Sub-Nyquist computational ghost imaging with deep learning.

We propose a deep learning computational ghost imaging (CGI) scheme to achieve sub-Nyquist and high-quality image reconstruction. Unlike the second-order-correlation CGI and compressive-sensing CGI, which use lots of illumination patterns and a one-dimensional (1-D) light intensity sequence (LIS) for image reconstruction, a deep neural network (DAttNet) is proposed to restore the target image only using the 1-D LIS. The DAttNet is trained with simulation data and retrieves the target image from experimental data. The experimental results indicate that the proposed scheme can provide high-quality images with a sub-Nyquist sampling ratio and performs better than the conventional and compressive-sensing CGI methods in sub-Nyquist sampling ratio conditions (e.g., 5.45%). The proposed scheme has potential practical applications in underwater, real-time and dynamic CGI.

Structured Background Modeling for Hyperspectral Anomaly Detection.

Background modeling has been proven to be a promising method of hyperspectral anomaly detection. However, due to the cluttered imaging scene, modeling the background of an hyperspectral image (HSI) is often challenging. To mitigate this problem, we propose a novel structured background modeling-based hyperspectral anomaly detection method, which clearly improves the detection accuracy through exploiting the block-diagonal structure of the background. Specifically, to conveniently model the multi-mode characteristics of background, we divide the full-band patches in an HSI into different background clusters according to their spatial-spectral features. A spatial-spectral background dictionary is then learned for each cluster with a principal component analysis (PCA) learning scheme. When being represented onto those dictionaries, the background often exhibits a block-diagonal structure, while the anomalous target shows a sparse structure. In light of such an observation, we develop a low-rank representation based anomaly detection framework that can appropriately separate the sparse anomaly from the block-diagonal background. To optimize this framework effectively, we adopt the standard alternating direction method of multipliers (ADMM) algorithm. With extensive experiments on both synthetic and real-world datasets, the proposed method achieves an obvious improvement in detection accuracy, compared with several state-of-the-art hyperspectral anomaly detection methods.