地块级航空高光谱遥感土地覆盖制图及其精度评估

Geo-parcel Airborne Level Hyperspectral Remote Sensing Land Cover Mapping and Accuracy Assessment

利用高光谱遥感影像可以开展精细化土地覆盖制图,相关技术已在农业生产、植被生态等领域中广泛应用。然而,现有的面向像元或对象的分析方法在制图单元的合理性、精细性尚有欠缺。鉴于此,提出了基于随机森林的地块级高光谱土地覆盖制图思路,并利用雄安新区马蹄湾村高光谱影像开展实验与精度评估,综合类型精度和形态精度指标,探析不同划分尺度的制图优劣。在类型精度方面,结果表明:地块级高光谱土地覆盖制图效果及类型精度最优;在形态精度方面,发现地块级土地划分优于对象级划分结果。综合对比两类精度后得出,面向地块的高光谱土地覆盖制图可生产更符合用户需求的信息成果,具有较高的潜在应用价值。

Hyperspectral remote sensing images can be used to carry out fine-type land cover mapping,and related technologies have been widely used in agricultural production,vegetation ecology and so on.However,most of the existing methods are pixel-oriented or object-oriented analysis methods,which lack the rationality and precision of mapping units.In view of this,the idea of geo-parcel level hyperspectral land cover mapping based on random forest is proposed,and the hyperspectral image of Matiwan Village in Xiongan New Area is used to carry out experiments and accuracy evaluation,.By integrating the type accuracy and morphological accuracy indexes,the advantages and disadvantages of mapping at different scales are analyzed.In terms of type accuracy,the results show that the effect and type accuracy of geo-parcel hyperspectral land cover mapping are the best.In terms of morphological accuracy,the result shows that the land division at geo-parcel is better than that at object level.After comprehensive comparison of the two kinds of accuracy,it is shown that the geo-parcel level hyperspectral land cover mapping can produce information results more in line with user needs and has higher potential application value.