Arie Nakhmani

A new distance measure based on generalized Image Normalized Cross-Correlation for robust video tracking and image recognition

We propose two novel distance measures, normalized between 0 and 1, and based on normalized cross-correlation for image matching. These distance measures explicitly utilize the fact that for natural images there is a high correlation between spatially close pixels. Image matching is used in various computer vision tasks, and the requirements to the distance measure are application dependent. Image recognition applications require more shift and rotation robust measures. In contrast, registration and tracking applications require better localization and noise tolerance. In this paper, we explore different advantages of our distance measures, and compare them to other popular measures, including Normalized Cross-Correlation (NCC) and Image Euclidean Distance (IMED). We show which of the proposed measures is more appropriate for tracking, and which is appropriate for image recognition tasks.

Quantifying liver fibrosis through the application of texture analysis to diffusion weighted imaging

The purpose of this study was to evaluate the potential utility of texture analysis of parametric apparent diffusion coefficient (ADC) maps in quantifying hepatic fibrosis. To this end, using ex vivo murine liver tissues from a dietary model of hepatic fibrosis, an array of texture analysis techniques, including histogram-based, gray-level co-occurrence matrix-based, and gray-level run-length-based features, was used to evaluate correlations with liver fibrosis. Moderate to very strong correlation between several of the texture-based features and both subjective as well as digital image analysis-based assessments of hepatic fibrosis was demonstrated. This rigorous study of texture analysis applied to parametric ADC maps in a liver fibrosis model study demonstrates and validates the potential utility of texture-based features for the noninvasive, quantitative assessment of hepatic fibrosis.

Self-Crossing Detection and Location for Parametric Active Contours

Active contours are very popular tools for video tracking and image segmentation. Parameterized contours are used due to their fast evolution and have become the method of choice in the Sobolev context. Unfortunately, these contours are not easily adaptable to topological changes, and they may sometimes develop undesirable loops, resulting in erroneous results. To solve such topological problems, one needs an algorithm for contour self-crossing detection. We propose a simple methodology via simple techniques from differential topology. The detection is accomplished by inspecting the total net change of a given contours angle, without point sorting and plane sweeping. We discuss the efficient implementation of the algorithm. We also provide algorithms for locating crossings by angle considerations and by plotting the four-connected lines between the discrete contour points. The proposed algorithms can be added to any parametric active-contour model. We show examples of successful tracking in real-world video sequences by Sobolev active contours and the proposed algorithms and provide ideas for further research.

Generalized Nyquist Criterion and Generalized Bode Diagram for Analysis and Synthesis of Uncertain Control Systems

Uncertainties in control systems models often have to be taken into account in their analysis and/or design. Negligence of such uncertainties is often unjustifiable and is done only due to lack of methods to treat the uncertainties. The presented work is concerned with analysis and design of interval uncertainty control systems, with regard to clustering of poles inside a simple symmetric bounded contour ¿. We extend the well known Nyquist and Mikhailov stability theorems to ¿ - stability tests of uncertain systems, defined by their generalized Bode envelopes. Also, using generalized definitions and theorems we solve the design problem of a controller which ensures clustering of closed loop poles of an interval uncertain family of transfer functions inside such prescribed ¿ -region.

Tracking through changes in scale

We propose a tracking system that is especially well-suited to tracking targets which change drastically in size or appearance. To accomplish this, we employ a fast, two phase template matching algorithm along with a periodic template update method. The template matching step ensures accurate localization while the template update scheme allows the target model to change over time along with the appearance of the target. Furthermore, the algorithm can deliver real-time results even when targets are very large. We demonstrate the proposed method with good results on several sequences showing targets which exhibit large changes in size, shape, and appearance.

Automated Image Analysis of FRET Signals for Subcellular cAMP Quantification

A variety of FRET probes have been developed to examine cAMP localization and dynamics in single cells. These probes offer a readily accessible approach to measure localized cAMP signals. However, given the low signal-to-noise ratio of most FRET probes and the dynamic nature of the intracellular environment, there have been marked limitations in the ability to use FRET probes to study localized signaling events within the same cell. Here, we outline a methodology to dissect kinetics of cAMP-mediated FRET signals in single cells using automated image analysis approaches. We additionally extend these approaches to the analysis of subcellular regions. These approaches offer an unique opportunity to assess localized cAMP kinetics in an unbiased, quantitative fashion.

MRI Brain Tumor Segmentation and Necrosis Detection Using Adaptive Sobolev Snakes

Brain tumor segmentation in brain MRI volumes is used in neurosurgical planning and illness staging. It is important to explore the tumor shape and necrosis regions at di erent points of time to evaluate the disease progression. We propose an algorithm for semi-automatic tumor segmentation and necrosis detection. Our algorithm consists of three parts: conversion of MRI volume to a probability space based on the on-line learned model, tumor probability density estimation, and adaptive segmentation in the probability space. We use manually selected acceptance and rejection classes on a single MRI slice to learn the background and foreground statistical models. Then, we propagate this model to all MRI slices to compute the most probable regions of the tumor. Anisotropic 3D di usion is used to estimate the probability density. Finally, the estimated density is segmented by the Sobolev active contour (snake) algorithm to select smoothed regions of the maximum tumor probability. The segmentation approach is robust to noise and not very sensitive to the manual initialization in the volumes tested. Also, it is appropriate for low contrast imagery. The irregular necrosis regions are detected by using the outliers of the probability distribution inside the segmented region. The necrosis regions of small width are removed due to a high probability of noisy measurements. The MRI volume segmentation results obtained by our algorithm are very similar to expert manual segmentation.

Anomaly detection in videos: A dynamical systems approach

We demonstrate a dynamical system framework based on motion patterns for detecting anomalous individual and group behavior in complex videos. We first describe a framework based on trajectory modeling, in which coarse statistical models are used to capture global motion patterns, and are employed in change detection to identify anomalous behavior at the object level. Our multi-target tracking framework combines geometric active contours with particle filtering to effectively deal with occlusions and clutter in the environment. In crowded scenes, however, such object level representation can become extremely unreliable: to deal with this we instead use of low-level motion features (e.g., optical flow) to capture group behavior. To keep the problem tractable, we utilize a subspace system identification method based on the Hankel matrix to extract relevant low order dynamics of these noisy features. The spectral properties of the Hankel matrix encode useful information about the dynamics, and can detect anomalous group behavior. In order to efficiently compute these spectral properties, we employ a randomized algorithm for singular value decomposition. Both approaches are demonstrated to robustly detect anomalous behavior in realistic indoor and outdoor videos.

Particle filtering using multiple cross-correlations for tracking occluded objects in cluttered scenes

This paper is concerned with the tracking of partially or entirely occluded objects in a video sequence. We propose certain modifications to the template matching approach, which seem to fit the type of tracking data being considered in the present note. Specifically, we will use a nonstandard particle filtering method via the following two steps: The first step employs the normalized cross-correlation function as the likelihood. The second step is to resample, and to fuse the results of multiple cross-correlations of different patches of the given object, in order to refine the likelihood for the particle filter. Experimental results show that the method is reliable for noisy measurements, and provides accurate results in cases of occlusion or heavy shadows.

Particle Filtering with Region-based Matching for Tracking of Partially Occluded and Scaled Targets

Visual tracking of arbitrary targets in clutter is important for a wide range of military and civilian applications. We propose a general framework for the tracking of scaled and partially occluded targets, which do not necessarily have prominent features. The algorithm proposed in the present paper utilizes a modified normalized cross-correlation as the likelihood for a particle filter. The algorithm divides the template, selected by the user in the first video frame, into numerous patches. The matching process of these patches by particle filtering allows one to handle the targets occlusions and scaling. Experimental results with fixed rectangular templates show that the method is reliable for videos with nonstationary, noisy, and cluttered background, and provides accurate trajectories in cases of target translation, scaling, and occlusion.