind of contextual knowledge inspectors already record, are used to condition pixel‐level prediction. Feature‐wise linear modulation (FiLM) aligns multiscale visual features with these linguistic descriptors, and an adaptive multiscale refinement module (AMRF) preserves crack boundary continuity under challenging surface conditions. To support this line of research, a multimodal dataset is contributed by annotating an existing crack mask repository with descriptive textual labels. On a unified benchmark combining seven public crack datasets, the proposed method achieves an F1 score of 79.37% and an intersection over union (IoU) of 65.80% when inspection descriptions are available, the highest among the convolutional, transformer, and foundation‐model baselines considered. It also shows a favorable precision–recall balance, faster training convergence, and qualitatively sharper feature activations in low‐contrast regions. All validation is limited to these seven public datasets; agency‐collected images and physical crack measurements were not evaluated. Beyond benchmark accuracy, the paper describes how the resulting masks can be converted into crack width, length, and density, which are inputs to established condition‐rating and maintenance‐prioritization workflows, and discusses deployment of the framework as an offline analysis module within existing inspection programs.

Accurate quantification of surface crack width is essential for maintaining civil infrastructure, yet conventional visual inspection is subjective and inconsistent. This study presents VisionCrack, a smartphone‐based system for low‐cost image‐based crack width measurement using a 1D barcode. By analysing five predefined barcode bar thicknesses (T1–T5), VisionCrack estimates an adaptive scale (mm/pixel) using linear regression. Rather than relying on a single fixed reference, the method uses multiple barcode thickness references within each image to compensate for measurement bias. In experiments against crack width gauges, VisionCrack achieved a mean absolute error (MAE) of 0.0105 mm. Compared with a single‐reference fixed‐scale baseline representing prior marker‐based approaches, the proposed method showed a lower error (0.0105 mm vs 0.1183 mm). These results demonstrate the calibration accuracy and practical potential of the proposed method under controlled image‐capture conditions.