Graph signal processing (GSP) is an emerging field developed for analyzing signals defined on irregular spatial structures modeled as graphs. Given the considerable literature regarding the resilience of infrastructure networks using graph theory, it is not surprising that a number of applications of GSP can be found in the resilience domain. GSP techniques assume that the choice of graphical Fourier transform (GFT) imparts a particular spectral structure on the signal of interest. We assess a number of power distribution systems with respect to metrics of signal structure and identify several correlates to system properties and further demonstrate how these metrics relate to performance of some GSP techniques. We also discuss the feasibility of a data-driven approach that improves these metrics and apply it to a water distribution scenario. Overall, we find that many of the candidate systems analyzed are properly structured in the chosen GFT basis and amenable to GSP techniques, but identify considerable variability and nuance that merits future investigation.
more »
« less
Multilayer graph spectral analysis for hyperspectral images
Abstract Hyperspectral imaging has broad applications and impacts in areas including environmental science, weather, and geo/space exploration. The intrinsic spectral–spatial structures and potential multi-level features in different frequency bands make multilayer graph an intuitive model for hyperspectral images (HSI). To study the underlying characteristics of HSI and to take the advantage of graph signal processing (GSP) tools, this work proposes a multilayer graph spectral analysis for hyperspectral images based on multilayer graph signal processing (M-GSP). More specifically, we present multilayer graph (MLG) models and tensor representations for HSI. By exploring multilayer graph spectral space, we develop MLG-based methods for HSI applications, including unsupervised segmentation and supervised classification. Our experimental results demonstrate the strength of M-GSP in HSI processing and spectral–spatial information extraction.
more »
« less
- NSF-PAR ID:
- 10422086
- Date Published:
- Journal Name:
- EURASIP Journal on Advances in Signal Processing
- Volume:
- 2022
- Issue:
- 1
- ISSN:
- 1687-6180
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Abstract Capturing fine spatial, spectral, and temporal information of the scene is highly desirable in many applications. However, recording data of such high dimensionality requires significant transmission bandwidth. Current computational imaging methods can partially address this challenge but are still limited in reducing input data throughput. In this paper, we report a video-rate hyperspectral imager based on a single-pixel photodetector which can achieve high-throughput hyperspectral video recording at a low bandwidth. We leverage the insight that 4-dimensional (4D) hyperspectral videos are considerably more compressible than 2D grayscale images. We propose a joint spatial-spectral capturing scheme encoding the scene into highly compressed measurements and obtaining temporal correlation at the same time. Furthermore, we propose a reconstruction method relying on a signal sparsity model in 4D space and a deep learning reconstruction approach greatly accelerating reconstruction. We demonstrate reconstruction of 128 × 128 hyperspectral images with 64 spectral bands at more than 4 frames per second offering a 900× data throughput compared to conventional imaging, which we believe is a first-of-its kind of a single-pixel-based hyperspectral imager.
-
Push-broom hyperspectral imaging (Pb-HSI) is a powerful technique for obtaining the spectral information along with the spatial information simultaneously for various applications, from remote sensing to chemical imaging. Spatial resolution improvement is beneficial in many instances; however, typical solutions suffer from the limitation of geometric extent, lowered light throughput, or reduced field-of-view (FOV). Sub-pixel shifting (SPS) acquires higher-resolution images, compared to typical imaging approaches, from the deconvolution of low-resolution images acquired with a higher sampling rate. Furthermore, SPS is particularly suited for Pb-HSI due to its scanning nature. In this study, an SPS approach is developed and implemented on a Pb-HSI system for plasma optical emission spectroscopy. The preliminary results showed that a periodic deconvolution error was generated in the final SPS Pb-HSI images. The periodic error was traced back to random noise present in the raw/convoluted SPS data and its frequency displays an inverse relationship with the number of sub-pixel samples acquired. Computer modelled data allows studying the effect of varying the relative standard deviation (RSD) in the raw/convoluted SPS data on the final reconstructed SPS images and optimization of noise filtering. The optimized SPS Pb-HSI technique was used to acquire the line-of-sight integrated optical emission maps from an atmospheric pressure micro-capillary dielectric barrier discharge (μDBD). The selected plasma species of interest (He, I, N 2 , N 2 + , and O) yield some insight into the underlying mechanisms. The SPS Pb-HSI technique developed here will allow implementing geometric super-resolution in many applications, for example, it will be used for extracting radially resolved information from Abel's inversion protocols, where improved fitting is expected due to the increase in resolution/data points.more » « less
-
Hyperspectral imaging (HSI) is a technology used in remote sensing, food processing and documentation recovery. Recently, this approach has been applied in the medical field to spectrally interrogate regions of interest within respective substrates. In spectral imaging, a two (spatial) dimensional image is collected, at many different (spectral) wavelengths, to sample spectral signatures from different regions and/or components within a sample. Here, we report on the use of hyperspectral imaging for endoscopic applications. Colorectal cancer is the 3rd leading cancer for incidences and deaths in the US. One factor of severity is the miss rate of precancerous/flat lesions (~65% accuracy). Integrating HSI into colonoscopy procedures could minimize misdiagnosis and unnecessary resections. We have previously reported a working prototype light source with 16 high-powered light emitting diodes (LEDs) capable of high speed cycling and imaging. In recent testing, we have found our current prototype is limited by transmission loss (~99%) through the multi-furcated solid light guide (lightpipe) and the desired framerate (20-30 fps) could not be achieved. Here, we report on a series of experimental and modeling studies to better optimize the lightpipe and the spectral endoscopy system as a whole. The lightpipe was experimentally evaluated using an integrating sphere and spectrometer (Ocean Optics). Modeling the lightpipe was performed using Monte Carlo optical ray tracing in TracePro (Lambda Research Corp.). Results of these optimization studies will aid in manufacturing a revised prototype with the newly designed light guide and increased sensitivity. Once the desired optical output (5-10 mW) is achieved then the HIS endoscope system will be able to be implemented without adding onto the procedure time.more » « less
-
Agaian, Sos S. ; Jassim, Sabah A. ; DelMarco, Stephen P. ; Asari, Vijayan K. (Ed.)Neural networks have emerged to be the most appropriate method for tackling the classification problem for hyperspectral images (HIS). Convolutional neural networks (CNNs), being the current state-of-art for various classification tasks, have some limitations in the context of HSI. These CNN models are very susceptible to overfitting because of 1) lack of availability of training samples, 2) large number of parameters to fine-tune. Furthermore, the learning rates used by CNN must be small to avoid vanishing gradients, and thus the gradient descent takes small steps to converge and slows down the model runtime. To overcome these drawbacks, a novel quaternion based hyperspectral image classification network (QHIC Net) is proposed in this paper. The QHIC Net can model both the local dependencies between the spectral channels of a single-pixel and the global structural relationship describing the edges or shapes formed by a group of pixels, making it suitable for HSI datasets that are small and diverse. Experimental results on three HSI datasets demonstrate that the QHIC Net performs on par with the traditional CNN based methods for HSI Classification with a far fewer number of parameters. Keywords: Classification, deep learning, hyperspectral imaging, spectral-spatial feature learningmore » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1186/s13634-022-00926-8
