Oleg Starostenko

Wavelet-based smoke detection in outdoor video sequences

In this paper an approach to detect smoke columns from outdoor forest video sequences is proposed. The approach follows three basic steps. The first step is an image pre-processing block which resizes the image by applying a bicubic interpolation algorithm. The image is then transformed to its intensity values with a gray-scale transformation and finally the image is grouped by common areas with an image indexation. The second step consists of a smoke detection algorithm which performs a stationary wavelet transform (SWT) to remove high frequencies on horizontal, vertical, and diagonal details. The inverse SWT is then implemented and finally the image is compared to a non-smoke scene in order to determine the possible regions of interest (ROI). In order to reduce the number of false alarms, the final step of the proposed approach consists on a smoke verification algorithm, which determines whether the ROI is increasing its area or not. These results are combined to reach a final decision for detecting a smoke column on a sequence of static images from an outdoor video. Experimental results show that multi-resolution wavelet analysis is more accurate than the traditional low-pass filters on this application.

3D laser scanning vision system for autonomous robot navigation

The presented Technical Vision System realizes the principle of dynamic triangulation. This technique is able to resolve in real time a triple task: to detect a presence of significant obstacle in a robots neighborhood; locate its position in a robots field-of-view; obtain in a short time a digital map of the obstacle visible surface with metrological accuracy of coordinates and adjustable step of discretization. Some aspects of theoretical backgrounds, technical design, optical principle, mathematical framework, signal processing, prototype design and experimentation are presented in this paper.

Resolution improvement of dynamic triangulation method for 3D vision system in robot navigation task

This paper presents a technical vision system designed to resolve multiple tasks which are fundamental for autonomous navigation. These tasks include detecting the presence of a significant obstacle for a mobile robot, locate its position in the mobile robots field of view and create a digital map of the obstacles visible surface with metrological accuracy. This technical vision system has been introduced and explained in other publications; therefore this paper focuses mostly on signal conditioning, processing and resolution increase for mobile robot navigation.

Breaking reCAPTCHAs with unpredictable collapse: heuristic character segmentation and recognition

In this paper we present a novel approach for automatic segmentation and recognition of reCAPTCHA in Web sites. It is based on CAPTCHA image preprocessing with character alignment, morphological segmentation with three-color bar character encoding and heuristic recognition. The original proposal consists in exploiting three-color bar code for characters in CAPTCHA for their robust segmentation with presence of random collapse overlapping letters and distortions by particular patterns of waving rotation. Additionally, a novel implementation of SVM-based learning classifier for recognition of combinations of characters in training corpus has been proposed that permits to increment more than twice the recognition success rate without time extension of system response. The main goal of this research is to reduce vulnerability of CAPTCHA from spam and frauds as well as to provide a novel approach for recognizing either handwritten or degraded and damaged texts in ancient manuscripts. Our designed framework implementing the proposed approach has been tested in real-time applications with sites used CAPTCHAS achieving segmentation success rate about of 82% and recognition success rate about of 94%.

Remote Sensor for Spatial Measurements by Using Optical Scanning

In this paper, we propose a low-cost contact-free measurement system for both 3-D data acquisition and fast surface parameter registration by digitized points. Despite the fact that during the last decade several approaches for both contact-free measurement techniques aimed at carrying out object surface recognition and 3-D object recognition have been proposed, they often still require complex and expensive equipment. Therefore, alternative low cost solutions are in great demand. Here, two low-cost solutions to the above-mentioned problem are presented. These are two examples of practical applications of the novel passive optical scanning system presented in this paper.

Automotive FDS Resolution Improvement by Using the Principle of Rational Approximation

In this paper, a novel method of frequency counting of signals coming from automotive sensors is presented. The present method helps to improve fast resolution of output parameters of typical automotive frequency-domain sensors (FDS). Controlling the electromechanical systems in todays cars is a task that requires a high processing speed. The method proposed here has been tested under computer experiments, and theoretical results have shown that it meets the requirements of speed of response and offset error of the parameters under measurement. Here, both a principle of rational approximation and its application to fast registration of frequency changes in the signal that is proportional to the physical parameter under measurement are shown. Finally, some experimental results are shown as well.

Facial feature model for emotion recognition using fuzzy reasoning

In this paper we present a fuzzy reasoning system that can measure and recognize the intensity of basic or non-prototypical facial expressions. The system inputs are the encoded facial deformations described either in terms of Ekmans Action Units (AUs) or Facial Animation Parameters (FAPs) of MPEG-4 standard. The proposed fuzzy system uses a knowledge base implemented on knowledge acquisition and ontology editor Protege. It allows the modeling of facial features obtained from geometric parameters coded by AUs - FAPs and also the definition of rules required for classification of measured expressions. This paper also presents the designed framework for fuzzyfication of input variables for fuzzy classifier based on statistical analysis of emotions expressed in video records of standard Cohn-Kanades and Pantics MMI face databases. The proposed system has been tested in order to evaluate its capability for detection, classifying, and interpretation of facial expressions.

Ontological shape-description, a new method for visual information retrieval

There is a growing need for efficient visual information retrieval systems which take into account particular features of images, in order to avoid nonsensical results. We propose a new method for content-based image retrieval, which can be divided into two main parts: 1) automatic segmentation and extraction of shapes from image sub-regions; 2) ontological descriptions of shapes contained in the images. Our method allows users to perform sketch queries; these are simple drawings which represent the main idea of something the user is expecting to retrieve from the results. Once the user introduces a sketch, it is simplified using discrete curve evolution; then it is turned into a tangent space representation. Similarity measures based on turning functions are used to recover similar images. Ontology reduces the proportion of nonsensical results since it permits the recovery of images related semantically, even if they do not have similar shapes.

Organizing open archives via lightweight ontologies to facilitate the use of heterogeneous collections

Purpose – This paper seeks to focus on the problems of integrating information from open, distributed scholarly collections, and on the opportunities these collections represent for research communities in developing countries. The paper aims to introduce OntOAIr, a semi‐automatic method for constructing lightweight ontologies of documents in repositories such as those provided by the Open Archives Initiative (OAI).Design/methodology/approach – OntOAIr uses simplified document representations, a clustering algorithm, and ontological engineering techniques.Findings – The paper presents experimental results of the potential positive impact of ontologies and specifically of OntOAIr on the use of collections provided by OAI.Research limitations/implications – By applying OntOAIr, scholars who frequently spend many hours organizing OAI information spaces will obtain support that will allow them to speed up the entire research cycle and, expectedly, participate more fully in global research communities.Original...

Foveated ROI compression with hierarchical trees for real-time video transmission

Region of interest (ROI) based compression can be applied to real-time video transmission in medical or surveillance applications where certain areas are needed to retain better quality than the rest of the image. The use of a fovea combined with ROI for image compression can help to improve the perception of quality and preserve different levels of detail around the ROI. In this paper, a fovea-ROI compression approach is proposed based on the Set Partitioning In Hierarchical Tree (SPIHT) algorithm. Simulation results show that the proposed approach presents better details in objects inside the defined ROI than the standard SPIHT algorithm.