Hyperspectral anomaly detection combining sparse constraint and feature extraction via stacked autoencoder
SONG Shangzhen, YANG Yixin, WANG Huifeng, WANG Xiaoyan, RONG Shenghui, ZHOU Huixin
2023, 52(6):
932-943.
doi:10.11947/j.AGCS.2023.20210604
Asbtract
(
)
HTML
(
)
PDF (7135KB)
(
)
References |
Related Articles |
Metrics
Anomaly detection of hyperspectral images has important application value in military, agriculture, exploration, fire protection and other fields. Traditional algorithms of hyperspectral image (HSI) anomaly detection (AD) do not effectively mine the deep features of the image spectrum, while the deep learning method has good ability to extract deep feature information. Since the AD problem generally cannot obtain the prior information in advance, the unsupervised network is more suitable. Existing AD algorithms based on autoencoder (AE) does not make effective use of the local information, resulting in limited detection effect. To overcome this shortcoming, the paper proposes an AD method based on sparse representation (SR) constraints for stacked autoencoder (SAE). Firstly, the semantic information is obtained by SAE. Secondly, the SR is used as a constraint to effectively combine with the encoder, and the local characteristics of the feature elements in the potential hidden space are mined. Finally, the fractional Fourier transform is utilized, and the characteristics of the original spectrum and its intermediate domain of Fourier transform are obtained by spatial-frequency representation. Consequently, the spectral discrimination between background and anomalies is further enhanced, and the effect of noise is also removed. The experiment performs verification on 5 HSIs collected by 4 spectrometers including Hymap, AVIRIS, ROSIS, and HYDICE. The area under curve (AUC) values are 0.990 5, 0.998 3, 0.999 0, 0.992 8 and 0.911 0, respectively. Compared with compared algorithms, the effect of the proposed algorithm can be improved.