IMTA-5 2015 Abstracts


Full Papers
Paper Nr: 1
Title:

Development of the Logic Programming Approach to the Intelligent Monitoring of Anomalous Human Behaviour

Authors:

Alexei Morozov and Alexander Polupanov

Abstract: A research software platform is developed that is based on the Actor Prolog concurrent object-oriented logic language and a state-of-the-art Prolog-to-Java translator for experimenting with the intelligent visual surveillance. We demonstrate an example of the application of the method to the monitoring of anomalous human behaviour that is based on the logical description of complex human behaviour patterns and special kinds of blob motion statistics. The logic language is used for the high-level (semantic) analysis of graphs of tracks of moving blobs; the graphs are supplied by low-level analysis algorithms implemented in a special built-in class of Actor Prolog. The blob motion statistics is collected by the low-level analysis procedures that are of the need for the discrimination of running people, people riding bicycles, and cars in a video scene. The first-order logic language is used for implementing the fuzzy logical inference based on the blob motion statistics.

Paper Nr: 4
Title:

Location of Pupil Contour by Hough Transform of Connectivity Components

Authors:

Ivan Matveev, Nikolay Chinaev and Vladimir Novik

Abstract: A method for determining the pupil boundary in the image of eye is proposed. The method is based on image binarization followed by a search of the pupil as one of the connectivity components. The pupil boundary is determined as a part of boundary of the connectivity component. Hough transform is used for separating pupil in the case of its merging in one connectivity component with other objects, as well as to verify the likelihood of solution.

Paper Nr: 6
Title:

Testing an Image Mining Approach to Obtain Pressure Ulcers Stage and Texture

Authors:

Renato V. Guadagnin, Levy Aniceto Santana and Rinaldo de Souza Neves

Abstract: Improvement of pressure ulcers (PU) images analysis through computerized techniques is advantageous both to medical assistance institutions and to patients’ life quality. The scientific challenge is to improve assistance to patients with PU by means of reliable image analysis procedures. Diagnosis of stage and predominant texture in a PU is essentially an image colour classification problem that can use existing knowledge. This study performs a classification of pressure ulcers images through an algorithm based on ID3 to construct a decision tree that has RGB statistics as input features and PU stage and texture as target features. A decision tree is constructed first by classification of 18 images of a training set. Then this tree is tested in a set of 45 PU images. Acceptable classification accuracy for training sets was not confirmed in test set.

Paper Nr: 7
Title:

On Image Representing in Image Analysis

Authors:

Igor Gurevich and Vera Yashina

Abstract: The presentation is devoted to the research of mathematical fundamentals for image analysis and recognition procedures being conducted currently in the Dorodnicyn Computing Centre of the Russian Academy of Sciences, Moscow, Russian Federation. The paper presents and discusses the main results obtained using the Descriptive Approach to Analysing and Understanding of Images when solving fundamental problems of the formalization and systematization of the methods and forms of representing information in the problems of the analysis, recognition, and understanding of images. In particular, the problems arise in connection with the automation of information extraction from images in order to make intelligent decisions (diagnostics, prediction, detection, evaluation, and identification of patterns). The final goal of this research is automated image mining: a) automated design, test and adaptation of techniques and algorithms for image recognition, estimation and understanding; b) automated selection of techniques and algorithms for image recognition, estimation and understanding; c) automated testing of the raw data quality and suitability for solving the image recognition problem.

Paper Nr: 8
Title:

A Variational Method to Remove the Combination of Poisson and Gaussian Noises

Authors:

D. N. H. Thanh and S. D. Dvoenko

Abstract: In this paper, we propose a method to remove noise in digital images. Our method is based on the wellknown variational approach. The novelty of proposed method consists in removing of mixed Poisson- Gaussian noise. This is the actual problem for many types of real raster images, for example, biomedical images. Our method is developed with the goal to combine two famous models: ROF for removing Gaussian noise and modified ROF for removing Poisson noise. As a result, our proposed method can be also applied to remove Gaussian or Poisson noise separately. We develop procedure to perform noise removal with automatically evaluated parameters to get the best result of denoising.

Paper Nr: 11
Title:

PRIAR using a Graph Segmentation Method

Authors:

M. Righi, M. D’Acunto and O. Salvetti

Abstract: Recently, we have suggested a simple and general-purpose method able to combine high-resolution analysis with the classification and identification of components of microscopy imaging. The method named PRIAR (Pattern Recognition Image Augumented Resolution) is a tool developed by the authors that gives the possibility to enhance spatial and photometric resolution of low-res images. The implemented algorithm follows the scheme: 1) image classification; 2) blind super-resolution on single frame; 3) pattern-analysis; 4) reconstruction of the discovered pattern. In this paper, we suggest some improvements of the PRIAR algorithm, in particular, the definition of a segmentation method which is based on homomorphism between a processed image and a graph describing the image itself, able to identify object of interest in complex patterns. The case study is the identification of organs inside biological cells acquired with Atomic Force Microscopy Technique.

Paper Nr: 12
Title:

Virtual Immersive Environments for Underwater Archaeological Exploration

Authors:

Massimo Magrini, Maria Antonietta Pascali, Marco Reggiannini, Ovidio Salvetti and Marco Tampucci

Abstract: In this paper we describe a system designed for the fruition of underwater archaeological sites. It is under development in the ARROWS project (end August 2015, funded by the European Commission), along with other advanced technologies and tools for mapping, diagnosing, cleaning, and securing underwater and coastal archaeological sites. The main objective is to make easier the management of the heterogeneous set of data available for each underwater archaeological site (archival and historical data, 3D measurements, images, videos, sonograms, georeference, texture and shape of artefacts, others). All the data will be represented in a 3D interactive and informative scene, making the archaeological site accessible to experts (for research purposes, e.g. classification of artefacts by template matching) and to the general public (for dissemination of the underwater cultural heritage).

Paper Nr: 13
Title:

Current Trends in Mathematical Image Analysis - A Survey

Authors:

Igor Gurevich and Vera Yashina

Abstract: The main task of the survey is to explain and discuss the opportunities and limitations of algebraic approaches in image analysis. During recent years there was accepted that algebraic techniques, in particular different kinds of image algebras, is the most prospective direction of construction of the mathematical theory of image analysis and of development an universal algebraic language for representing image analysis transforms and image models. The main goal of the Algebraic Approach is designing of a unified scheme for representation of objects under recognition and its transforms in the form of certain algebraic structures. It makes possible to develop corresponding regular structures ready for analysis by algebraic, geometrical and topological techniques. Development of this line of image analysis and pattern recognition is of crucial importance for automatic image-mining and application problems solving, in particular for diversification classes and types of solvable problems and for essential increasing of solution efficiency and quality.

Paper Nr: 14
Title:

Human Pose Estimation in Video via MCMC Sampling

Authors:

Evgeny Shalnov and Anton Konushin

Abstract: We describe a method for the human pose estimation in a video sequence. We propose a new mathematical model of a human pose in a video sequence, which incorporates motion and pose parameters. We show that the model of (Park and Ramanan, 2011) is a particular case of our model. We introduce a framework to infer an approximation of the optimal value in the proposed model. We use an exact algorithm of motion parameters estimation to reduce complexity of inference. Our approach outperforms results of (Park and Ramanan, 2011) in the most complicated video sequences.

Paper Nr: 15
Title:

Signal Processing for Underwater Archaeology

Authors:

Davide Moroni, Maria Antonietta Pascali, Marco Reggiannini and Ovidio Salvetti

Abstract: About three million wrecks lie scattered on the oceans’ seafloors. This huge patrimony is actually threatened by criminal enterprises having advanced tools available for localization and rescue operations. ARROWS, a currently ongoing EU FP7 project, is an example of the effective commitment between cultural institutions and the scientific community towards the safeguard of the sunken cultural heritage. ARROWS is devoted to advanced technologies and tools for mapping, diagnosing, cleaning, and securing underwater and coastal archaeological sites. A fleet of Autonomous Underwater Vehicles (AUVs) will be manufactured with the purpose of surveying the seabed and sensing the underwater environment by means of proper payload sensors (digital cameras, side scan and multi-beam sonars). This paper describes a set of underwater scene understanding procedures specifically tailored to the purposes addressed in the ARROWS frame. In particular the data collected by the AUVs during the acquisition campaigns will be processed to detect targets of interest located on the seabed. The main approach adopted in the object detection procedures is to highlight the amount of regularity in the captured data. This can be pursued by exploiting computer vision algorithms that perform i) the recognition of geometrical curves ii) the classification of seafloor areas by means of textural pattern analysis iii) a large scale map generation to return an overall view of the site and iv) a reliable object recognition process performing the integration of the available multi modal information. Moreover the collected raw data together with the analysis output results will be stored to allow for an offline deep analysis of the archaeological findings. This will represent a powerful tool to be used by expert users or by the general public to enjoy the underwater cultural heritage.

Paper Nr: 16
Title:

Experimenting an Embedded-sensor Network for Early Warning of Natural Risks Due to Fast Failures along Railways

Authors:

Andrea Fantini, Massimo Magrini, Salvatore Martino, Davide Moroni, Gabriele Pieri, Alberto Prestininzi and Ovidio Salvetti

Abstract: This paper deals with a project for real-time monitoring of railway tracks to detect events, such as fast failures from natural risks, which may threaten the transit of trains. The paper describes a network of smart sensors for early warning of these endangering events. Three main types of fast-failure events involving railways were identified: sinkhole, rock and debris falls. A case study on a known test site and experimentation with various scenarios were carried out with a view to developing algorithms capable of spotting and localising them. Results demonstrate the good performance of the network in monitoring the investigated events.

Paper Nr: 17
Title:

Selective Use of Optimal Image Resolution for Depth from Multiple Motions based on Gradient Scheme

Authors:

Norio Tagawa and Shoei Koizumi

Abstract: The gradient-based depth from motion method is effective for obtaining a dense depth map. However, the accuracy of the depth map recovered only from two successive images is not so high, and hence, to increase the depth information by tracking corresponding image points through an image sequence is often performed by using, for example, the Kalman filter-like technique. Alternatively, multiple image pairs generated by random small camera rotations around a reference direction can be used for gaining much information of depth without such the tracking procedure. In the framework of this strategy, in this study, to further improve the accuracy, we propose a selective use of the optimal image resolution. The appropriate resolution image is required to have a linear intensity pattern which is the most important supposition for the gradient method often used for dense depth recovery based on the theory of “shape from motion.” The performance of our proposal is examined through numerical evaluations using artificial images.

Short Papers
Paper Nr: 2
Title:

Determination of Direction and Velocity of the Objects

Authors:

Vasiliy N. Kruglov, Artem V. Kruglov and Uriy V. Chiryshev

Abstract: In this paper the analysis of methods for determination the direction and velocity of the objects is given. As applied to the problem of geometry assessment for round timber the optimum by the ratio of accuracy and performance is phase correlation method. Nonetheless the pointed problem requires better accuracy and validity, so we had to improve this method and adapt it to the concrete conditions. Modified algorithm was tested on the image database of real technological process of round timber movement on the conveyer belt. The offered method has shown its high effectiveness and validity.

Paper Nr: 9
Title:

Blood Flow Prediction and Visualization within the Aneurysm of the Middle Cerebral Artery after Surgical Treatment

Authors:

Artem Yatchenko, Andrey Gavrilov, Elena Boldyreva, Ivan Arkhipov, Elena Grigorieva, Ivan Godkov and Vladimir Krylov

Abstract: All cerebral aneurysms have the potential to rupture and cause bleeding within the brain. To understand the tactics of treatment of patients with intracranial aneurysms, it is necessary to study in detail the pressure and flow within the aneurysm and vessels. Numerical modelling is a powerful tool for blood flow study, prediction and visualisation. In this paper the method that uses patient-oriented physiological model to determine the numerical modelling parameters is proposed. The experiments were carried out on the real geometry of the patient with two aneurisms of the middle cerebral artery and showed that the proposed methods improves the quality of the surgical planning.

Paper Nr: 10
Title:

Parallel Version n-Dimensional Fast Fourier Transform Algorithm - Analog of the Cooley-Tukey Algorithm

Authors:

M. V. Noskov and V. S. Tutatchikov

Abstract: One-, two- and three-dimensional fast Fourier transform (FFT) algorithms has been widely used in digital processing. Multi-dimensional discrete Fourier transform is reduced to a combination of one-dimensional FFT for all coordinates due to the increased complexity and the large amount of computation by increasing the dimensional of the signal. This article provides a general Cooley-Tukey algorithm analog, which requires less complex operations of additional and multiplication than the standard method, and runs 1.5 times faster than analogue in Matlab.