Sewer Inlet Localization in UAV Image Clouds: Improving Performance with Multiview Detection
AbstractSewer and drainage infrastructure are often not as well catalogued as they should be, considering the immense investment they represent. In this work, we present a fully automatic framework for localizing sewer inlets from image clouds captured from an unmanned aerial vehicle (UAV). The framework exploits the high image overlap of UAV imaging surveys with a multiview approach to improve detection performance. The framework uses a Viola–Jones classifier trained to detect sewer inlets in aerial images with a ground sampling distance of 3–3.5 cm/pixel. The detections are then projected into three-dimensional space where they are clustered and reclassified to discard false positives. The method is evaluated by cross-validating results from an image cloud of 252 UAV images captured over a 0.57-km2 study area with 228 sewer inlets. Compared to an equivalent single-view detector, the multiview approach improves both recall and precision, increasing average precision from 0.65 to 0.73. The source code and case study data are publicly available for reuse. View Full-Text
Externally hosted supplementary file 1
Description: This package contains image data for conducting multi- and single-view sewer inlet detection in UAV image clouds. The package consists in: - individual UAV images, taken with high overlap and corrected for lens distortion - ortho-image of the case study area, clipped to road boundaries. The code for the method can be found at: https://github.com/Eawag-SWW/raycast
Share & Cite This Article
Moy de Vitry, M.; Schindler, K.; Rieckermann, J.; Leitão, J.P. Sewer Inlet Localization in UAV Image Clouds: Improving Performance with Multiview Detection. Remote Sens. 2018, 10, 706.
Moy de Vitry M, Schindler K, Rieckermann J, Leitão JP. Sewer Inlet Localization in UAV Image Clouds: Improving Performance with Multiview Detection. Remote Sensing. 2018; 10(5):706.Chicago/Turabian Style
Moy de Vitry, Matthew; Schindler, Konrad; Rieckermann, Jörg; Leitão, João P. 2018. "Sewer Inlet Localization in UAV Image Clouds: Improving Performance with Multiview Detection." Remote Sens. 10, no. 5: 706.
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.