No abstract

Many municipalities and road authorities seek to implement automated evaluation of road damage. However, they often lack technology, know-how, and funds to afford state-of-theart equipment for data collection and analysis of road damages. Although some countries, like Japan, have developed less expensive and readily available Smartphone-based methods for automatic road condition monitoring, other countries still struggle to find efficient solutions. This work makes the following contributions in this context. Firstly, it assesses usability of the Japanese model for other countries. Secondly, it proposes a large-scale heterogeneous road damage dataset comprising 26620 images collected from multiple countries using smartphones. Thirdly, we propose generalized models capable of detecting and classifying road damages in more than one country. Lastly, we provide recommendations for readers, local agencies, and municipalities of other countries when one other country publishes its data and model for automatic road damage detection and classification. Our dataset is available at (https://github.com/sekilab/RoadDamageDetector/).

The goal of this study was calibration of the ECH₂0 soil moisture sensor EC-5 and the sensor SM200 for selected soils of the Czech Republic. Based on the soil maps of the Czech Republic and various climatic conditions, five humic horizons of different soil types were selected: Stagnic Chernozem Siltic, Haplic Chernozem, Chernozem Arenic, Haplic Luvisol, and Haplic Cambisol. Soil properties (pH_KCl, pH_H2O, exchangeable acidity, cation exchange capacity, hydrolytic acidity, basic cation saturation, sorption complex saturation, oxidable organic carbon content, CaCO₃ content, salinity, sand, silt, and clay content, soil particle density, bulk density) were determined using the standard laboratory techniques. Six ECH₂0 EC-5 sensors permanently installed in six 606 cm³ repacked soil samples of each soil were calibrated. Four calibrated SM200 sensors were inserted into the same soil samples only when measuring sensor signal. Soil water contents were determined gravimetrically. Linear equation was used to find parameters of the calibration equations relating sensor signals or evaluated dielectric constants and soil water contents. The multiple linear analyses showed that the parameters of the calibration equations for the EC-5 depended on the bulk density, fraction of sand particles, and salinity. Parameters a and b of the SM200 depended on the initial soil salinity, sand fraction and CaCO₃ content, and on the sand fraction, respectively. The impact of KBr solute (concentrations of 0.01, 0.05 and 0.1M Br) on calibration equations was studied as well. It was found that ECH₂0 EC-5 sensor measurements were more influenced by KBr solution than SM200 measurements. In the case of the ECH₂0 EC-5 sensor, impact of KBr was lower in soils of higher initial salinity. SM200 measurements were noticeably influenced only when 0.1M Br solution was applied.

No abstract