测绘通报 ›› 2019, Vol. 0 ›› Issue (7): 78-82.doi: 10.13474/j.cnki.11-2246.2019.0223

• 技术交流 • 上一篇    下一篇

基于多特征CRF的无人机影像松材线虫病监测方法

刘金沧1, 王成波2, 常原飞2   

  1. 1. 广东省国土资源测绘院, 广东 广州 510500;
    2. 中国科学院遥感与数字地球研究所, 北京 100101
  • 收稿日期:2019-03-21 修回日期:2019-05-22 出版日期:2019-07-25 发布日期:2019-07-31
  • 作者简介:刘金沧(1987-),男,硕士,工程师,主要从事自然资源调查监测、摄影测量与遥感应用研究。E-mail:liujincang_whu@126.com
  • 基金资助:
    广东省省级科技计划(2018B020207002)

Monitoring method of bursaphelenchus xylophilus based on multi-feature CRF by UAV image

LIU Jincang1, WANG Chengbo2, CHANG Yuanfei2   

  1. 1. Surveying and Mapping Institute, Land and Resources Department of Guangdong Province, Guangzhou 510500, China;
    2. Institute of Remote Sensing and Digital Earth, CAS, Beijing 100101, China
  • Received:2019-03-21 Revised:2019-05-22 Online:2019-07-25 Published:2019-07-31

摘要: 利用无人机遥感技术进行林业调查,可以获取低成本、高分辨率、高时间密度的遥感数据,特别是为小尺度范围的森林病虫害监测提供了非常有效的监测手段。本文以小型无人机为影像获取平台,航摄获取可见光RGB影像,基于高分辨率影像进行松材线虫病松树提取方法研究。根据影像特点,提取影像中地物颜色、纹理特征,并采用CRF方法进行分类,识别出病害松树。通过比较多种分类方法的提取结果,验证了基于多特征CRF方法在松材线虫病监测中的可行性和有效性。

关键词: 无人机影像, 特征提取, 图像分类, CRF, 松材线虫病

Abstract: The use of UAV remote sensing technology for forest survey can obtain low-cost, high-resolution, high-time-density remote sensing data, especially for small-scale forest pest monitoring. In this paper, we use the small unmanned aerial vehicle as the image acquisition platform, acquire the RGB image, and study the extraction method of red-attacked pine based on the high resolution image. According to the image characteristics, the color and texture features of the image are extracted, and the CRF method is adopted to identify red-attacked pine. The feasibility and effectiveness of the multi-feature conditional random field method in the monitoring of bursaphelenchus xylophilus is verified by comparing the extraction results of multiple classification methods.

Key words: UAV image, feature selection, image classification, CRF, bursaphelenchus xylophilus

中图分类号: