Limits...
A Weighted Spatial-Spectral Kernel RX Algorithm and Efficient Implementation on GPUs

View Article: PubMed Central - PubMed

ABSTRACT

The kernel RX (KRX) detector proposed by Kwon and Nasrabadi exploits a kernel function to obtain a better detection performance. However, it still has two limits that can be improved. On the one hand, reasonable integration of spatial-spectral information can be used to further improve its detection accuracy. On the other hand, parallel computing can be used to reduce the processing time in available KRX detectors. Accordingly, this paper presents a novel weighted spatial-spectral kernel RX (WSSKRX) detector and its parallel implementation on graphics processing units (GPUs). The WSSKRX utilizes the spatial neighborhood resources to reconstruct the testing pixels by introducing a spectral factor and a spatial window, thereby effectively reducing the interference of background noise. Then, the kernel function is redesigned as a mapping trick in a KRX detector to implement the anomaly detection. In addition, a powerful architecture based on the GPU technique is designed to accelerate WSSKRX. To substantiate the performance of the proposed algorithm, both synthetic and real data are conducted for experiments.

No MeSH data available.


(a) The subarea of SpecTIR image; (b) ground truth of the SpecTIR image scene.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC5375727&req=5

sensors-17-00441-f010: (a) The subarea of SpecTIR image; (b) ground truth of the SpecTIR image scene.

Mentions: The dataset were collected through the SpecTIR Hyperspectral Airborne Rochester Experiment (SHARE) by the ProSpecTIR-VS2 sensor (SpecTIR, LLC, Rochester, New York, NY, USA). It contains 3127 × 320 pixels with an 1 m space resolution, and 360 bands ranging from 390 nm to 2450 nm with a 5 nm spectral resolution. In this experiment, a subset with a size of 100 × 100 pixels and 360 bands is segmented from the original data. There are some square fabrics placed as anomaly targets in the subarea of image (Figure 10a), and the ground truth map is shown in Figure 10b.


A Weighted Spatial-Spectral Kernel RX Algorithm and Efficient Implementation on GPUs
(a) The subarea of SpecTIR image; (b) ground truth of the SpecTIR image scene.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC5375727&req=5

sensors-17-00441-f010: (a) The subarea of SpecTIR image; (b) ground truth of the SpecTIR image scene.
Mentions: The dataset were collected through the SpecTIR Hyperspectral Airborne Rochester Experiment (SHARE) by the ProSpecTIR-VS2 sensor (SpecTIR, LLC, Rochester, New York, NY, USA). It contains 3127 × 320 pixels with an 1 m space resolution, and 360 bands ranging from 390 nm to 2450 nm with a 5 nm spectral resolution. In this experiment, a subset with a size of 100 × 100 pixels and 360 bands is segmented from the original data. There are some square fabrics placed as anomaly targets in the subarea of image (Figure 10a), and the ground truth map is shown in Figure 10b.

View Article: PubMed Central - PubMed

ABSTRACT

The kernel RX (KRX) detector proposed by Kwon and Nasrabadi exploits a kernel function to obtain a better detection performance. However, it still has two limits that can be improved. On the one hand, reasonable integration of spatial-spectral information can be used to further improve its detection accuracy. On the other hand, parallel computing can be used to reduce the processing time in available KRX detectors. Accordingly, this paper presents a novel weighted spatial-spectral kernel RX (WSSKRX) detector and its parallel implementation on graphics processing units (GPUs). The WSSKRX utilizes the spatial neighborhood resources to reconstruct the testing pixels by introducing a spectral factor and a spatial window, thereby effectively reducing the interference of background noise. Then, the kernel function is redesigned as a mapping trick in a KRX detector to implement the anomaly detection. In addition, a powerful architecture based on the GPU technique is designed to accelerate WSSKRX. To substantiate the performance of the proposed algorithm, both synthetic and real data are conducted for experiments.

No MeSH data available.