Active polarization descattering.

Treibitz T, Schechner YY.

Electrical Engineering Department, Technion - Israel Institute of Technology , Haifa, Israel. ttali@tx.technion.ac.il

Abstract
Vision in scattering media is important but challenging. Images suffer from poor visibility due to
backscattering and attenuation. Most prior methods for scene recovery use active illumination scanners
(structured and gated), which can be slow and cumbersome, while natural illumination is inapplicable to dark
environments. The current paper addresses the need for a non-scanning recovery method, that uses active
scene irradiance. We study the formation of images under widefield artificial illumination. Based on the
formation model, the paper presents an approach for recovering the object signal. It also yields rough
information about the 3D scene structure. The approach can work with compact, simple hardware, having
active widefield, polychromatic polarized illumination. The camera is fitted with a polarization analyzer. Two
frames of the scene are taken, with different states of the analyzer or polarizer. A recovery algorithm follows
the acquisition. It allows both the backscatter and the object reflection to be partially polarized. It thus unifies
and generalizes prior polarization-based methods, which had assumed exclusive polarization of either of
these components. The approach is limited to an effective range, due to image noise and illumination falloff.
Thus, the limits and noise sensitivity are analyzed. We demonstrate the approach in underwater field
experiments.

Epipolar geometry of opti-acoustic stereo imaging.

Negahdaripour S.

Electrical and Computer Engineering Department, University of Miami, FL 33146, USA. shahriar@miami.edu

Abstract
Optical and acoustic cameras are suitable imaging systems to inspect underwater structures, both in regular
maintenance and security operations. Despite high resolution, optical systems have limited visibility range
when deployed in turbid waters. In contrast, the new generation of high-frequency (MHz) acoustic cameras
can provide images with enhanced target details in highly turbid waters, though their range is reduced by
one to two orders of magnitude compared to traditional low-/midfrequency (10s-100s KHz) sonar systems. It
is conceivable that an effective inspection strategy is the deployment of both optical and acoustic cameras
on a submersible platform, to enable target imaging in a range of turbidity conditions. Under this scenario
and where visibility allows, registration of the images from both cameras arranged in binocular stereo
configuration provides valuable scene information that cannot be readily recovered from each sensor alone.
We explore and derive the constraint equations for the epipolar geometry and stereo triangulation in utilizing
these two sensing modalities with different projection models. Theoretical results supported by computer
simulations show that an opti-acoustic stereo imaging system outperforms a traditional binocular vision with
optical cameras, particularly for increasing target distance and (or) turbidity.

PMID: 17699922 [PubMed - indexed for MEDLINE]

Regularized image recovery in scattering media.

Schechner YY, Averbuch Y.

Department of Electrical Engineering, Technion--Israel Institute of Technology, Haifa, Israel.

yoav@ee.technion.ac.il

Abstract
When imaging in scattering media, visibility degrades as objects become more distant. Visibility can be
significantly restored by computer vision methods that account for physical processes occurring during
image formation. Nevertheless, such recovery is prone to noise amplification in pixels corresponding to
distant objects, where the medium transmittance is low. We present an adaptive filtering approach that
counters the above problems: while significantly improving visibility relative to raw images, it inhibits noise
amplification. Essentially, the recovery formulation is regularized, where the regularization adapts to the
spatially varying medium transmittance. Thus, this regularization does not blur close objects. We
demonstrate the approach in atmospheric and underwater experiments, based on an automatic method for
determining the medium transmittance.

PMID: 17627052 [PubMed - indexed for MEDLINE]

Application of acoustic reflection tomography to sonar imaging.

Ferguson BG, Wyber RJ.

Maritime Operations Division-Sydney, Defence Science and Technology Organisation, PO. Box 44, Pyrmont NSW
2009, Australia. brian.ferguson@dsto.defence.gov.au

Abstract
Computer-aided tomography is a technique for providing a two-dimensional cross-sectional view of a three-
dimensional object through the digital processing of many one-dimensional views (or projections) taken at
different look directions. In acoustic reflection tomography, insonifying the object and then recording the
backscattered signal provides the projection information for a given look direction (or aspect angle).
Processing the projection information for all possible aspect angles enables an image to be reconstructed
that represents the two-dimensional spatial distribution of the object's acoustic reflectivity function when
projected on the imaging plane. The shape of an idealized object, which is an elliptical cylinder, is
reconstructed by applying standard backprojection, Radon transform inversion (using both convolution and
filtered backprojections), and direct Fourier inversion to simulated projection data. The relative merits of the
various reconstruction algorithms are assessed and the resulting shape estimates compared. For bandpass
sonar data, however, the wave number components of the acoustic reflectivity function that are outside the
passband are absent. This leads to the consideration of image reconstruction for bandpass data.
Tomographic image reconstruction is applied to real data collected with an ultra-wideband sonar transducer
to form high-resolution acoustic images of various underwater objects when the sonar and object are widely
separated.

PMID: 15957762 [PubMed - indexed for MEDLINE]

Image change detection algorithms: a systematic survey.

Radke RJ, Andra S, Al-Kofahi O, Roysam B.

Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, Troy, NY 12180,
USA. rjradke@ecse.rpi.edu

Abstract
Detecting regions of change in multiple images of the same scene taken at different times is of widespread
interest due to a large number of applications in diverse disciplines, including remote sensing, surveillance,
medical diagnosis and treatment, civil infrastructure, and underwater sensing. This paper presents a
systematic survey of the common processing steps and core decision rules in modern change detection
algorithms, including significance and hypothesis testing, predictive models, the shading model, and
background modeling. We also discuss important preprocessing methods, approaches to enforcing the
consistency of the change mask, and principles for evaluating and comparing the performance of change
detection algorithms. It is hoped that our classification of algorithms into a relatively small number of
categories will provide useful guidance to the algorithm designer.

PMID: 15762326 [PubMed - indexed for MEDLINE]

Recognizing plankton images from the shadow image particle profiling

evaluation recorder.
Luo T, Kramer K, Goldgof DB, Hall LO, Samson S, Remsen A, Hopkins T.

Department of Computer Science and Engineering, University of South Florida, Tampa, FL 33620, USA.
tluo2@csee.usf.edu

Erratum in:

• IEEE Trans Syst Man Cybern B Cybern. 2004 Dec;34(6):2423.

Abstract
We present a system to recognize underwater plankton images from the shadow image particle profiling
evaluation recorder (SIPPER). The challenge of the SIPPER image set is that many images do not have
clear contours. To address that, shape features that do not heavily depend on contour information were
developed. A soft margin support vector machine (SVM) was used as the classifier. We developed a way to
assign probability after multiclass SVM classification. Our approach achieved approximately 90% accuracy
on a collection of plankton images. On another larger image set containing manually unidentifiable particles,
it also provided 75.6% overall accuracy. The proposed approach was statistically significantly more accurate
on the two data sets than a C4.5 decision tree and a cascade correlation neural network. The single SVM
significantly outperformed ensembles of decision trees created by bagging and random forests on the
smaller data set and was slightly better on the other data set. The 15-feature subset produced by our feature
selection approach provided slightly better accuracy than using all 29 features. Our probability model gave
us a reasonable rejection curve on the larger data set.