基于WorldView-2影像的外来物种薇甘菊入侵遥感监测

Remote sensing of a Mikania micrantha invasion in alien species with WordView-2 images

为了探究利用高分辨率影像进行外来物种薇甘菊Mikania micrantha遥感监测,以WorldView-2影像为数据源,利用面向对象的分类方法,对深圳市薇甘菊进行遥感监测。研究结果表明:利用WorldView-2影像进行薇甘菊的最佳波段组合为364波段(近红外波段、海岸波段、红色波段),薇甘菊的制图精度为83.33%,用户精度为81.08%,总体精度为87.5%,且其他地物类型的分类精度也比较高,都达到80%以上,取得较好的监测结果,突破了人工调查周期长,主观性强等缺点,在监测手段、方法以及时间上更加具有优势。因此,基于WorldView-2影像面向对象方法进行薇甘菊遥感信息提取具有良好的应用价值。

To explore the practicality of using high resolution images from remote sensing to monitor the inva- sire species Mikania micrantha, WordView-2 images as data sources were employed along with object-oriented classification methods in Shenzhen City. Results using WordView-2 images showed that the optimal band com- bination for M. micrantha was 364 bands （near infrared band, coastal band, and red light） with an 83.3% mapping accuracy, a user accuracy of 81.1%, and an overall accuracy of 87.5%. Precise classification of other object types was above 80%. Although subjectivity was a strong disadvantage, monitoring with remote sens- ing, based on the object-oriented methodology of a WordView-2 video, was advantageous for extraction and application ofM. micrantha data.