差分信息引导的三分支洪涝水淹道路检测网络

Differential Information Guided Triple Branch Network for Flooded Road Detection

洪涝灾害是一种极具破坏力的自然灾害,其产生原因主要包括强降水、风暴潮以及水坝溃堤等,当城市、乡镇等居住区域发生洪涝灾害时,洪水会直接威胁到居民的生命财产安全,同时造成陆上及地下交通瘫痪、水电运输中断等。在洪涝灾害的抢险救灾过程中,快速准确地对洪涝淹没道路进行识别,有利于制定合适的人员转运及物资运送路线,减少洪涝带来的后续损失。针对当前洪涝灾害场景下的道路无法实现准确自动化识别的问题,提出了一种基于差分信息引导的洪涝水淹道路检测方法,该方法采用了三支路的编码器-解码器结构,利用条带卷积提取道路特征,协调双注意力机制引导网络学习多时相差分信息,挖掘水淹道路的时相信息。该方法能有效利用灾前的历史光学遥感影像和灾中的实时光学遥感影像对受灾区域内已被水淹和未被水淹的道路进行检测,并在自建数据集上进行对比实验,所提出网络对灾前道路的识别精确率为0.8381,召回率为0.6668,对灾中道路的识别精确率为0.7966,召回率为0.6074,对受灾区域识别精确率为0.7800,召回率为0.6614。结果表明,所提出方法达成了自动化识别洪涝灾区水淹道路的目标,其识别已被水淹道路及未被水淹道路的能力可为洪涝灾害的抢险救援提供有力支持,减小洪涝灾害带来的生命及财产损失。

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,quick and accurate 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 ef‑fectively guide the network,and realize the identification of road areas.The method can effectively utilize the historical optical remote sensing images before the disaster and the real-time optical remote sensing during the disaster.The image is applied 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 experimental results show that the precison and recall rate are 0.8381 and 0.6668 on pre-disaster road,0.7966 and 0.6074 on post-disaster road,0.7800 and 0.6614 on affected road respectively.Conclusions: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 non-flooded roads can provide strong support for flood disaster rescue and reduce losses of life and property caused by flood disasters.