Translator Disclaimer
Paper
12 March 2019 Study on extraction of foreign invasive species Mikania micrantha based on unmanned aerial vehicle (UAV) hyperspectral remote sensing
Author Affiliations +
Abstract
Mikania micrantha is a harmful foreign invasive species, which poses a great threat to the ecological balance and forestry production in southern China. In the study, typical Mikania micrantha multi-incidence area was used as the research area. After data pre-processing, 250 bands were obtained and subjected to a single factor ANOVA analysis. Anterior 10 bands with F values from the largest to the smallest were selected as the spectral characteristic bands. Spectral characteristics were extracted, together with texture characteristics. Texture characteristic of hyperspectral data was calculated by Gray level co-occurrence matrix, with processing window sizes of 11, 15, 21, 31, 41, 51, respectively. Results showed that the mean and second moment in processing window of 15 was more appropriate. A total of 200 verification points were randomly selected from five flight concentration areas. Visual interpretation was performed to verify the accuracy of the extraction. Results showed that the total accuracy was 85.5%. In this paper, key technology of unmanned aerial vehicle (UAV) hyperspectral remote sensing for extracting Mikania micrantha was studied, having constructed process of extracting the Mikania micrantha range by UAV hyperspectral data. Research results provide a new technical reference for the extraction of Mikania micrantha.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jianhui Li, Dingquan Li, Gui Zhang, Haizhou Xu, Rongliang Zeng, Wangjun Luo, and Youliang Yu "Study on extraction of foreign invasive species Mikania micrantha based on unmanned aerial vehicle (UAV) hyperspectral remote sensing", Proc. SPIE 11023, Fifth Symposium on Novel Optoelectronic Detection Technology and Application, 110232F (12 March 2019); https://doi.org/10.1117/12.2520027
PROCEEDINGS
9 PAGES


SHARE
Advertisement
Advertisement
Back to Top