### 2012

Zhong, Jingshan; Dauwels, Justin; Vazquez, Manuel A; Waller, Laura

Efficient Gaussian Inference Algorithms for Phase Imaging Inproceedings

In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 617–620, IEEE, Kyoto, 2012, ISSN: 1520-6149.

Abstract | Links | BibTeX | Tags: biomedical optical imaging, complex optical field, computational complexity, defocus distances, Fourier domain, Gaussian inference algorithms, image sequences, inference mechanisms, intensity image sequence, iterative Kalman smoothing, iterative methods, Kalman filter, Kalman filters, Kalman recursions, linear model, Manganese, Mathematical model, medical image processing, Noise, noisy intensity image, nonlinear observation model, Optical imaging, Optical sensors, Phase imaging, phase inference algorithms, smoothing methods

@inproceedings{Zhong2012a,

title = {Efficient Gaussian Inference Algorithms for Phase Imaging},

author = {Jingshan Zhong and Justin Dauwels and Manuel A Vazquez and Laura Waller},

url = {http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=6287959},

issn = {1520-6149},

year = {2012},

date = {2012-01-01},

booktitle = {2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

pages = {617--620},

publisher = {IEEE},

address = {Kyoto},

abstract = {Novel efficient algorithms are developed to infer the phase of a complex optical field from a sequence of intensity images taken at different defocus distances. The non-linear observation model is approximated by a linear model. The complex optical field is inferred by iterative Kalman smoothing in the Fourier domain: forward and backward sweeps of Kalman recursions are alternated, and in each such sweep, the approximate linear model is refined. By limiting the number of iterations, one can trade off accuracy vs. complexity. The complexity of each iteration in the proposed algorithm is in the order of N logN, where N is the number of pixels per image. The storage required scales linearly with N. In contrast, the complexity of existing phase inference algorithms scales with N3 and the required storage with N2. The proposed algorithms may enable real-time estimation of optical fields from noisy intensity images.},

keywords = {biomedical optical imaging, complex optical field, computational complexity, defocus distances, Fourier domain, Gaussian inference algorithms, image sequences, inference mechanisms, intensity image sequence, iterative Kalman smoothing, iterative methods, Kalman filter, Kalman filters, Kalman recursions, linear model, Manganese, Mathematical model, medical image processing, Noise, noisy intensity image, nonlinear observation model, Optical imaging, Optical sensors, Phase imaging, phase inference algorithms, smoothing methods},

pubstate = {published},

tppubtype = {inproceedings}

}

### 2009

Bugallo, Monica F; Maiz, Cristina S; Miguez, Joaquin; Djuric, Petar M

Cost-Reference Particle Filters and Fusion of Information Inproceedings

In: 2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop, pp. 286–291, IEEE, Marco Island, FL, 2009.

Abstract | Links | BibTeX | Tags: costs, distributed processing, Electronic mail, fusion, Information filtering, Information filters, information fusion, Measurement standards, probabilistic information, random measures, sensor fusion, smoothing methods, Weight measurement

@inproceedings{Bugallo2009,

title = {Cost-Reference Particle Filters and Fusion of Information},

author = {Monica F Bugallo and Cristina S Maiz and Joaquin Miguez and Petar M Djuric},

url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=4785936},

year = {2009},

date = {2009-01-01},

booktitle = {2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop},

pages = {286--291},

publisher = {IEEE},

address = {Marco Island, FL},

abstract = {Cost-reference particle filtering is a methodology for tracking unknowns in a system without reliance on probabilistic information about the noises in the system. The methodology is based on analogous principles as the ones of standard particle filtering. Unlike the random measures of standard particle filters that are composed of particles and weights, the random measures of cost-reference particle filters contain particles and user-defined costs. In this paper, we discuss a few scenarios where we need to meld random measures of two or more cost-reference particle filters. The objective is to obtain a fused random measure that combines the information from the individual cost-reference particle filters.},

keywords = {costs, distributed processing, Electronic mail, fusion, Information filtering, Information filters, information fusion, Measurement standards, probabilistic information, random measures, sensor fusion, smoothing methods, Weight measurement},

pubstate = {published},

tppubtype = {inproceedings}

}