Comparative analysis of sensing matrices for compressed sensed thermal images

Dias, Usham V.; Rane, Milind

doi:10.1109/imac4s.2013.6526420

Cited by 13 publications

(13 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This process is repeated across all frames in the video under test. This paper tests fourteen different sensing patterns described in [3] for acquiring the data. Greedy reconstruction algorithms implemented in this paper include Orthogonal Matching Pursuit and Regularized Orthogonal Matching Pursuit.…”

Section: Block Based Compressive Sensingmentioning

confidence: 99%

“…As compared to [3] which reconstructs an image of 64x64 size with much larger time consumption which is further sensitive to the kind of sensing matrix selected, this paper reconstructs a large frame of size 256x256 in 0.964, 0.729 and 0.649 seconds using OMP, ROMP 10% and ROMP 20% respectively.…”

Section: Number Of Iterations For Reconstructionmentioning

confidence: 99%

“…In [3], fourteen different sensing matrices have been considered for acquiring the signal, some of which have the potential for object specific reconstruction. This paper tests all the fourteen sensing patterns using Orthogonal Matching Pursuit (OMP) and Regularized Orthogonal Matching Pursuit (ROMP) as reconstruction algorithms.…”

Section: Introductionmentioning

confidence: 99%

“…Object specific reconstruction based on the reconstructed algorithm for surveillance was proposed in [5]. The different sensing matrices implemented in [3] are based on [6][7][8][9]. The combinatorial algorithms for reconstruction are not efficient for real time applications hence this paper implements greedy algorithms for reconstruction [10][11][12].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Block-Based Compressive Sensed Thermal Image Reconstruction using Greedy Algorithms

Dias¹,

Rane²

2014

IJIGSP

View full text Add to dashboard Cite

Abstract-This paper implements a block based compressive sensing technique for thermal image reconstruction using greedy algorithms. A total of fourteen different sensing patterns were tested for data acquisition. Orthogonal Matching Pursuit (OMP) and Regularized Orthogonal Matching Pursuit (ROMP) with two different thresholds were implemented for image reconstruction with OMP having an edge over ROMP in terms of error and PSNR. ROMP was faster in terms of iterations needed for reconstruction. As the threshold for ROMP was increased the number of iterations needed decreased. Gaussian, Bernoulli and Hadamard patterns were the best for reconstruction. Hadamard matrix, Bernoulli matrix with +/-1 entries and Bernoulli matrix with 0/1 entries have the added advantage of being more conducive for hardware implementation. This paper used Discrete Cosine Transform as the sparsifying basis for reconstruction.

show abstract

Section: Block Based Compressive Sensingmentioning

confidence: 99%

Section: Number Of Iterations For Reconstructionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Block-Based Compressive Sensed Thermal Image Reconstruction using Greedy Algorithms

Dias¹,

Rane²

2014

IJIGSP

View full text Add to dashboard Cite

show abstract

“…Structured sensing matrices (e.g., Toeplitz matrices and sparse matrices) have been proposed [20][21][22][23][24][25][26] to reduce the computational complexity of sensing signals in hardware (such as digital signal processor and FPGA) [27,28], or applications like electrocardiography (ECG) compression [29] and data stream computing [30]. A Toeplitz matrix can be implemented efficiently to a vector by the fast Fourier transform (FFT).…”

Section: Introductionmentioning

confidence: 99%

Optimized structured sparse sensing matrices for compressive sensing

et al. 2019

View full text Add to dashboard Cite

We consider designing a robust structured sparse sensing matrix consisting of a sparse matrix with a few nonzero entries per row and a dense base matrix for capturing signals efficiently. We design the robust structured sparse sensing matrix through minimizing the distance between the Gram matrix of the equivalent dictionary and the target Gram of matrix holding small mutual coherence. Moreover, a regularization is added to enforce the robustness of the optimized structured sparse sensing matrix to the sparse representation error (SRE) of signals of interests. An alternating minimization algorithm with global sequence convergence is proposed for solving the corresponding optimization problem. Numerical experiments on synthetic data and natural images show that the obtained structured sensing matrix results in a higher signal reconstruction than a random dense sensing matrix. (Zhihui Zhu), qiuli@mines.edu (Qiuwei Li) 1 Throughout this paper, MATLAB notations are adopted: Q(m, : ), Q(:, k) and Q(i, j) denote the mth row, kth column, and (i, j)th entry of the matrix Q; q(n) denotes the nth entry of the vector q. · 0 is used to count the number of nonzero elements.

show abstract

Efficient measurement matrix for speech compressive sampling

Ahmed

Khan

et al. 2021

Multimed Tools Appl

View full text Add to dashboard Cite

Comparative analysis of sensing matrices for compressed sensed thermal images

Cited by 13 publications

References 9 publications

Block-Based Compressive Sensed Thermal Image Reconstruction using Greedy Algorithms

Block-Based Compressive Sensed Thermal Image Reconstruction using Greedy Algorithms

Optimized structured sparse sensing matrices for compressive sensing

Efficient measurement matrix for speech compressive sampling

Contact Info

Product

Resources

About