Computer vision-based inspection methods show promise for automating post-earthquake building inspections.These methods survey a building with unmanned aerial vehicles and automatically detect damage in the collected ...Computer vision-based inspection methods show promise for automating post-earthquake building inspections.These methods survey a building with unmanned aerial vehicles and automatically detect damage in the collected images.Nevertheless,assessing the damage′s impact on structural safety requires localizing damage to specific building components with known design and function.This paper proposes a BIM-based automated inspection framework to provide context for visual surveys.A deep learning-based semantic segmentation algorithm is trained to automatically identify damage in images.The BIM automatically associates any identified damage with specific building components.Then,components are classified into damage states consistent with component fragility models for integration with a structural analysis.To demonstrate the framework,methods are developed to photorealistically simulate severe structural damage in a synthetic computer graphics environment.A graphics model of a real building in Urbana,Illinois,is generated to test the framework;the model is integrated with a structural analysis to apply earthquake damage in a physically realistic manner.A simulated UAV survey is flown of the graphics model and the framework is applied.The method achieves high accuracy in assigning damage states to visible structural components.This assignment enables integration with a performance-based earthquake assessment to classify building safety.展开更多
Computer vision techniques, in conjunction with acquisition through remote cameras and unmanned aerial vehicles (UAVs), offer promising non-contact solutions to civil infrastructure condition assessment. The ultimate ...Computer vision techniques, in conjunction with acquisition through remote cameras and unmanned aerial vehicles (UAVs), offer promising non-contact solutions to civil infrastructure condition assessment. The ultimate goal of such a system is to automatically and robustly convert the image or video data into actionable information. This paper provides an overview of recent advances in computer vision techniques as they apply to the problem of civil infrastructure condition assessment. In particular, relevant research in the fields of computer vision, machine learning, and structural engineering is presented. The work reviewed is classified into two types: inspection applications and monitoring applications. The inspection applications reviewed include identifying context such as structural components, characterizing local and global visible damage, and detecting changes from a reference image. The monitoring applications discussed include static measurement of strain and displacement, as well as dynamic measurement of displacement for modal analysis. Subsequently, some of the key challenges that persist toward the goal of automated vision-based civil infrastructure and monitoring are presented. The paper concludes with ongoing work aimed at addressing some of these stated challenges.展开更多
Research has been continually growing toward the development of image-based structural health monitoring tools that can leverage deep learning models to automate damage detection in civil infrastructure.However,these ...Research has been continually growing toward the development of image-based structural health monitoring tools that can leverage deep learning models to automate damage detection in civil infrastructure.However,these tools are typically based on RGB images,which work well under ideal lighting conditions,but often have degrading performance in poor and low-light scenes.On the other hand,thermal images,while lacking in crispness of details,do not show the same degradation of performance in changing lighting conditions.The potential to enhance automated damage detection by fusing RGB and thermal images together within a deep learning network has yet to be explored.In this paper,RGB and thermal images are fused in a ResNET-based semantic segmentation model for vision-based inspections.A convolutional neural network is then employed to automatically identify damage defects in concrete.The model uses a thermal and RGB encoder to combine the features detected from both spectrums to improve its performance of the model,and a single decoder to predict the classes.The results suggest that this RGB-thermal fusion network outperforms the RGB-only network in the detection of cracks using the Intersection Over Union(IOU)performance metric.The RGB-thermal fusion model not only detected damage at a higher performance rate,but it also performed much better in differentiating the types of damage.展开更多
基金Financial support for this research was provided in part by the US Army Corps of Engineers through a subaward from the University of California,San Diego,USA。
文摘Computer vision-based inspection methods show promise for automating post-earthquake building inspections.These methods survey a building with unmanned aerial vehicles and automatically detect damage in the collected images.Nevertheless,assessing the damage′s impact on structural safety requires localizing damage to specific building components with known design and function.This paper proposes a BIM-based automated inspection framework to provide context for visual surveys.A deep learning-based semantic segmentation algorithm is trained to automatically identify damage in images.The BIM automatically associates any identified damage with specific building components.Then,components are classified into damage states consistent with component fragility models for integration with a structural analysis.To demonstrate the framework,methods are developed to photorealistically simulate severe structural damage in a synthetic computer graphics environment.A graphics model of a real building in Urbana,Illinois,is generated to test the framework;the model is integrated with a structural analysis to apply earthquake damage in a physically realistic manner.A simulated UAV survey is flown of the graphics model and the framework is applied.The method achieves high accuracy in assigning damage states to visible structural components.This assignment enables integration with a performance-based earthquake assessment to classify building safety.
基金supported in part by funding from the US Army Corps of Engineers under a project entitled ‘‘Cybermodeling: A Digital Surrogate Approach for Optimal Risk-Based Operations and Infrastructure” (W912HZ-17-2-0024)
文摘Computer vision techniques, in conjunction with acquisition through remote cameras and unmanned aerial vehicles (UAVs), offer promising non-contact solutions to civil infrastructure condition assessment. The ultimate goal of such a system is to automatically and robustly convert the image or video data into actionable information. This paper provides an overview of recent advances in computer vision techniques as they apply to the problem of civil infrastructure condition assessment. In particular, relevant research in the fields of computer vision, machine learning, and structural engineering is presented. The work reviewed is classified into two types: inspection applications and monitoring applications. The inspection applications reviewed include identifying context such as structural components, characterizing local and global visible damage, and detecting changes from a reference image. The monitoring applications discussed include static measurement of strain and displacement, as well as dynamic measurement of displacement for modal analysis. Subsequently, some of the key challenges that persist toward the goal of automated vision-based civil infrastructure and monitoring are presented. The paper concludes with ongoing work aimed at addressing some of these stated challenges.
文摘Research has been continually growing toward the development of image-based structural health monitoring tools that can leverage deep learning models to automate damage detection in civil infrastructure.However,these tools are typically based on RGB images,which work well under ideal lighting conditions,but often have degrading performance in poor and low-light scenes.On the other hand,thermal images,while lacking in crispness of details,do not show the same degradation of performance in changing lighting conditions.The potential to enhance automated damage detection by fusing RGB and thermal images together within a deep learning network has yet to be explored.In this paper,RGB and thermal images are fused in a ResNET-based semantic segmentation model for vision-based inspections.A convolutional neural network is then employed to automatically identify damage defects in concrete.The model uses a thermal and RGB encoder to combine the features detected from both spectrums to improve its performance of the model,and a single decoder to predict the classes.The results suggest that this RGB-thermal fusion network outperforms the RGB-only network in the detection of cracks using the Intersection Over Union(IOU)performance metric.The RGB-thermal fusion model not only detected damage at a higher performance rate,but it also performed much better in differentiating the types of damage.