Hyperspectral Target Detection via Multiple Instance LSTM Target Localization Network
- Resource Type
- Conference
- Authors
- Chen, Xiaoying; Wang, Xiuxiu; Guo, Chubing; Chen, Chao; Gou, Shuiping; Yu, Tao; Jiao, Changzhe
- Source
- IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium Geoscience and Remote Sensing Symposium, IGARSS 2020 - 2020 IEEE International. :2436-2439 Sep, 2020
- Subject
- Aerospace
Computing and Processing
Geoscience
Photonics and Electrooptics
Signal Processing and Analysis
Hyperspectral imaging
Feature extraction
Object detection
Training
Task analysis
Long short term memory
Location awareness
hyperspectral
target detection
LSTM
multiple instance learning
labeling uncertainties
- Language
- ISSN
- 2153-7003
Modeling target detection problem given inaccurate annotations as a multiple instance learning (MIL) problem is an effective way for addressing the ground truth uncertainties of remotely sensed hyperspectral imagery. In this paper, we propose a hyperspectral target detection method based on 1D convolution neural network (1DCNN) feature extraction and long short term memory network (LSTM) under the MIL framework, where the LSTM features for each hyperspectral pixel is further refined by a scoring network as to discriminate the real target instance from the inaccurately labeled hyperspectral regions. The proposed method has achieved superior results on both simulated data and real hyperspectral data over the state-of-the-art methods, showing the prospects for further investigation.