摘要
高效识别阴影信息是利用阴影和消除阴影的关键前提,有助于城市遥感应用研究的开展,现有关于城市阴影检测多关注在近红外和可见光的多波段合成方面,而对可见光提取阴影的能力检测有待深入。针对这一问题,基于红、绿、蓝(R、G、B)高分卫星影像,结合色彩空间变换和影像多波段运算,研究并提出一种由绿光波段、蓝光波段和亮度分量构建的城市阴影优化指数OUSI(Optimization Urban Shadow Index),从视觉效果及提取精度评估角度进行验证分析。结果表明:OUSI可较完整地提取城市阴影,总体精度达90.46%,高于当前常见的指数法和深度学习阴影检测算法;OUSI受不同土地覆被类型的影响较小,阴影检测结果稳定。与既往基于特征的方法不同,研究构建的阴影指数对原始影像数据仅依赖RGB三波段信息,OUSI指数简洁有效、运算耗时少,进而可以为实现大区域和高精度的城市阴影检测提供切实可行的方案。
Efficient recognition of shadow information is a key prerequisite for utilizing and eliminating shadows,most of the existing studies on urban shadow detection have been attached to the multi-band synthesis of near-infrared and visible light,while the detection ability of shadows extraction from visible light still remains insuffi⁃cient.In this study,based on red,green,and blue(R,G,B)high-resolution satellite images,we used color space transformation and image multi-band operation to constructed an Optimization Urban Shadow Index(OUSI)with green light band,blue light band,and luminance component.The visual effect and accuracy eval⁃uation were also be analyzed.The results showed that a more complete urban shadow can be extracted by OUSI with an overall accuracy of 90.46%,outperforming the current common exponential method and deep learning shadow detection algorithms;the shadow detection results were the most stable as it suffered less from the influ⁃ence of different land cover types.In contrast to the previous feature-based methods,the raw image data of this study only rely on RGB three-band information.The OUSI consumes fewer computing hours and thus provid⁃ing an effective practical solution to achieve urban shadow detection in large areas.
作者
唐晔
刘小燕
崔耀平
史志方
邓亮
陈准
TANG Ye;CUI Yaoping;LIU Xiaoyan;SHI Zhifang;CHEN Zhun;DENG Liang(Key Laboratory of Geospatial Technology for the Middle and Lower Yellow River Regions(Henan University),Ministry of Education,Kaifeng 475004,China;School of Geography and Environmental Science,Henan University,Kaifeng 475004,China;School of Philosophy and Public Administration Henan University,Kaifeng 475004,China)
出处
《遥感技术与应用》
CSCD
北大核心
2023年第4期945-955,共11页
Remote Sensing Technology and Application
基金
国家自然科学基金项目(42071415)
河南省自然科学基金优秀青年科学基金项目(202300410049)
信阳生态研究院开放基金(2023XYMS014)
河南省研究生教育改革与质量提升工程项目(YJS2023JC22)。
关键词
阴影指数
深度学习
色彩空间
高分影像
可见光
Shadow index
Deep learning
Color space
High-resolution image
Visible light
