HyperReconNet: Joint Coded Aperture Optimization and Image Reconstruction for Compressive Hyperspectral Imaging

Wang, Lizhi; Zhang, Tao; Fu, Ying; Huang, Hua

doi:10.1109/tip.2018.2884076

Cited by 136 publications

(57 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, we can calculate the makespan and total energy consumption by Eqs. (3) and (5), respectively, to evaluate the fitness of this particular scheduling solution.…”

Section: B Fitness Calculationmentioning

confidence: 99%

“…H Yperspectral remote sensing has been popularly used in a variety earth observation fields such as environment monitoring and object identification, and military defense [1]- [3]. Hyperspectral sensors can now simultaneously measure hundreds of contiguous spectral bands with high spectral resolution.…”

Section: Introductionmentioning

confidence: 99%

“…t k 's predecessor tasks in preT ask;11 calculate the maximum completion time of all these predecessor tasks, and denote it by T max end ;12 determine task execution time T Dura according to the number of computing nodes assigned for t k ;13 update computing node's operation time T exec [i] = T max end + T Dura ;14 update task complete time T end [i] = T max end + T Dura ;15 add task t k into preT ask;16 calculate the makespan and total energy consumption by Eqs. (3) and (5); 17 return makespan and energy consumption by Eqs (3). and (5);…”

mentioning

confidence: 99%

See 2 more Smart Citations

Multiobjective Task Scheduling for Energy-Efficient Cloud Implementation of Hyperspectral Image Classification

Sun

Zhang

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

“…Finally, we can calculate the makespan and total energy consumption by Eqs. (3) and (5), respectively, to evaluate the fitness of this particular scheduling solution.…”

Section: B Fitness Calculationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Multiobjective Task Scheduling for Energy-Efficient Cloud Implementation of Hyperspectral Image Classification

Sun

Zhang

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

“…Classes of CS algorithms commonly employed are sparse recovery [16], [17] (which is frequently augmented by dictionary learning [18]), neural network-based reconstruction [19]- [22], and adaptive basis scan (or adaptive direct sampling) [23]- [26]. Sparse recovery algorithms tend to have good performance guarantees, but generally are computationally intensive, making them slow for large signals like hyperspectral scenes.…”

Section: Compressed Sensing For Hsimentioning

confidence: 99%

Multitrack Compressed Sensing for Faster Hyperspectral Imaging

Kubal¹,

Lee²,

Tay³

et al. 2021

Preprint

View full text Add to dashboard Cite

<div>Hyperspectral imaging (HSI) provides much more information than regular optical microscopy and spectroscopy, making it valuable in areas such as biomedicine, materials inspection and food safety. However HSI is challenging because of the large amount of data that has to be acquired, and large measurement times. Compressed sensing (CS) approaches to hyperspectral imaging have been developed to address this, albeit subject to tradeoffs between image reconstruction accuracy, time and generalizability to different types objects or scenes.</div><div>Here, we develop improved compressed sensing approaches for HSI, based on parallelized multitrack acquisition of multiple spectra per shot. This is an augmentation of single-pixel-camera-style acquisition for HSI, where a single spectrum is measured per shot. The multitrack architecture can be paired up with either of the two compatible CS algorithms developed here: (1) a sparse recovery algorithm based on block compressed sensing, and (2) an adaptive CS algorithm based on sampling in the wavelet domain. As a result, the measurement speed can be drastically increased, while maintaining reconstruction speed as well as accuracy.</div><div>The methods are validated computationally, via noiseless as well as noisy simulated measurements. Multitrack adaptive CS has a ~10 times smaller measurement plus reconstruction time as compared to full sampling HSI, without compromise to reconstruction accuracies across the different sample images tested. Multitrack non-adaptive CS (sparse recovery) suffers a large reconstruction time, but is the most robust to Poisson noise.</div><div><i><b>Note: This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.</b></i><br></div>

show abstract

“…In the context of Compressed Sensing, Yuann et al [87] consider the super-resolution of observations acquired by a Compressed Sensing architectures, specifically the CASSI [88], using CNN architectures, which allow demonstrates promising performance under simulated conditions. A similar approach involving the recovery of HS observations from Compressed Sensing measurements is also considered in [89], while in [90], in addition to the recovery process, optimization of the acquisition process is also explored.…”

Section: Super-resolutionmentioning

confidence: 99%

Survey of Deep-Learning Approaches for Remote Sensing Observation Enhancement

Tsagkatakis

Aidini

Fotiadou

et al. 2019

Sensors

111

View full text Add to dashboard Cite

Deep Learning, and Deep Neural Networks in particular, have established themselves as the new norm in signal and data processing, achieving state-of-the-art performance in image, audio, and natural language understanding. In remote sensing, a large body of research has been devoted to the application of deep learning for typical supervised learning tasks such as classification. Less yet equally important effort has also been allocated to addressing the challenges associated with the enhancement of low-quality observations from remote sensing platforms. Addressing such channels is of paramount importance, both in itself, since high-altitude imaging, environmental conditions, and imaging systems trade-offs lead to low-quality observation, as well as to facilitate subsequent analysis, such as classification and detection. In this paper, we provide a comprehensive review of deep-learning methods for the enhancement of remote sensing observations, focusing on critical tasks including single and multi-band super-resolution, denoising, restoration, pan-sharpening, and fusion, among others. In addition to the detailed analysis and comparison of recently presented approaches, different research avenues which could be explored in the future are also discussed.

show abstract

HyperReconNet: Joint Coded Aperture Optimization and Image Reconstruction for Compressive Hyperspectral Imaging

Cited by 136 publications

References 64 publications

Multiobjective Task Scheduling for Energy-Efficient Cloud Implementation of Hyperspectral Image Classification

Multiobjective Task Scheduling for Energy-Efficient Cloud Implementation of Hyperspectral Image Classification

Multitrack Compressed Sensing for Faster Hyperspectral Imaging

Survey of Deep-Learning Approaches for Remote Sensing Observation Enhancement

Contact Info

Product

Resources

About