Hybrid model to optimize object-based land cover classification by meta-heuristic algorithm:an example for supporting urban management in Ha Noi,Viet Nam
作者机构：Center for Applied Research in Remote sensing and GIS(CARGIS)VNU University of ScienceHa NoiViet Nam VNU University of ScienceHa NoiViet Nam Vietnam Institute of Geodesy and CartographyHa NoiViet Nam Ministry of Education and TrainingHa NoiViet Nam
出 版 物：《International Journal of Digital Earth》 (国际数字地球学报（英文）)
年 卷 期：2019年第12卷第10期
页 面：1118-1132页
核心收录：
学科分类：08[工学] 0708[理学-地球物理学] 0835[工学-软件工程] 0704[理学-天文学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）]
主 题：Urban remote sensing object-based classification neural network grasshopper optimization algorithm
摘 要：This study proposed a novel object-based hybrid classification model named GMNN that combines Grasshopper Optimization Algorithm(GOA)and the multiple-class Neural network(MNN)for urban pattern detection in Hanoi,*** bands of SPOT 7 image and derivable NDVI,NDWI were used to generate image segments with associated attributes by PCI Geomatics *** segments were classified into four urban surface types(namely water,impervious surface,vegetation and bare soil)by the proposed ***,three training and validation datasets of different sizes were used to verify the robustness of this *** all tests,the overall accuracies of the classification were approximately 87%,and the Area under Receiver Operating Characteristic curves for each land cover type was ***,the performance of this model was examined by comparing several statistical indicators with common benchmark *** results showed that GMNN out-performed established methods in all comparable *** results suggested that our hybrid model was successfully deployed in the study area and could be used as an alternative classification method for urban land cover *** a broader sense,classification methods will be enriched with the active and fast-growing contribution of metaheuristic algorithms.
维普期刊数据库