基于原型网络的泥石流沟谷图像预测  

Prediction of Debris Flow Valley Images Based on Prototypical Network

作　　者：王旭 王保云 韩俊 徐繁树 WANG Xu;WANG Baoyun;HAN Jun;XU Fanshu(School of Mathematics,Yunnan Normal University,Kunming 650500,China;School of Information,Yunnan Normal University,Kunming 650500,China;Key Laboratory of Complex System Modeling and Application for Universities in Yunnan,Kunming 650500,China)

机构地区：[1]云南师范大学数学学院,云南昆明650500 [2]云南师范大学信息学院,云南昆明650500 [3]云南省高校复杂系统建模及应用重点实验室,云南昆明650500

出　　处：《现代信息科技》2022年第11期130-132,共3页Modern Information Technology

基　　金：国家自然科学基金(61966040)。

摘　　要：泥石流灾害发生迅速、破坏力极大,给人类生命财产安全带来了严重的威胁,云南省西北部地区极易发生泥石流灾害。针对泥石流灾害预测问题,文中以云南怒江流域为研究区域,以历史泥石流灾害数据为基础,提取该流域沟谷数字高程模型图,发生泥石流的沟谷图像记为正样本,未发生过泥石流的沟谷图像记为负样本。采用原型网络作为小样本学习框架,Conv4和ResNet12分别作为特征提取网络对沟谷图像进行训练、测试,实现了六分类预测。经实验结果对比,2-way 5-shot条件下、ResNet12作为特征提取网络时表现最佳,预测准确率达到75.36%。Debris flow disasters occur rapidly and are extremely destructive.It poses a serious threat to the safety of human life and property.The northwestern region of Yunnan Province is highly prone to debris flow disasters.Aiming at the problem of debris flow disaster prediction,this paper takes the Nujiang River Basin in Yunnan as the research area,based on the historical debris flow disaster data,extracts the digital elevation model images of the valleys in the basin.The valley images which occurs debris flow are recorded as positive samples,and valley images which no debris flow are recorded as negative samples.The prototype network is used as a small sample learning framework,and Conv4 and ResNet12 are used as feature extraction networks to train and test valley images respectively,and achieve six-class prediction.Compared with the experimental results,under the condition of 2-way 5-shot,ResNet12 performs the best as the feature extraction network,and the prediction accuracy rate reaches 75.36%.

关 键 词：小样本学习 原型网络 泥石流 数字高程模型 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] P407.8[自动化与计算机技术—计算机科学与技术]