Localizzazione e riconoscimento di oggetti mediante descrittori locali

La tesi presenta un lavoro svolto nell'ambito dell'object recognition, in particolare riguardante l'analisi dei descrittori locali SIFT e BRIEF. Dopo aver implementato BRIEF, sono stati realizzati numerosi test al fine di presentare un esauriente confronto prestazionale tra i due descrittori. Infine, è stato realizzato un applicativo per la localizzazione e il riconoscimento di oggetti su ripiani.

Geophotohunt: Progettazione e sviluppo di una App Android per la gestione di cacce al tesoro fotografiche

Il problema che si vuole affrontare è la progettazione e lo sviluppo di un sistema interattivo volto all’apprendimento e alla visita guidata di città d’arte. Si vuole realizzare un’applicazione per dispositivi mobili che offra sia il servizio di creazione di visite guidate che l’utilizzo delle stesse in assenza di connessione internet. Per rendere l’utilizzo dei servizi offerti più piacevole e divertente si è deciso di realizzare le visite guidate sotto forma di cacce al tesoro fotografiche, le cui tappe consistono in indizi testuali che per essere risolti richiedono risposte di tipo fotografico. Si è inoltre scelto di realizzare una community volta alla condivisione delle cacce al tesoro realizzate e al mantenimento di statistiche di gioco. Il contributo originale di questa tesi consiste nella progettazione e realizzazione di una App Android, denominata GeoPhotoHunt, che sfrutta l’idea della caccia al tesoro fotografica e geo localizzata per facilitare le visite guidate a luoghi di interesse, senza la necessità di una connessione ad internet. Il client viene reso indipendente dal server grazie allo spostamento degli algoritmi di image recognition sul client. Esentare il client dalla necessità di una connessione ad internet permette il suo utilizzo anche in città estere dove solitamente non si ha possibilità di connettersi alla rete.

Qualitatitive and quantitative analysis of fish spoilage processes for development of new food monitoring systems

This study investigates the growth and metabolite production of microorganisms causing spoilage of Atlantic cod (Gadus morhua) fillets packaged under air and modified atmosphere (60 % CO2, 40 % O2). Samples were provided by two different retailers (A and B). Storage of packaged fillets occurred at 4 °C and 8 °C. Microbiological quality and metabolite production of cod fillets stored in MAP 4 °C, MAP 8 °C and air were monitored during 13 days, 7 days and 3 days of storage, respectively. Volatile compounds concentration in the headspace were quantified by Selective ion flow tube mass spectrometry and a correlation with microbiological spoilage was studied. The onset of volatile compounds detection was observed to be mostly around 7 log cfu/g of total psychrotrophic count. Trimethylamine and dimethyl sulfide were found to be the dominant volatiles in all of the tested storage conditions, nevertheless there was no close correlation between concentrations of each main VOC and percentages of rejection based on sensory evaluation. According to results it was concluded that they cannot be considered as only indicators of the quality of cod fillets stored in modified atmosphere and air.  

Applicazioni di realtà aumentata in ambito museale

La realtà aumentata, unitamente a quella mista, stanno rapidamente prendendo pieno all'interno di molti aspetti della vita umana. Scopo di questo lavoro è di analizzare tecnologie e tecniche esistenti al fine di applicarle ad un caso reale, la rilevazione e la sovrapposizione di un oggetto digitale tridimensionale ad uno presente in un museo.

Identification and in silico analyses of novel TGFBR1 and TGFBR2 mutations in Marfan syndrome-related disorders

Very recently, heterozygous mutations in the genes encoding transforming growth factor beta receptors I (TGFBR1) and II (TGFBR2) have been reported in Loeys-Dietz aortic aneurysm syndrome (LDS). In addition, dominant TGFBR2 mutations have been identified in Marfan syndrome type 2 (MFS2) and familial thoracic aortic aneurysms and dissections (TAAD). In the past, mutations of these genes were associated with atherosclerosis and several human cancers. Here, we report a total of nine novel and one known heterozygous sequence variants in the TGFBR1 and TGFBR2 genes in nine of 70 unrelated individuals with MFS-like phenotypes who previously tested negative for mutations in the gene encoding the extracellular matrix protein fibrillin-1 (FBN1). To assess the pathogenic impact of these sequence variants, in silico analyses were performed by the PolyPhen, SIFT, and Fold-X algorithms and by means of a 3D homology model of the TGFBR2 kinase domain. Our results showed that in all but one of the patients the pathogenic effect of at least one sequence variant is highly probable (c.722C > T, c.799A > C, and c.1460G > A in TGFBR1 and c.773T > G, c.1106G > T, c.1159G > A, c.1181G > A, and c.1561T > C in TGFBR2). These deleterious alleles occurred de novo or segregated with the disease in the families, indicating a causative association between the sequence variants and clinical phenotypes. Since TGFBR2 mutations found in patients with MFS-related disorders cannot be distinguished from heterozygous TGFBR2 mutations reported in tumor samples, we emphasize the importance of segregation analysis in affected families. In order to be able to find the mutation that is indeed responsible for a MFS-related phenotype, we also propose that genetic testing for sequence alterations in TGFBR1 and TGFBR2 should be complemented by mutation screening of the FBN1 gene.

An Empirical Study of Non-Rigid Surface Feature Matching of Human from 3D Video

This paper presents an empirical study of affine invariant feature detectors to perform matching on video sequences of people with non-rigid surface deformation. Recent advances in feature detection and wide baseline matching have focused on static scenes. Video frames of human movement capture highly non-rigid deformation such as loose hair, cloth creases, skin stretching and free flowing clothing. This study evaluates the performance of six widely used feature detectors for sparse temporal correspondence on single view and multiple view video sequences. Quantitative evaluation is performed of both the number of features detected and their temporal matching against and without ground truth correspondence. Recall-accuracy analysis of feature matching is reported for temporal correspondence on single view and multiple view sequences of people with variation in clothing and movement. This analysis identifies that existing feature detection and matching algorithms are unreliable for fast movement with common clothing.

High Resolution Image Correspondences for Video Post-Production

We present an algorithm for estimating dense image correspondences. Our versatile approach lends itself to various tasks typical for video post-processing, including image morphing, optical flow estimation, stereo rectification, disparity/depth reconstruction, and baseline adjustment. We incorporate recent advances in feature matching, energy minimization, stereo vision, and data clustering into our approach. At the core of our correspondence estimation we use Efficient Belief Propagation for energy minimization. While state-of-the-art algorithms only work on thumbnail-sized images, our novel feature downsampling scheme in combination with a simple, yet efficient data term compression, can cope with high-resolution data. The incorporation of SIFT (Scale-Invariant Feature Transform) features into data term computation further resolves matching ambiguities, making long-range correspondence estimation possible. We detect occluded areas by evaluating the correspondence symmetry, we further apply Geodesic matting to automatically determine plausible values in these regions.

Pilot Project: Use of Wikis to Supplement Student Orientation

Background: During the orientation process, new students are often inundated with manuals, maps, and other materials essential to their success as students. The experience can leave students feeling overwhelmed, unable to sift through the substantial amount of information that has been given to them. Wikis, in contrast, are well-suited for facilitating userinteraction with vast amounts of diverse information. [See PDF for complete abstract]

Whole-Genome Sequencing of a Canine Family Trio Reveals a FAM83G Variant Associated with Hereditary Footpad Hyperkeratosis

Over 250 Mendelian traits and disorders, caused by rare alleles have been mapped in the canine genome. Although each disease is rare in the dog as a species, they are collectively common and have major impact on canine health. With SNP-based genotyping arrays, genome-wide association studies (GWAS) have proven to be a powerful method to map the genomic region of interest when 10-20 cases and 10-20 controls are available. However, to identify the genetic variant in associated regions, fine-mapping and targeted re-sequencing is required. Here we present a new approach using whole-genome sequencing (WGS) of a family trio without prior GWAS. As a proof-of-concept, we chose an autosomal recessive disease known as hereditary footpad hyperkeratosis (HFH) in Kromfohrl änder dogs. To our knowledge, this is the first time this family trio WGS-approach, has successfully been used to identify a genetic variant that perfectly segregates with a canine disorder. The sequencing of three Kromfohrl änder dogs from a family trio (an affected offspring and both its healthy parents) resulted in an average genome coverage of 9.2X per individual. After applying stringent filtering criteria for candidate causative coding variants, 527 single nucleotide variants (SNVs) and 15 indels were found to be homozygous in the affected offspring and heterozygous in the parents. Using the computer software packages ANNOVAR and SIFT to functionally annotate coding sequence differences and to predict their functional effect, resulted in seven candidate variants located in six different genes. Of these, only FAM83G:c155G>C (p.R52P) was found to be concordant in eight additional cases and 16 healthy Kromfohrl änder dogs.

Characterization of vineyard's canopy through fuzzy clustering and svm over color images

In this work we propose an image acquisition and processing methodology (framework) developed for performance in-field grapes and leaves detection and quantification, based on a six step methodology: 1) image segmentation through Fuzzy C-Means with Gustafson Kessel (FCM-GK) clustering; 2) obtaining of FCM-GK outputs (centroids) for acting as seeding for K-Means clustering; 3) Identification of the clusters generated by K-Means using a Support Vector Machine (SVM) classifier. 4) Performance of morphological operations over the grapes and leaves clusters in order to fill holes and to eliminate small pixels clusters; 5)Creation of a mosaic image by Scale-Invariant Feature Transform (SIFT) in order to avoid overlapping between images; 6) Calculation of the areas of leaves and grapes and finding of the centroids in the grape bunches. Image data are collected using a colour camera fixed to a mobile platform. This platform was developed to give a stabilized surface to guarantee that the images were acquired parallel to de vineyard rows. In this way, the platform avoids the distortion of the images that lead to poor estimation of the areas. Our preliminary results are promissory, although they still have shown that it is necessary to implement a camera stabilization system to avoid undesired camera movements, and also a parallel processing procedure in order to speed up the mosaicking process.

Comparación de algoritmos detectores de puntos singulares para reconocimiento de objetos en vídeo quirúrgico.

El análisis de vídeo laparoscópico ofrece nuevas posibilidades a la navegación quirúrgica al garantizar una incorporación mínima de tecnología en quirófano, evitando así alterar la ergonomía y los flujos de trabajo de las intervenciones. Una de sus principales ventajas es que puede servir como fuente de datos para reconstruir tridimensionalmente la escena laparoscópica, lo que permite dotar al cirujano de la sensación de profundidad perdida en este tipo de cirugía. En el presente trabajo de investigación se comparan dos detectores de puntos singulares, SIFT y SURF, para estimar cuál de los dos podría integrarse en un algoritmo de cálculo de coordenadas 3D, MonoSLAM, basado en la detección y el seguimiento de estos puntos singulares en los fotogramas del vídeo. Los resultados obtenidos posicionan a SURF como la mejor opción gracias a su rapidez y a su mayor capacidad de discriminación entre estructuras anatómicas e instrumental quirúrgico.

Refined facial disparity maps for automatic creation of 3D avatars

We propose a new method to automatically refine a facial disparity map obtained with standard cameras and under conventional illumination conditions by using a smart combination of traditional computer vision and 3D graphics techniques. Our system inputs two stereo images acquired with standard (calibrated) cameras and uses dense disparity estimation strategies to obtain a coarse initial disparity map, and SIFT to detect and match several feature points in the subjects face. We then use these points as anchors to modify the disparity in the facial area by building a Delaunay triangulation of their convex hull and interpolating their disparity values inside each triangle. We thus obtain a refined disparity map providing a much more accurate representation of the the subjects facial features. This refined facial disparity map may be easily transformed, through the camera calibration parameters, into a depth map to be used, also automatically, to improve the facial mesh of a 3D avatar to match the subjects real human features.

Casamento de modelos baseado em projeções radiais e circulares invariante a pontos de vista.

Este trabalho aborda o problema de casamento entre duas imagens. Casamento de imagens pode ser do tipo casamento de modelos (template matching) ou casamento de pontos-chaves (keypoint matching). Estes algoritmos localizam uma região da primeira imagem numa segunda imagem. Nosso grupo desenvolveu dois algoritmos de casamento de modelos invariante por rotação, escala e translação denominados Ciratefi (Circula, radial and template matchings filter) e Forapro (Fourier coefficients of radial and circular projection). As características positivas destes algoritmos são a invariância a mudanças de brilho/contraste e robustez a padrões repetitivos. Na primeira parte desta tese, tornamos Ciratefi invariante a transformações afins, obtendo Aciratefi (Affine-ciratefi). Construímos um banco de imagens para comparar este algoritmo com Asift (Affine-scale invariant feature transform) e Aforapro (Affine-forapro). Asift é considerado atualmente o melhor algoritmo de casamento de imagens invariante afim, e Aforapro foi proposto em nossa dissertação de mestrado. Nossos resultados sugerem que Aciratefi supera Asift na presença combinada de padrões repetitivos, mudanças de brilho/contraste e mudanças de pontos de vista. Na segunda parte desta tese, construímos um algoritmo para filtrar casamentos de pontos-chaves, baseado num conceito que denominamos de coerência geométrica. Aplicamos esta filtragem no bem-conhecido algoritmo Sift (scale invariant feature transform), base do Asift. Avaliamos a nossa proposta no banco de imagens de Mikolajczyk. As taxas de erro obtidas são significativamente menores que as do Sift original.

Human Motion Analysis Based on Sequential Modeling of Radar Signal and Stereo Image Features

Falls are one of the greatest threats to elderly health in their daily living routines and activities. Therefore, it is very important to detect falls of an elderly in a timely and accurate manner, so that immediate response and proper care can be provided, by sending fall alarms to caregivers. Radar is an effective non-intrusive sensing modality which is well suited for this purpose, which can detect human motions in all types of environments, penetrate walls and fabrics, preserve privacy, and is insensitive to lighting conditions. Micro-Doppler features are utilized in radar signal corresponding to human body motions and gait to detect falls using a narrowband pulse-Doppler radar. Human motions cause time-varying Doppler signatures, which are analyzed using time-frequency representations and matching pursuit decomposition (MPD) for feature extraction and fall detection. The extracted features include MPD features and the principal components of the time-frequency signal representations. To analyze the sequential characteristics of typical falls, the extracted features are used for training and testing hidden Markov models (HMM) in different falling scenarios. Experimental results demonstrate that the proposed algorithm and method achieve fast and accurate fall detections. The risk of falls increases sharply when the elderly or patients try to exit beds. Thus, if a bed exit can be detected at an early stage of this motion, the related injuries can be prevented with a high probability. To detect bed exit for fall prevention, the trajectory of head movements is used for recognize such human motion. A head detector is trained using the histogram of oriented gradient (HOG) features of the head and shoulder areas from recorded bed exit images. A data association algorithm is applied on the head detection results to eliminate head detection false alarms. Then the three dimensional (3D) head trajectories are constructed by matching scale-invariant feature transform (SIFT) keypoints in the detected head areas from both the left and right stereo images. The extracted 3D head trajectories are used for training and testing an HMM based classifier for recognizing bed exit activities. The results of the classifier are presented and discussed in the thesis, which demonstrates the effectiveness of the proposed stereo vision based bed exit detection approach.

Comparativa de detectores de características visuales y su aplicación al SLAM

Comunicación presentada en el X Workshop of Physical Agents, Cáceres, 10-11 septiembre 2009.