An essential component of image analysis is floodsegmentation, which makes it possible to identify flooded areas from aerial or satellite data. Unmanned aerial vehicles (UAVs) are acknowledged as useful instruments t...
详细信息
A breakthrough in building models for image processing came with the discovery that a convolutional neural net-work (CNN) can progressively extract higher-level represen-tations of the image content. Having high-resol...
详细信息
A breakthrough in building models for image processing came with the discovery that a convolutional neural net-work (CNN) can progressively extract higher-level represen-tations of the image content. Having high-resolution images to train CNN models is a key for optimizing the performance of imagesegmentation models. This paper presents a new dataset-called floodimage (floodIMG) database system- that was developed for flood related image processing and segmentation. We developed various Internet of Things Ap-plication Programming Interfaces (IoT API) to gather flood-related images from Twitter, and US federal agencies' web servers, such as the US Geological Survey (USGS) and the De-partment of Transportation (DOT). Overall, > 9200 images of flooding events were collected, preprocessed, and formatted to make the dataset applicable for CNN training. Bounding boxes and polygon primitives were also labeled on each im-age to localize and classify an object in the image. Two use cases of floodIMG are presented in this paper, where the Fast Region-based CNN (R-CNN) algorithm was used to estimate flood severity and depth during recent flooding events in the US. As of > 9200 images, 7,400 were categorized as training sets, whereas > 1,800 images were used for the R-CNN test -ing. Users can access the floodIMG database freely through Kaggle platform to create more accessible, accurate, and op-timized imagesegmentation models. The floodIMG workflow concludes with a visualization of colors and labels per im-age that can serve as a benchmark for floodimage processing and segmentation.(c) 2023 The Author(s). Published by Elsevier Inc. This is an open access article under the CC BY license ( http://***/licenses/by/4.0/ )
暂无评论