The timely and proper rehabilitation of damaged roads is essential for road maintenance, and an effective method to detect road surface distress with high efficiency and low cost is urgently needed. Meanwhile, unmanned aerial vehicles (UAVs), with the advantages of high flexibility, low cost, and easy maneuverability, are a new fascinating choice for road condition monitoring. In this paper, road images from UAV oblique photogrammetry are used to reconstruct road three-dimensional (3D) models, from which road pavement distress is automatically detected and the corresponding dimensions are extracted using the developed algorithm. Compared with a field survey, the detection result presents a high precision with an error of around 1 cm in the height dimension for most cases, demonstrating the potential of the proposed method for future engineering practice.

Real and reliable poverty data are critical for regional economic analysis and policy making, especially considering that economic inequality and sustainable development are a broad social concern. This study proposed a multitask learning model combining deep residual neural networks and feature pyramid networks to estimate poverty level by combining features extracted from different data sources, including the nighttime light data, landsat 8 imagery, and spectral index data. We trained the multitask learning model using data from Chongqing (China), and applied the model to estimate the representative economic indicators in Chongqing area. The accuracy of the model is evaluated by calculating Pearson coefficient between the actual economic indicators and the estimated economic indicators, which shows that the model outperforms other models with the Pearson coefficient of up to 0.87 in the annual estimates of economic indicators between 2013 and 2017.Considering that all the data used in the proposed model are publicly available, the methodology in this paper can be used to estimate the economic indicators of long time series in other regions as well.