Jabłoński, Mirosław
Loading...
Email Address
Employee
aktywny
Alternative name
Discipline
automatyka, elektronika, elektrotechnika i technologie kosmiczne
Author Profiles
Systemy AGH
13 results
Filters
Advanced Search
Filter by
Settings
Search Results
Now showing 1 - 10 of 13
Item type:Article, Access status: Open Access , Rozszerzenia SIMD w przetwarzaniu obrazów(Wydawnictwa AGH, 2008) Bubliński, Zbigniew; Jabłoński, MirosławThe paper presents an attempt to utilize the SIMD extensions, available in modern processor architectures, in order to minimize image processing time. In particular, the effect of MMX and SSE instructions on the digital image brightness (intensity) modification algorithm was investigated in detail. All experiments were performed in 'VirtualDub' environment. The results, i.e. processing times, were compared with those obtained from an algorithm written in plain C language.Item type:Article, Access status: Open Access , Modelowanie i realizacja algorytmów wideodetekcji na platformie FPGA(Wydawnictwa AGH, 2006) Gorgoń, Marek; Pawlik, Piotr; Jabłoński, Mirosław; Przybyło, JaromirIn the present paper the background generation and motion detection algorithms, which are of key importance for the implementation of videodetection, has been presented. A modification of the background generation algorithm, allowing for a proper algorithm functioning at medium and high traffic conditions, has been proposed. An adaptation of the algorithm for implementation in the reprogrammable device has been presented. A modification of the SAD algorithm, used for motion detection has been introduced. The modification allows for unrestricted defining of 32 Regions of Interest of irregular shape and structure in the analyzed image. It gives a capability to conduct the calculation in independent and parallel manner for particular, user-defined, active videodetection regions.Item type:Article, Access status: Open Access , Badanie zdolności percepcji przestrzennej sceny akustycznej u ludzi(Wydawnictwa AGH, 2008) Wołoszyn, Paweł; Jabłoński, Mirosław; Malicki, ŁukaszHuman ability to discern sounds coming from different locations is based on interaural differences and head-related filtration of acoustic signals. It allows to precisely localize a single sound source with high acuity. Our research focuses on more difficult task of perceiving and recognizing complex spatial sound patterns consisting of several acoustic signals emitted simultaneously from multiple sources. In this paper we describe our hardware platform used to perform such psychoacoustic experiments. We also discuss the results of some experiments performed to check what requirements must be met in order to make perception of spatial sound scene possible.Item type:Article, Access status: Open Access , Stanowisko wizyjnego śledzenia odkształceń metalu w procesie obróbki plastycznej na zimno(Wydawnictwa AGH, 2010) Pociecha, Daniel; Jabłoński, MirosławThe paper presents metal deformation trace vision station, in cold tube pilger rolling process. Aluminium tube was prepared, with cooper grid on their surface. Measurement of metal deformation is possible, when grid point's displacement is traced. During rolling process, photos were taken. Using those photos, three-dimensional coordinates of tube grid points were determinate. Stereophotogrammetric method was used to point's coordinate's calculation. Before stereophotogrammetric calculation, annotation of all points which are visible on photos is essential. Two methods of point annotation - manual and automatic - are presented in paper.Item type:Article, Access status: Open Access , Analiza sekwencji filmowych w środowisku VirtualDub w oparciu o platformę FPGA(Wydawnictwa AGH, 2006) Bubliński, Zbigniew; Jabłoński, Mirosław; Mikrut, ZbigniewThis paper describes the method of linear components labelling. Real and artificially generated sequences of frames were used as source of input images, and labelling was conducted in Virtual-Dub environment as processing of movie with VirtualDub filters. One filter is a pure software implementation of labelling algorithm, and the other is hardware implementation based on FPGA circuit. The detailed comparison of results obtained during analysis of selected video sequences is presented.Item type:Article, Access status: Open Access , Automatyczna anotacja znaczników sztyftowych w procesie walcowania pielgrzymowego rur na zimno(Wydawnictwa AGH, 2010) Jabłoński, Mirosław; Pociecha, DanielA system of automatic calculation of characteristic points in the process of tube cold rolling process has been presented. The very basic problem that has been addressed in this paper was a method of segmentation of particular regions in high resolution images i.e. reference board, tube area, and copper pin-markers. Three methods of adaptive thresholding have been examined for each type of object. Through application of computer vision algorithms duration of annotation phase has been greatly reduced in comparison to manual method.Item type:Article, Access status: Open Access , Detekcja markerów dla celów automatycznej anotacji mimiki twarzy(Wydawnictwa AGH, 2006) Przybyło, Jaromir; Jabłoński, Mirosław; Wołoszyn, PawełIn this paper we present an approach to automatic annotation of face image features utilizing markers. Markers are located on adequate facial regions and are acquired using color camera. Location and topology of markers has been determined utilizing knowledge of facial morphology and facial action units. We design algorithm of marker detection, as well as method of results verification. Also, analysis of detection and verification algorithms results has been performed. The goal of our work is to use proposed approach to create facial database for evaluation facial expression recognition, without need of manual annotation of image features.Item type:Article, Access status: Open Access , Integracja toru wizyjnego na platformie rekonfigurowalnej(Wydawnictwa AGH, 2008) Jabłoński, Mirosław; Bubliński, ZbigniewThe research includes the review and classification of computing platforms types suitable for streambased operation and embedded vision system. Experimental, integrated vision pipeline includes advanced image sensor and reprogrammable circuit. Criteria for evaluation of stream based video processing system have been defined and applied to edge detector application.Item type:Article, Access status: Open Access , Akceleracja algorytmów przetwarzania obrazów z wykorzystaniem zasobów karty graficznej(Wydawnictwa AGH, 2009) Jabłoński, Mirosław; Bubliński, ZbigniewThe paper presents an attempt to utilize the graphics card resources for acceleration of selected image processing operations. The use of tools obtained from NVIDIA for GeForce graphics cards series makes it possible to distribute a computational task on threads executed by GPU floating-point cores. Execution times of parallelized operations were measured and compared with execution time of single-threaded program ran on CPU. Also, the speed-up factors (acceleration factors) were calculated.Item type:Article, Access status: Open Access , Automatyczna segmentacja twarzy dla potrzeb interfejsu człowiek-komputer(Wydawnictwa AGH, 2005) Jabłoński, Mirosław; Przybyło, Jaromir; Wołoszyn, PawełEfficient face detection and localization is a basic functionality needed for face gesture recognition in visual human-computer interfaces. Existing approaches to face localization are based on skin segmentation. However additional analysis is required when using popular, Iow quality cameras. This paper describes color-based face segmentation algorithm with automatic calibration of skin-color model parameters, using flash illumination. Proposed algorithm allows to increase efficiency of face segmentation.