Quantify pixel-level detection of dam surface crack using deep learning

An increasing number of detection methods based on computer vision are applied to detect cracks in water conservancy infrastructure. However, most studies directly use existing feature extraction networks to extract cracks information, which are proposed for open-source datasets. As the cracks distribution and pixel features are different from these data, the extracted cracks information is incomplete. In this paper, a deep learning-based network for dam surface crack detection is proposed, which mainly addresses the semantic segmentation of cracks on the dam surface. Particularly, we design a shallow encoding network to extract features of crack images based on the statistical analysis of cracks. Further, to enhance the relevance of contextual information, we introduce an attention module into the decoding network. During the training, we use the sum of Cross-Entropy and Dice Loss as the loss function to overcome data imbalance. The quantitative information of cracks is extracted by the imaging principle after using morphological algorithms to extract the morphological features of the predicted result. We built a manual annotation dataset containing 1577 images to verify the effectiveness of the proposed method. This method achieves the state-of-the-art performance on our dataset. Specifically, the precision, recall, IoU, F1_measure, and accuracy achieve 90.81%, 81.54%, 75.23%, 85.93%, 99.76%, respectively. And the quantization error of cracks is less than 4%.

Comprehensive Analysis on the Hydrologic Alteration and Causes of River Runoff in Min River of the Yangtze River, China

The construction of water conservancy projects has changed the hydrological situation of rivers and has an essential impact on the river ecosystem. The influence modes of different factors on runoff alteration are discussed to improve the development and utilization of water resources and promote ecological benefits. The ecological, hydrological index change range method (IHA-RVA) and hydrological alteration degree method were comprehensively used to evaluate Min River's hydrological situation. Based on six budyko hypothesis formulas, the contribution rates of climate change and human activities to runoff change are quantitatively analyzed. The study showed that the runoff of Min River basin showed a significant decreasing trend from 1960 to 2019 and a sudden alteration around 1993; The overall alteration in runoff conditions was 45% moderate, and the overall alteration in precipitation was 37% moderate; Precipitation and potential evapotranspiration also showed a decreasing trend within the same period, but the overall trend was not significant; The contribution of climate alteration to runoff alteration is 30.2%, and the contribution of human activities to runoff alteration is 69.8%, human activities are the dominant factor affecting the alteration of runoff situation in Min River basin.