No abstract

Dimensionality reduction (DR) is of great significance for simplifying and optimizing hyperspectral image (HSI) features. As a widely used DR method, kernel minimum noise fraction (KMNF) transformation preserves the high-order structures of the original data perfectly. However, the conventional KMNF noise estimation (KMNF-NE) uses the local regression residual of neighbourhood pixels, which depends heavily on spatial information. Due to the limited spatial resolution, there are many mixed pixels in HSI, making KMNF-NE unreliable for noise estimation and leading to poor performance in KMNF for classification on HSIs with low spatial resolution. In order to overcome this problem, a mixed noise estimation model (MNEM) is proposed in this paper for optimized KMNF (OP-KMNF). The MNEM adopts the sequential and linear combination of the Gaussian prior denoising model, median filter, and Sobel operator to estimate noise. It retains more details and edge features, making it more suitable for noise estimation in KMNF. Experiments using several HSI datasets with different spatial and spectral resolutions are conducted. The results show that, compared with some other DR methods, the improvement of OP-KMNF in average classification accuracy is up to 4%. To improve the efficiency, the OP-KMNF was implemented on graphics processing units (GPU) and sped up by about 60× compared to the central processing unit (CPU) implementation. The outcome demonstrates the significant performance of OP-KMNF in terms of classification ability and execution efficiency.

Rapid disaster assessment is critical for public security and rescue. As a secondary disaster of large-scale meteorological disasters, power outages cause severe outcomes and thus need to be monitored efficiently and without being costly. Power outage detection from space-borne remote sensing imagery offers a broader coverage and is more temporally sensitive than ground-based surveys are. However, it is challenging to determine the affected area accurately and quantitatively evaluate its severity. Therefore, a new method is proposed to solve the above problems by building a power outage detection model (PODM) and drawing a power outage spatial distribution map (POSDM). This paper takes the winter storm Uri, of 2021, as the meteorological disaster background and Harris County, Texas, which was seriously affected, as the research object. The proposed method utilises the cloud-free VIIRS DNB nadir and close nadir images (<60 degrees) collected during the 3 months before and 15 days after Uri. The core idea beneath the proposed method is to compare the radiance difference in the affected area before and after the disaster, and a large difference in radiance indicates the happening of power outages. The raw radiance of night light measurement is first corrected to remove lunar and atmospheric effects to improve accuracy. Then, the maximum and minimum pixels in the target area of the image are considered outliers and iteratively eliminated until the standard deviation change before and after elimination is less than 1% to finalize the outlier removals. The case study results in Harris show that the PODM detects 28% of outages (including traffic area) compared to 17% of outages (living area only) reported by ground truth data, indicating general agreement with the proposed method.

A significant challenge in methods for anomaly detection (AD) in hyperspectral images (HSIs) is determining how to construct an efficient representation for anomalies and background information. Considering the high-order structures of HSIs and the estimation of anomalies and background information in AD, this article proposes a kernel minimum noise fraction transformation-based background separation model (KMNF-BSM) to separate the anomalies and background information. First, spectral-domain KMNF transformation is performed on the original hyperspectral data to fully mine the high-order correlation between spectral bands. Then, a BSM that combines the outlier removal, the iteration strategy, and the Reed–Xiaoli detector (RXD) is proposed to obtain accurate anomalous and background pixel sets based on the extracted features. Finally, the anomalous and background pixel sets are used as input for anomaly detectors to improve the background suppression and anomaly detection capabilities. Experiments on several HSIs with different spatial and spectral resolutions over different scenes are performed. The results demonstrate that the KMNF-BSM-based algorithms have better target detectability and background suppressibility than other state-of-the-art algorithms.