Abstract: Objectives: Flood disaster is a very destructive natural disaster. The main reasons for its generation include heavy rainfall, storm surge and dam break. When flood disaster occurs in populated areas such as cities and towns, the flood will directly threaten the safety of life and property of residents. Also it will cause paralysis of land and underground transportation, interruption of water and electricity transportation. In the process of flood rescue, quickly and accurately identification of flooded roads is conducive to planning appropriate personnel transfer and material transportation routes, and reducing subsequent losses caused by floods. Aiming at the problem that roads in the flood disaster scenario cannot be automatically and correctly identified, this paper proposes an end-to-end flooded road detection method based on deep learning. Methods: The proposed method uses a three-branch encoder-decoder structure and uses strip convolution, in which the efficient extraction of linear features is realized. And the coordination dual attention mechanism can effectively guide the network, and realize the identification of road areas. The method in this paper can effectively use the historical optical remote sensing images before the disaster and the real-time optical remote、sensing during the disaster. The image is used to detect the flooded and non-flooded roads in the disaster-stricken area, and a comparative experiment is carried out on the self-built dataset. Results: The proposed network's precison and recall rate are 83.81% and 66.68% on pre-disaster road, 79.66% and 60.74% on post-disaster road, 78.00% and 66.14% on affected road. Conclusions: The results show that the proposed method has achieved the goal of automatically identifying the flooded roads in the flood-stricken area. The ability of detecting flooded roads and nonflooded roads can provide strong support for flood disaster rescue and reduce life safety and property losses caused by flood disasters.