从遥感影像上自动解译铁路设计控制要素是实现“一键成图”的关键,但深度学习遥感影像智能解译需要大量标注样本。依据铁路线路设计原则,提出一种多源遥感数据的设计控制要素智能解译样本库构建方法。首先,基于数字正射影像图(Digital O...从遥感影像上自动解译铁路设计控制要素是实现“一键成图”的关键,但深度学习遥感影像智能解译需要大量标注样本。依据铁路线路设计原则,提出一种多源遥感数据的设计控制要素智能解译样本库构建方法。首先,基于数字正射影像图(Digital Orthophoto Map,DOM)、数字线划地图(Digital Line Graphic,DLG)和激光雷达(Light Detection and Ranging,Lidar)点云多源数据自动生成初始样本;其次,基于增量主动学习迭代方法对初始样本进行优化,达到高质量、全面覆盖铁路沿线的目的;然后,以长赣铁路为例,构建以铁路沿线周边房屋、道路、水体和植被四类铁路线路设计控制要素为重点的高分辨率智能解译样本数据库——铁路线路设计控制要素智能解译样本库(Wuhan University Sample Database of Control Elements of Railway Route Design,WHU-RRDSD),其地面分辨率为0.1 m,样本总数超过20万张;最后,为验证样本库的可用性,分别从定性评价、定量评价以及其他场景应用案例三方面进行详细验证,结果表明,基于房屋、道路、水体和植被四类样本库的IoU评价指标分别为84.43%、82.38%、90.19%、90.28%,表现出优异的解译效果;基于WHU-RRDSD训练得到的智能模型迁移至宜涪高铁场景中房屋、道路、水体和植被要素的解译,验证样本库在其他场景的可用性;简要介绍基于WHU-RRDSD样本库进行的高分辨率遥感图像弱监督建筑提取和高分辨率遥感图像地物分类两个应用案例,进一步验证本文方法所构建样本库可用性。展开更多
The embankment and bridge are the basic forms of railway lines.To date,no reports have addressed the optimal form to adopt when passing through sandy areas.Therefore,models of railway embankment and bridge were create...The embankment and bridge are the basic forms of railway lines.To date,no reports have addressed the optimal form to adopt when passing through sandy areas.Therefore,models of railway embankment and bridge were created,and wind tunnel experiments were conducted to compare the differences in wind speed,flow field,sand transport rate,and other wind–sand environmental effects of railway embankment and bridge.Results show that wind speed reduction areas in the upwind and downwind directions were observed for the railway embankment and bridge.In these areas,the extent and degree of wind speed reduction on the embankment were greater than those on the bridge.At the top of the embankment,especially on the windward slope shoulder,an obvious area of wind speed increase was observed.Similarly,a distinct area of wind speed increase was found between the top of the windward side slope shoulder and 3H downwind of the bridge.Within these regions,the range of wind speed increase on the embankment was smaller than that on the bridge,but the degree of increase was greater than that on the bridge.The range of variation in wind speed on the embankment was generally greater than that on the bridge.The wind–sand flow field around the embankment exhibited greater variability than that around the bridge.Moreover,higher wind–sand flow passage rates on the embankment than on the bridge.This study aims to offer recommendations to assist in the route selection,surveying,and design of railways in sandy regions.展开更多
文摘从遥感影像上自动解译铁路设计控制要素是实现“一键成图”的关键,但深度学习遥感影像智能解译需要大量标注样本。依据铁路线路设计原则,提出一种多源遥感数据的设计控制要素智能解译样本库构建方法。首先,基于数字正射影像图(Digital Orthophoto Map,DOM)、数字线划地图(Digital Line Graphic,DLG)和激光雷达(Light Detection and Ranging,Lidar)点云多源数据自动生成初始样本;其次,基于增量主动学习迭代方法对初始样本进行优化,达到高质量、全面覆盖铁路沿线的目的;然后,以长赣铁路为例,构建以铁路沿线周边房屋、道路、水体和植被四类铁路线路设计控制要素为重点的高分辨率智能解译样本数据库——铁路线路设计控制要素智能解译样本库(Wuhan University Sample Database of Control Elements of Railway Route Design,WHU-RRDSD),其地面分辨率为0.1 m,样本总数超过20万张;最后,为验证样本库的可用性,分别从定性评价、定量评价以及其他场景应用案例三方面进行详细验证,结果表明,基于房屋、道路、水体和植被四类样本库的IoU评价指标分别为84.43%、82.38%、90.19%、90.28%,表现出优异的解译效果;基于WHU-RRDSD训练得到的智能模型迁移至宜涪高铁场景中房屋、道路、水体和植被要素的解译,验证样本库在其他场景的可用性;简要介绍基于WHU-RRDSD样本库进行的高分辨率遥感图像弱监督建筑提取和高分辨率遥感图像地物分类两个应用案例,进一步验证本文方法所构建样本库可用性。
基金supported by the National Natural Science Foundation of China(Grant Nos.42077448 and 42477505)the Western Young Scholars project of the Chinese Academy of Sciences of China(Grant No.xbzglzb2022024)+2 种基金the Natural Science Foundation of Gansu Province for Distinguished Young Scholars(Grant No.22JR5RA049)the Ordos Science and Technology Plan(Grant No.2021EEDSCXQDFZ013)the Longyuan Youth Talent Project of Gansu Province(Grant No.E339020101)。
文摘The embankment and bridge are the basic forms of railway lines.To date,no reports have addressed the optimal form to adopt when passing through sandy areas.Therefore,models of railway embankment and bridge were created,and wind tunnel experiments were conducted to compare the differences in wind speed,flow field,sand transport rate,and other wind–sand environmental effects of railway embankment and bridge.Results show that wind speed reduction areas in the upwind and downwind directions were observed for the railway embankment and bridge.In these areas,the extent and degree of wind speed reduction on the embankment were greater than those on the bridge.At the top of the embankment,especially on the windward slope shoulder,an obvious area of wind speed increase was observed.Similarly,a distinct area of wind speed increase was found between the top of the windward side slope shoulder and 3H downwind of the bridge.Within these regions,the range of wind speed increase on the embankment was smaller than that on the bridge,but the degree of increase was greater than that on the bridge.The range of variation in wind speed on the embankment was generally greater than that on the bridge.The wind–sand flow field around the embankment exhibited greater variability than that around the bridge.Moreover,higher wind–sand flow passage rates on the embankment than on the bridge.This study aims to offer recommendations to assist in the route selection,surveying,and design of railways in sandy regions.
