Depth image acquisition with structured light approaches in outdoor environments is a challenging problem due to external factors, such as ambient sunlight, which commonly affect the acquisition ...procedure. This paper presents a novel structured light sensor designed specifically for operation in outdoor environments. The sensor exploits a modulated sequence of structured light projected onto the target scene to counteract environmental factors and estimate a spatial distortion map in a robust manner. The correspondence between the projected pattern and the estimated distortion map is then established using a probabilistic framework based on graphical models. Finally, the depth image of the target scene is reconstructed using a number of reference frames recorded during the calibration process. We evaluate the proposed sensor on experimental data in indoor and outdoor environments and present comparative experiments with other existing methods, as well as commercial sensors.
This work discusses a novel approach to image acquisition which improves the robustness of captured data required for 3D range measurements. By applying a pseudo-random code modulation to sequential ...acquisition of projected patterns the impact of environmental factors such as ambient light and mutual interference is significantly reduced. The proposed concept has been proven with an experimental range sensor based on the laser triangulation principle. The proposed design can potentially enhance the use of this principle to a variety of outdoor applications, such as autonomous vehicles, pedestrians' safety, collision avoidance, and many other tasks, where robust real-time distance detection in real world environment is crucial.
This work discusses an innovative approach to imaging which can improve the robustness of existing active-range measurement methods and potentially enhance their use in a variety of outdoor ...applications. By merging a proven modulation technique from the domain of spread-spectrum communications with the bleeding-edge CMOS sensor technology, the prototype of the modulated range sensor is designed and evaluated. A suitable set of application-specific spreading codes is proposed, evaluated and tested on the prototype. Experimental results show that the introduced modulation technique significantly reduces the impacts of environmental factors such as sunlight and external light sources, as well as mutual interference of identical devices. The proposed approach can be considered as a promising basis for a new generation of robust and cost-efficient range-sensing solutions for automotive applications, autonomous vehicles or robots.
Računalniški modeli končnih pretvornikov omogočajo zgoščeno predstavitev slovarjev izgovarjav, ki jih uporabljajo tako sintetizatorji govora kot tudi razpoznavalniki govora. V članku je predstavljen ...nov tip končnih pretvornikov, t. i. končni super pretvorniki, s katerimi lahko slovarje izgovarjav predstavimo z manjšim številom stanj in prehodov kot z uporabo običajnih minimalnih determinističnih končnih pretvornikov. Predstavljen je učinkovit postopek gradnje končnih super pretvornikov, ki ohranjajo svojo determinističnost, poleg besed iz danega slovarja izgovarjav pa lahko sprejmejo in pretvorijo tudi nekatere druge besede, ki niso bile zastopane v izvirnem slovarju. Oddani izhodni fonetični prepisi za določene sprejete izvenslovarske besede so sicer lahko napačni, vendar se izkaže, da je napaka pri pretvorbi primerljiva z napakami, ki jih dosegajo trenutno najboljše metode za samodejno grafemsko-fonemsko pretvorbo besed za slovenski jezik. Za preizkus in preverjanje predlaganega postopka gradnje končnih super pretvornikov je bil uporabljen slovar izgovarjav SI-PRON za slovenski jezik, ki vsebuje več kot milijon različnih slovarskih vnosov. Rezultati poskusov so med drugim podali presenetljivo ugotovitev, da se velikost končnih pretvornikov z naraščanjem obsega slovarja prek določenega števila besed prične zmanjševati, kar pripisujemo predvsem velikemu številu pregibnih oblik besed v slovenščini.
Finite-state transducers are frequently used for pronunciation lexicon representations in speech engines, in which memory and processing resources are scarce. This paper proposes two possibilities ...for further reducing the memory footprint of finite-state transducers representing pronunciation lexicons. First, different alignments of grapheme and allophone transcriptions are studied and a reduction in the number of states of up to 30% is reported. Second, a combination of grapheme-to-allophone rules with a finite-state transducer is proposed, which yields a 65% smaller finite-state transducer than conventional approaches.
This paper proposes a novel approach to light plane labeling in depth-image sensors relying on "uncoded" structured light. The proposed approach adopts probabilistic graphical models (PGMs) to solve ...the correspondence problem between the projected and the detected light patterns. The procedure for solving the correspondence problem is designed to take the spatial relations between the parts of the projected pattern and prior knowledge about the structure of the pattern into account, but it also exploits temporal information to achieve reliable light-plane labeling. The procedure is assessed on a database of light patterns detected with a specially developed imaging sensor that, unlike most existing solutions on the market, was shown to work reliably in outdoor environments as well as in the presence of other identical (active) sensors directed at the same scene. The results of our experiments show that the proposed approach is able to reliably solve the correspondence problem and assign light-plane labels to the detected pattern with a high accuracy, even when large spatial discontinuities are present in the observed scene.
To analyze the presence of malignancy associated changes (MACs) in normal buccal mucosa cells of lung and breast cancer patients and their relationship to tumor subtype, stage and size.
Buccal mucosa ...smears of 107 lung cancer and 100 breast cancer patients and corresponding healthy subjects were collected, stained by the DNA-specific Feulgen-thionin method and scanned using an automated high-resolution cytometer. Nuclear texture features of a minimum of 500 nuclei per slide were calculated, and statistical classifiers using Gaussian models of class-probability distribution were designed, trained and tested in 3 parts: (1) ability to separate cancer patient samples from controls, (2) cross-validation of classifiers for different cancer types, and (3) correlation of MAC expression with tumor subtype, stage and size.
Lung and breast cancer induce MACs in normal buccal mucosa cells. The classifiers based on the selected nuclear features correctly recognized >80% of lung and breast cancer cases. The results indicate that MAC detection is not dependent on the tumor subtype, stage or size.
The presence of MACs in buccal mucosa cells offers the potential for developing a new noninvasive cancer screening test.
This paper presents a method for selecting speech units for polyphone concatenative speech synthesis, in which the simplification of procedures for search paths in a graph accelerated the speed of ...the unit-selection procedure with minimum effects on the speech quality. The speech units selected are still optimal; only the costs of merging the units on which the selection is based are less accurately determined. Due to its low processing power and memory footprint requirements, the method is suitable for use in embedded speech synthesizers.
The aim of the study was to determine optimal hydrolysis time for the Feulgen DNA staining of archival formalin fixed paraffin-embedded surgical samples, prepared as single cell suspensions for image ...cytometric measurements. The nuclear texture features along with the IOD (integrated optical density) of the tumor nuclei were analysed by an automated high resolution image cytometer as a function of duration of hydrolysis treatment (in 5 N HCl at room temperature). Tissue blocks of breast carcinoma, ovarian serous carcinoma, ovarian serous tumor of borderline malignancy and leiomyosarcoma were included in the study. IOD hydrolysis profiles showed plateau between 30 and 60 min in the breast carcinoma and leiomyosarcoma, and between 40 and 60 min in the ovarian serous carcinoma and ovarian serous tumor of borderline malignancy. Most of the nuclear texture features remained stable after 20 min of hydrolysis treatment. Our results indicate that the optimal hydrolysis time for IOD and for nuclear texture feature measurements, was between 40 and 60 min in the cell preparations from tissue blocks of three epithelial and one soft tissue tumor.
To test the discriminatory capability of nuclear features in the subclassification of rhabdomyosarcoma (RMS) and especially to differentiate embryonal from alveolar RMS.
The study included 42 ...patients with RMS. We performed the analysis on Feulgen-stained filtrates of cell suspensions prepared from deparaffinized tissue sections. Image analysis was performed by an automated, high-resolution image cytometer on at least 200 nuclear images. Photometric, morphometric and nuclear texture features were analyzed. Probability density distributions were calculated for each nuclear feature of individual RMS subgroups and compared in order to detect possible differences.
There were significant differences between embryonal and alveolar RMS in five nuclear features: DNA index, sphericity, elongation, low_DNA_area and fractall_area. We were able to differentiate between the two main RMS subgroups in 82% of cases on the basis of either sphericity or elongation alone, while the power of differentiation for texture features was 72-79%.
Differentiation between embryonal and alveolar RMS using one nuclear feature is not an important adjunct to light microscopy. However, the possibility of using a combination of nuclear features would probably increase the discriminatory ability.