数字农科院2.0

Research on forage hyperspectral image recognition based on F-SVD and XGBoost

文献类型： 外文期刊

作者： Zhao, Xuanhe;Pan, Xin;Ma, Yubao;Yan, Weihong

作者机构：

期刊名称： 2020 2ND INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE COMMUNICATION AND NETWORK SECURITY (CSCNS2020)

ISSN： 2261-236X

年卷期： 2021 年 336 卷

页码：

收录情况： 不在遴选数据库范围

摘要： Aiming at the high time complexity and poor accuracy of traditional SVD in hyperspectral recognition. we proposed F-SVD, which introduces the latent factors(F) into the SVD decomposition strategy and uses the correlation between the latent variable and the original variable to improve the singular matrix. Firstly, we used F-SVD to reduce the dimension of visible-near infrared hyperspectral image, and consequently designed a forage recognition model based on XGBoost. When the test set sets 40%, the OA of F-SVD-XGBoost is 91.67%, which takes 0.601s. Compared with the traditional FA-XGBoost and SVD-XGBoost, OA increases 1.98% and 1.67%, and the time consumption decreases 1.369s and 0.522s, respectively. The results show that our model not only effectively extracts the essential features of forage hyperspectral and improves the accuracy of classification, but also has a faster processing speed, so that can efficiently and quickly realize the identification of forage hyperspectral images.

分类号：

  • 相关文献
作者其他论文 更多>>