Introduction
Relation to other fields
Organization of this paper
Review
UAV-driven visual monitoring for construction and civil infrastructure systems
Collecting informative visual data
Autonomy | Sensor | A Priori | Literature |
---|---|---|---|
Autonomous | Camera | None | |
RGB-D | None | (Michael et al. 2014) | |
Semi-autonomous | Camera | None | |
Manual | Camera | Model-driven | |
None |
Visual data analytics
Application | Data Analytics | Integration with BIM | Literature | |
---|---|---|---|---|
Progress monitoring | • BIM-assisted image-based 3D & 4D reconstruction | • Leveraging spatial and temporal information in 4D BIM for monitoring work-in-progress | Y | (Lin, Han, Fukuchi et al. 2015a) |
• Appearance-based reasoning about progress deviations | Y | (Han et al. 2015) | ||
• Image-based 3D & 4D reconstruction | • Measuring mass excavation | Y | (Lin, Han & Golparvar-Fard 2015) | |
• Surface reconstructed • Multi-sensors fusion (GPS, IMU, vision-based panoramic tracker) for data registration in mobile AR system | Y | (Zollmann et al. 2014) | ||
• Surface reconstructed • 4D visualization with multiple levels of detail | Y | (Zollmann et al. 2012) | ||
• Geometry-based change detection. | N | (Kluckner et al. 2011) | ||
Site monitoring | • Integrating aerial images and virtual rendering scenes (3D models) for a WLAN-based AR system | Y | (Wen et al. 2014) | |
Building inspection | • Image-based 3D reconstruction and meshing | N | (Wefelscheid et al. 2011) | |
• 3D mapping of earthquake damages buildings using RGB-D sensors and 3D rotating laser scanners | N | (Michael et al. 2014) | ||
• Image stitching for large façade reconstruction • Edge detection for identifying cracks on building façades | N | (Eschmann 2999) | ||
Building measurement | • Image-based 3D reconstruction using a four-camera system mounted on the UAV • Extracting roof contours | Y | (Xie et al. 2012) | |
Surveying | • Image-based 3D reconstruction • Geo-referencing by using time-stamped GPS Data or PhotoScan software • 3D mapping for monitoring earthmoving | N | (Siebert & Teizer 2014) | |
• Image-based 3D reconstruction • Image segmentation and Orthophoto mapping | N | (Fiorillo et al. 2012) | ||
Safety inspection | • Visual inspection for counting hardhats in images under different environmental conditions | N |
Application | Data Analytics | Literature | |
---|---|---|---|
Structural damage assessment | • Image-based 3D reconstruction • Image segmentation and object classification for damage feature extraction | ||
• Machine learning-based classification of damaged buildings using feature sets obtained from feature extraction and transformation in images | (Ye et al. 2014) | ||
Infrastructure inspection | • Image-based 3D reconstruction • Geometrical feature recognition and classification for planning laser scans | (Oskouie et al. 2015) | |
• Creating comprehensive, high-resolution, semantically rich 3D models of infrastructure | (ARIA (Team 2015)) | ||
Urban monitoring | • Image-based 3D reconstruction for inferring geometric characteristics of buildings • Segmentation using geometric features obtained from 3D point cloud along with radiometric features | (Vetrivel 2999) | |
• 4D image registration for change detection • Orthophoto mapping and multi-primitive image segmentation for object-based decision tree analysis | (Qin 2014) | ||
Road Assessment | • Image-based 3D reconstruction | • Feature extraction through image filtering | (Dobson et al. 2013) |
• Analyzing the size and dimension of road surface distresses • Feature extraction and Orthophoto mapping | (Zhang & Elaksher 2012) | ||
Surveying | • Image-based 3D reconstruction • Surveying post-disaster sites | (Yamamoto et al. 2014) | |
Solar power plant investigations | • Leveraging aerial triangulation using ImageStation Automatic Triangulation (ISAT) software | (Matsuoka et al. 2012) | |
Geo-hazard investigations | • Orthophoto mapping and visual interpretation to inspect geologic hazards along oil and gas pipelines | (Gao et al. 2011) |