Cluster kernels for semisupervised classification of VHR urban images

In this paper, we present and apply a semisupervised support vector machine based on cluster kernels for the problem of very high resolution image classification. In the proposed setting, a base kernel working with labeled samples only is deformed by a likelihood kernel encoding similarities between unlabeled examples. The resulting kernel is used to train a standard support vector machine (SVM) classifier. Experiments carried out on very high resolution (VHR) multispectral and hyperspectral images using very few labeled examples show the relevancy of the method in the context of urban image classification. Its simplicity and the small number of parameters involved make it versatile and workable by unexperimented users.

Detection of matchings in a sequence of underwater images through texture analysis

This paper presents an approach to ameliorate the reliability of the correspondence points relating two consecutive images of a sequence. The images are especially difficult to handle, since they have been acquired by a camera looking at the sea floor while carried by an underwater robot. Underwater images are usually difficult to process due to light absorption, changing image radiance and lack of well-defined features. A new approach based on gray-level region matching and selective texture analysis significantly improves the matching reliability

Dam wall detection and tracking using a Mechanically Scanned Imaging Sonar

In dam inspection tasks, an underwater robot has to grab images while surveying the wall meanwhile maintaining a certain distance and relative orientation. This paper proposes the use of an MSIS (mechanically scanned imaging sonar) for relative positioning of a robot with respect to the wall. An imaging sonar gathers polar image scans from which depth images (range & bearing) are generated. Depth scans are first processed to extract a line corresponding to the wall (with the Hough transform), which is then tracked by means of an EKF (Extended Kalman Filter) using a static motion model and an implicit measurement equation associating the sensed points to the candidate line. The line estimate is referenced to the robot fixed frame and represented in polar coordinates (rho&thetas) which directly corresponds to the actual distance and relative orientation of the robot with respect to the wall. The proposed system has been tested in simulation as well as in water tank conditions

Estimation of the lateral correlation structure of subsurface water content from surface-based ground-penetrating radar reflection images

Over the past decade, significant interest has been expressed in relating the spatial statistics of surface-based reflection ground-penetrating radar (GPR) data to those of the imaged subsurface volume. A primary motivation for this work is that changes in the radar wave velocity, which largely control the character of the observed data, are expected to be related to corresponding changes in subsurface water content. Although previous work has indeed indicated that the spatial statistics of GPR images are linked to those of the water content distribution of the probed region, a viable method for quantitatively analyzing the GPR data and solving the corresponding inverse problem has not yet been presented. Here we address this issue by first deriving a relationship between the 2-D autocorrelation of a water content distribution and that of the corresponding GPR reflection image. We then show how a Bayesian inversion strategy based on Markov chain Monte Carlo sampling can be used to estimate the posterior distribution of subsurface correlation model parameters that are consistent with the GPR data. Our results indicate that if the underlying assumptions are valid and we possess adequate prior knowledge regarding the water content distribution, in particular its vertical variability, this methodology allows not only for the reliable recovery of lateral correlation model parameters but also for estimates of parameter uncertainties. In the case where prior knowledge regarding the vertical variability of water content is not available, the results show that the methodology still reliably recovers the aspect ratio of the heterogeneity.

Contrast ultrasound: a simple-to-use phase-shifting medium offers saline infusion sonography-like images.

OBJECTIVE: To test the ability of a novel phase-shifting medium (PSM) to provide sustained distension of the uterine cavity and produce saline infusion sonography (SIS)-like images in a simplified contrast ultrasound procedure. DESIGN: Prospective pilot feasibility trial of a new diagnostic procedure, contrast ultrasound. SETTING: Clinical reproductive endocrine and infertility unit of regional teaching hospital. PATIENT(S): Twenty-six asymptomatic infertile women (group I) and 27 women presenting with dysfunctional uterine bleeding (DUB) who were scheduled for exploratory surgery (group II). INTERVENTION(S): All women who were temporarily on oral contraceptive first had a regular pelvic ultrasound followed by the intrauterine instillation of up to 3 mL PSM, using a regular insemination catheter, after which all instruments were removed and a regular ultrasound was performed again. RESULT(S): In all 53 women, intrauterine instillation of 1-3 mL PSM resulted in a 3-7 mm uterine distension, sufficient to produce SIS-like images of the uterine cavity that lasted 7-10 min. Contrast ultrasound revealed an endometrial polyp in 3 asymptomatic women of group I. In group II. 12 of 14 women (86%) whose vaginal ultrasound were positive or dubious had positive findings with contrast ultrasound; 9 of 12 patients whose vaginal ultrasounds were negative also had positive contrast ultrasound findings. All the positive and negative findings of contrast ultrasound made in group II were confirmed anatomically (sensitivity and specificity of 100%), whereas the correlation for standard vaginal ultrasound was markedly lower at 57.1% and 85.7%, respectively. Most patients (46 of 53) reported no discomfort during or after the procedure, and 7 women described the procedure as mildly uncomfortable. CONCLUSION(S): Contrast ultrasound, a novel simple diagnostic procedure conducted after intrauterine instillation of 1-3 mL PSM using a simple plastic catheter, delivered SIS-quality images in asymptomatic (group I) and symptomatic (group II) patients while retaining the simplicity of standard ultrasound. We therefore foresee broad application of contrast ultrasound for sensitive and specific assessment for uterine pathologies in the physician's office.

Bodyweight and migration-related differences in motor abilities in preschool children "Ballabeina"

Introduction: Motor abilities in schoolchildren have been decreasing in the last two decades (Bös, 2003, Tomkinson et al., 2003). This may be related to the dramatic increase in overweight and adiposity during the same time period. Children of migrant background are especially affected (Lasserre et al., 2007). But little is known about the relationship between BMI and migration background and motor abilities in preschool children. Methods/Design We carried out a cross-sectional analysis with 665 children (age 5.1 ± 0.6 years; 49.8 % female) of 40 randomly selected kindergarten classes from German and French speaking regions in Switzerland with a high migrant background. We investigated BMI, cardiorespiratory fitness (20 m shuttle run), static (displacement of center of pressure (COP)) and dynamic (balancing forward on a beam) postural control and overall fitness (obstacle course). Results: Of the children, 9.6 % were overweight, 10.5 % were obese (Swiss national percentiles) and 72.8 % were of migrant background (at least one parent born outside of Switzerland). Mean BMI from children of non-migrant background was 15.5 ± 1.1 kg/m2, while migrant children had a mean BMI of 15.8 ± 1.7 kg/m2 (p=0.08). Normal-weight children performed better in cardiorespiratory fitness (3.1 ± 1.4 vs. 2.6 ± 1.1 stages, p<0.001), overall fitness (18.9 ± 4.4 vs. 20.8 ± 4.6 sec, p<0.001) and in dynamic balance (4.9 ± 3.5 vs. 3.8 ± 2.5 steps, p<0.001) compared to overweight and obese children, while the latter had less postural sway (COP: 956 ± 302 vs. 1021 ± 212 mm, p=0.008). There was a clear inverse dose-response relationship between weight status and dynamic motor abilities. There were no significant differences in most tested motor abilities between non-migrant and migrant. The latter performed less well in only one motor test (overall fitness: 20.2 ± 5.2 vs. 18.3 ± 3.5 sec, p<0.001). These findings persisted after adjustment for BMI. Conclusion In preschool children, differences in motor abilities are already present between normal weight and overweight/obese children. However, migrant children demonstrate similar motor abilities compared to non-migrant children for almost all tests, despite their slightly higher BMI.

Locating and extracting the textual content from complex colour images using techniques inspired by human perception

Los sistemas de radio cognitivos son una solución a la deficiente distribución del espectro inalámbrico de frecuencias. Usando acceso dinámico al medio, los usuarios secundarios pueden comunicarse en canales de frecuencia disponibles, mientras los usuarios asignados no están usando dichos canales. Un buen sistema de mensajería de control es necesario para que los usuarios secundarios no interfieran con los usuarios primarios en las redes de radio cognitivas. Para redes en donde los usuarios son heterogéneos en frecuencia, es decir, no poseen los mismos canales de frecuencia para comunicarse, el grupo de canales utilizado para transmitir información de control debe elegirse cuidadosamente. Por esta razón, en esta tesis se estudian las ideas básicas de los esquemas de mensajería de control usados en las redes de radio cognitivas y se presenta un esquema adecuado para un control adecuado para usuarios heterogéneos en canales de frecuencia. Para ello, primero se presenta una nueva taxonomía para clasificar las estrategias de mensajería de control, identificando las principales características que debe cumplir un esquema de control para sistemas heterogéneos en frecuencia. Luego, se revisan diversas técnicas matemáticas para escoger el mínimo número de canales por los cuales se transmite la información de control. Después, se introduce un modelo de un esquema de mensajería de control que use el mínimo número de canales y que utilice las características de los sistemas heterogéneos en frecuencia. Por último, se comparan diversos esquemas de mensajería de control en términos de la eficiencia de transmisión.

Brain tissue segmentation of fetal MR images

We present a segmentation method for fetal brain tissuesof T2w MR images, based on the well known ExpectationMaximization Markov Random Field (EM- MRF) scheme. Ourmain contribution is an intensity model composed of 7Gaussian distribution designed to deal with the largeintensity variability of fetal brain tissues. The secondmain contribution is a 3-steps MRF model that introducesboth local spatial and anatomical priors given by acortical distance map. Preliminary results on 4 subjectsare presented and evaluated in comparison to manualsegmentations showing that our methodology cansuccessfully be applied to such data, dealing with largeintensity variability within brain tissues and partialvolume (PV).