期刊
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
卷 14, 期 -, 页码 9079-9088出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSTARS.2021.3110897
关键词
Forestry; Vegetation; Anomaly detection; Hyperspectral imaging; Sparse matrices; Object detection; Estimation; Anomaly detection; hyperspectral image (HSI); isolation forest (iForest)
类别
资金
- National Natural Science Foundation of China [62071438, 62171417, 61701452, 61801444, 62071439]
- State Key Laboratory of Integrated Services Networks (Xidian University) [ISN20-07]
- Open Research Fund of CAS Key Laboratory of Spectral Imaging Technology [LSIT201921W]
- Open Research Project of The Hubei Key Laboratory of Intelligent Geo-Information Processing [KLIGIP-2018A01]
The proposed method in this article, based on an Otsu-based isolation forest, effectively separates anomalies from backgrounds by assembling multiple binary trees and using the Otsu-based splitting criterion for a more discriminative binary tree construction.
Hyperspectral anomaly detection involves in many practical applications. Traditional anomaly detection methods are mainly proposed based on statistical models and geometrical models. This article proposes an Otsu-based isolation forest method, which applies the assumption that anomaly pixels are more sensitive to be isolated from the alternative pixels. The proposed article trains an isolation forest by assembling multiple binary trees. To construct a more discriminative binary tree, Otsu-based splitting criterion is applied to split subsamples into two groups at each division. Then, it feeds each tested pixel into isolation forest and obtains its anomaly score via the average path length throughout isolation forest. Considering the pixels with anomaly attribute values, path length refinement strategy based on distance weight is applied to better distinguish anomaly scores of tested pixels. Experimental results on three datasets reveal that the proposed method can effectively separate anomalies from backgrounds compared with other anomaly detection methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据