摘要
遥感图像处理软件的性能直接制约了相关工作者开展教学和科研活动的效果和效率。该文以复杂矿山场景土地利用分类为任务对象,对比研究了PIE,ENVI,ERDAS和eCognition等主流遥感软件以及分析了自研的深度学习算法的性能。结果表明:(1)ENVI在常规方法面向像元分类时表现出最高的总体精度(overall accuracy,OA)和Kappa系数,但分类效率最低,相比之下,ERDAS在兼顾较高精度的条件下运行效率最高;(2)eCognition在常规方法面向对象分类时取得了最优的OA和Kappa,也具备较高的运行效率;(3)深度卷积神经网络算法相较于常规方法的分类结果具有明显的精度优势。文章定量地揭示了不同软件在不同策略方法上的性能表现,能够为相关工作者选择合适的图像处理软件、提升教学效果和科研效率提供科学依据。
The performance of remote sensing image processing software directly influences the effectiveness and efficiency of teaching and research activities conducted by related workers.Focusing on land use classification in a complex mine scene,this study comparatively investigated the performance of popular remote sensing software including Pixel Information Expert(PIE),Environment for Visualizing Images(ENVI),ERDAS IMAGINE(ERDAS),and eCognition Developer(eCognition),and the self-developed deep learning algorithm.The results show that ENVI yielded the highest overall accuracy(OA)and Kappa coefficient but the lowest classification efficiency in conventional pixel-oriented classification.In contrast,ERDAS exhibited the highest operational efficiency while maintaining relatively high accuracy.eCognition achieved the optimal OA and Kappa coefficient and relatively high operational efficiency in conventional object-oriented classification.The deep convolutional neural network algorithm demonstrated superior accuracy over the classification results of conventional methods.Overall,this study quantitatively revealed the performance of various software on different strategies and methods,providing a scientific basis for related workers to choose appropriate image processing software and improve teaching effect and research efficiency.
作者
张成业
李梦圆
邢江河
邱宇航
ZHANG Chengye;LI Mengyuan;XING Jianghe;QIU Yuhang(College of Geoscience and Surveying Engineering,China University of Mining and Technology(Beijing),Beijing 100083,China;State Key Laboratory of Coal Fine Exploration and Intelligent Development,China University of Mining and Technology(Beijing),Beijing 100083,China)
出处
《自然资源遥感》
北大核心
2025年第3期9-16,共8页
Remote Sensing for Natural Resources
基金
国家自然科学基金项目“露天煤矿区植被扰动过程遥感提取方法与全国分区时空规律挖掘”(编号:42371347)
教育部产学合作协同育人项目“面向PIE首套实践教材的遥感数字图像处理体验式课程建设与共享”(编号:202101162010)共同资助。
关键词
遥感软件
复杂矿山
土地利用分类
教学科研
神经网络
remote sensing software
complex mine
land use classification
teaching and research
neural network
