Deep Learning for Detection of Pavement Distress using Nonideal Photographic Images

Pavement Distress Detection with Deep Learning Using the Orthoframes Acquired by a Mobile Mapping System

“…The resulting information is used by the Estonian Road Administration via a web application called EyeVi. Compared to our previous work on the same topic [2], several changes were introduced. First of all, Reach-U Ltd. has recently upgraded from the Ladybug 5 360 • Spherical Camera Imaging System to Ladybug 5+, which is equipped with Sony Pregius global shutter CMOS sensors that provide more consistent overall quality of acquired images across a wide range of lighting conditions.…”

“…First of all, Reach-U Ltd. has recently upgraded from the Ladybug 5 360 • Spherical Camera Imaging System to Ladybug 5+, which is equipped with Sony Pregius global shutter CMOS sensors that provide more consistent overall quality of acquired images across a wide range of lighting conditions. Secondly, we decided to focus on individual 4096 × 4096 pixel orthoframes, the building blocks of the orthophotos that we employed in [2] to avoid some side-effects of the assembly process (e.g., inherent blurring of interpolated regions in the orthophotos). Finally, the orthoframes were manually redigitized for the defects by the authors of this paper because the digitization of defects carried out by experienced operators occasionally suffers from spatial inaccuracy and thus does not necessarily meet the demands of machine learning.…”

“…Research by input data and data collection. [2, Image [35][36][37] Radar [38][39][40][41][42][43][44][45][46] 3D images or point clouds [47,48] Acoustic…”

“…The work in [14], on the other hand, used 3900 raw images captured by a NIKON digital camera with a resolution of 3456 × 4608 pixels where the camera took pictures between the ground and the camera with an approximate distance from 80 cm to 100 cm. Similarly, the work in [2,10,13] used custom datasets. In addition, the work in [9,11] used a low cost approach of obtaining images using mobile phones.…”

“…Note also that in the resulting image, the area that was not road surface became much smaller and was most often present on one side of the road only and could be thus typically separated with a single line ( Figure 5). Therefore, the road extraction procedure that was automated in [2] was now delegated to the digitizers (a digitizer in the context of this work refers to a person engaged in digitization of defect information based on the provided orthoframes and initial defect data) who processed the orthoframes as part of the preprocessing step for obtaining more accurate training data for the automatic detector. Out of 33,288 orthoframes, 20,318 that contained defects in the area of interest were algorithmically picked out for further consideration.…”