Corneliu Toma

Bio: Corneliu Toma is an academic researcher from Politehnica University of Timișoara. The author has contributed to research in topics: Mean-shift & Image registration. The author has an hindex of 4, co-authored 15 publications receiving 89 citations.

A fast algorithm for background tracking in video surveillance, using nonparametric kernel density estimation

Abstract: Moving object detection and tracking in video surveillance systems is commonly based on background estimation and subtraction. For satisfactory performance in real world applications, robust estimators, tolerating the presence of outliers in the data, are needed. Nonparametric kernel density estimation has been successfully used in modeling the background statistics due to its capability to perform well without making any assumption about the form of the underlying distributions. However, in real-time applications, the O(N2) complexity of the method can be a bottleneck preventing the object tracking and event analysis modules from having the computing time needed. In this paper, we propose a new background subtraction technique, using multiresolution and recursive density estimation with mean shift based mode tracking. An algorithm with complexity independent on N is developed for fast, real-time implementation. Comparative results with known methods are included, in order to attest the effectiveness and quality of the proposed approach.

Computer aided diagnosis method for steatosis rating in ultrasound images using random forests

Abstract: In this paper we discuss the problem of computer aided evaluation of the severity of steatosis disease using ultrasound images, the aim of the study being to compare the automatic evaluation of liver steatosis using random forests (RF) and support vector machine (SVM) classifiers. Material and method: One hundred and twenty consecutive patients with steatosis or normal liver, assessed by ultrasound by the same expert, were enrolled. We graded steatosis in four stages and trained two classifiers to rate the severity of disease, based on a large set of labeled images and a large set of features, including several features obtained by robust estimation techniques. We compared RF and SVM classifiers. The classifiers were trained using cross-validation. There was 80% of data randomly selected for training and 20% for testing the classifier. This procedure was performed 20 times. The main measure of performance was the accuracy. Results: From all cases, 10 were rated as normal liver, 70 as hav ing mild, 33 moderate, and 7 severe steatosis. Our best experts’ ratings were used as ground truth data. RF outperformed the SVM classifier and confirmed the ability of this classifier to perform well without feature selection. In contrast, the performance of the SVM classifier was poor without feature selection and improved significantly after feature selection. Conclusion: The ability and accuracy of RF to classify well the steatosis severity, without feature selection, were superior as compared to SVM.

Using Registration Algorithms for Wireless Sensor Network Node Localization

Abstract: This paper investigates the possibility of using image registration techniques to solve node localization problem in a wireless sensor network based on video sensors. Moreover, the proposed solution adds video-field overlap estimation to classical spatial localization. Several registration algorithms are analyzed and tested for performance evaluation.

Automatic evaluation of steatosis by ultrasound image analysis

Abstract: This paper presents a new method for computer based diagnosis in liver steatosis diagnosis. The effectiveness of several image features extracted by robust estimation in conjunction with a random forests classifier for steatosis stage assessment is proved. We found that a successive dichotomy approach using random forests leads to better diagnosis than simultaneous classification with random forests.

Fast and accurate background subtraction for video surveillance, using an adaptive mode -tracking algorithm

Abstract: Background estimation and subtraction is a critical and time consuming step in moving object segmentation for video surveillance. Nonparametric kernel density estimation has been successfully used in modeling the background statistics, due to its capability to perform well without making any assumption about the form of the underlying distributions. To obtain real-time performance of the nonparametric estimator, we recently proposed an algorithm based on mean shift mode-tracking and a rough histogram test to fast discard foreground pixels from exact evaluation. In the present work, an improvement of the new algorithm is proposed, leading to faster background change tracking capability and more accurate background estimation.

Recent Advanced Statistical Background Modeling for Foreground Detection - A Systematic Survey

Abstract: Background modeling is currently used to detect moving objects in video acquired from static cameras. Numerous statistical methods have been developed over the recent years. The aim of this paper is firstly to provide an extended and updated survey of the recent researches and patents which concern statistical background modeling and secondly to achieve a comparative evaluation. For this, we firstly classified the statistical methods in terms of category. Then, the original methods are reminded and discussed following the challenges met in video sequences. We classified their respective improvements in terms of strategies used. Furthermore, we discussed them in terms of the critical situations they claim to handle. Finally, we conclude with several promising directions for future research. The survey also discussed relevant patents.

Independent Component Analysis-Based Background Subtraction for Indoor Surveillance

Abstract: In video surveillance, detection of moving objects from an image sequence is very important for target tracking, activity recognition, and behavior understanding. Background subtraction is a very popular approach for foreground segmentation in a still scene image. In order to compensate for illumination changes, a background model updating process is generally adopted, and leads to extra computation time. In this paper, we propose a fast background subtraction scheme using independent component analysis (ICA) and, particularly, aims at indoor surveillance for possible applications in home-care and health-care monitoring, where moving and motionless persons must be reliably detected. The proposed method is as computationally fast as the simple image difference method, and yet is highly tolerable to changes in room lighting. The proposed background subtraction scheme involves two stages, one for training and the other for detection. In the training stage, an ICA model that directly measures the statistical independency based on the estimations of joint and marginal probability density functions from relative frequency distributions is first proposed. The proposed ICA model can well separate two highly-correlated images. In the detection stage, the trained de-mixing vector is used to separate the foreground in a scene image with respect to the reference background image. Two sets of indoor examples that involve switching on/off room lights and opening/closing a door are demonstrated in the experiments. The performance of the proposed ICA model for background subtraction is also compared with that of the well-known FastICA algorithm.

Statistical Background Modeling for Foreground Detection: A Survey

Abstract: Background modeling is often used in the context of moving objects detection from static cameras. Numerous methods have been developed over the recent years and the most used are the statistical ones. The purpose of this chapter is to provide a recent survey of these different statistical methods. For this, we have classified them in term of generation following the years of publication and the statistical tools used. We then focus on the first generation methods: Single Gaussian, Mixture of Gaussians, Kernel Density Estimation and Subspace Learning using PCA. These original methods are reminded and then we have classified their different improvements in term of strategies. After analyzing the strategies and identifying their limitations, we conclude with several promising directions for future research.