Autonomous image localization for visual inspection of civil infrastructure

Abstract

Low-cost, high-performance vision sensors in conjunction with aerial sensing platforms are providing new possibilities for achieving autonomous visual inspection in civil engineering structures. A large volume of images of a given structure can readily be collected for use in visual inspection, overcoming spatial and temporal limitations associated with human-based inspection. Although researchers have explored several algorithms and techniques for vision-based inspection in recent decades, a major challenge in past implementations lies in dealing with a high volume of images while only a small fraction of them are important for actual inspection. Because processing irrelevant images can generate a significant number of false-positives, automated visual inspection techniques should be used in coordination with methods to localize relevant regions on the images. When combined, automated visual inspection will be able to meet the objectives and quality of human visual inspection. To enable this technology, we develop and validate a novel automated image localization technique to extract regions of interest (ROIs) on each of the images before utilizing vision-based damage detection techniques. ROIs are the portions of an image that contain the physical region of the structure that is targeted for visual interrogation, denoted as the targeted region of interest (TRI). ROIs are computed based on the geometric relationship between the collected images and the TRIs. Analysis of such highly relevant and localized images would enable efficient and reliable visual inspection. We successfully demonstrate the capability of the technique to extract the ROIs using a full-scale highway sign structure in the case where weld connections serve as the TRIs.

Measuring Change Using Quantitative Differencing of Repeat Structure-From-Motion Photogrammetry: The Effect of Storms on Coastal Boulder Deposits

“…UAVs and structure-from-motion (SfM) photogrammetric software have become go-to tools for monitoring hazardous locations such as landslides [6][7][8][9][10][11][12] and subsidence/sinkholes [13][14][15]. These technologies have also been widely adopted in coastal erosion [16][17][18], marine science [19][20][21], both marine and terrestrial ecology [22][23][24][25][26][27], archaeology [28][29][30][31][32][33][34][35], and civil engineering [36][37][38][39][40].…”

Automatic seismic damage identification of reinforced concrete columns from images by a region-based deep convolutional neural network

“…An unsupervised structural damage localization method was proposed using a density peaks‐based fast clustering algorithm . An autonomous image localization method was proposed for visual inspection of civil infrastructure by 3D coordinate transformation and region of interest (ROI) localization . Photogrammetry has been involved in the recent vision‐based damage detection field as a noncontact optical measurement method, which is relatively low‐cost, agile, and provides high spatial resolution and simultaneous measurements.…”

“…15 An autonomous image localization method was proposed for visual inspection of civil infrastructure by 3D coordinate transformation and region of interest (ROI) localization. 16 Photogrammetry has been involved in the recent vision-based damage detection field as a noncontact optical measurement method, which is relatively low-cost, agile, and provides high spatial resolution and simultaneous measurements. A data-driven and unsupervised approach based on low rank and sparse separation was proposed for real-time detection of local structural damage that required no parametric model or prior structural information for calibration.…”

Computer-Aided Approach for Rapid Post-Event Visual Evaluation of a Building Façade

“…These requirements are because the visibility of the crack depends on the viewing angles. Since UAVs do not selectively capture favorable images in an automated manner, a large volume of images needs to be collected and used for visual inspection [ 19 , 21 , 22 , 23 ]. Thus, to enable efficient visual inspection using such a large volume of images, an automated technique should be incorporated to localize the close-view images captured from different viewpoints to the corresponding region on the building facades.…”

“…Also, applying an existing damage detection algorithm to the ROIs may fully automate the inspection process. Such use of highly relevant ROIs greatly reduces false-positive and false-negative damage detection by processing many images captured from various viewpoints for viewing [ 19 , 21 , 22 , 23 ].…”