Using Deep Learning for Automatic Water Stage Measurements

Image-based gauging stations can allow for significant densification of monitoring networks of river water stages. However, thus far, most camera gauges do not provide the robustness of accurate measurements due to the varying appearance of water in the stream throughout the year. We introduce an approach that allows for automatic and reliable water stage measurement combining deep learning and photogrammetric techniques. First, a convolutional neural network (CNN), a class of deep learning, is applied to the segmentation (i.e., pixel classification) of water in images. The CNNs SegNet and fully convolutional network (FCN) are associated with a transfer learning strategy to segment water on images acquired by a Raspberry Pi camera. Errors of water segmentation with the two CNNs are lower than 3%. Second, the image information is transformed into metric water stage values by intersecting the extracted water contour, generated using the segmentation results, with a 3D model reconstructed with structure-from-motion (SfM) photogrammetry. The highest correlations between a reference gauge and the image-based approaches reached 0.93, and average deviations were lower than 4 cm. Our approach allows for the densification of river monitoring networks based on camera gauges, providing accurate water stage measurements.

Automated summary

This study introduces an automatic water stage measurement method combining deep learning and photogrammetric techniques, providing accurate water stage measurements. The method first segments water in images using convolutional neural networks and then transforms image information into metric water stage values by intersecting with a 3D model reconstructed with structure-from-motion photogrammetry. Experimental results show that the method achieves a correlation of 0.93 with reference gauges and average deviations lower than 4 cm.