Histograms of oriented gradients for fast on-board vehicle verification

Histograms of Oriented Gradients (HoGs) provide excellent results in object detection and verification. However, their demanding processing requirements bound their applicability in some critical real-time scenarios, such as for video-based on-board vehicle detection systems. In this work, an efficient HOG configuration for pose-based on-board vehicle verification is proposed, which alleviates both the processing requirements and required feature vector length without reducing classification performance. The impact on classification of some critical configuration and processing parameters is in depth analyzed to propose a baseline efficient descriptor. Based on the analysis of its cells contribution to classification, new view-dependent cell-configuration patterns are proposed, resulting in reduced descriptors which provide an excellent balance between performance and computational requirements, rendering higher verification rates than other works in the literature.

MRI texture analysis as means for addressing rehydration and milk diffusion of cereals

Cereals microstructure is one of the primary quality attributes of cereals. Cereals rehydration and milk diffusion depends on such microstructure and thus, the crispiness and the texture, which will make it more palatable for the final consumer. Magnetic Resonance Imaging (MRI) is a very powerful topographic tool since acquisition parameter leads to a wide possibility for identifying textures, structures and liquids mobility. It is suited for non-invasive imaging of water and fats. Rehydration and diffusion cereals processes were measured by MRI at different times and using two different kinds of milk, varying their fat level. Several images were obtained. A combination of textural analysis (based on the analysis of histograms) and segmentation methods (in order to understand the rehydration level of each variety of cereals) were performed. According to the rehydration level, no advisable clustering behavior was found. Nevertheless, some differences were noticeable between the coating, the type of milk and the variety of cereals

Grid-based histogram arithmetic for the probabilistic analysis of functions

The selection of predefined analytic grids (partitions of the numeric ranges) to represent input and output functions as histograms has been proposed as a mechanism of approximation in order to control the tradeoff between accuracy and computation times in several áreas ranging from simulation to constraint solving. In particular, the application of interval methods for probabilistic function characterization has been shown to have advantages over other methods based on the simulation of random samples. However, standard interval arithmetic has always been used for the computation steps. In this paper, we introduce an alternative approximate arithmetic aimed at controlling the cost of the interval operations. Its distinctive feature is that grids are taken into account by the operators. We apply the technique in the context of probability density functions in order to improve the accuracy of the probability estimates. Results show that this approach has advantages over existing approaches in some particular situations, although computation times tend to increase significantly when analyzing large functions.

Influencias de los barnices incoloros en las propiedades superficiales de las maderas de construcción

En esta Tesis se cuantifica la variación cromática que producen los barnices en el color de los diferentes tipos de maderas de construcción, obteniendo un modelo matemático de predicción de color de la madera. Se analizan las prestaciones de dieciséis barnices, supuestamente incoloros, aplicados sobre veinte tipos de maderas, angiospermas y gimnospermas, de distintas densidades y latitudes. Ambos materiales son de uso frecuente en el ámbito de la construcción y de fácil localización en las tiendas y almacenes de ambos sectores. Se utilizan técnicas de descomposición cromática, mediante el empleo de microscopio óptico de reflexión, para poder obtener un abanico gráfico de histogramas con valores numéricos de luminosidad y composición cromática, y de esta forma comprobar que los supuestos barnices que se venden como incoloros, no son totalmente incoloros sino que muestran tendencias a virar hacia alguno de los colores básicos. En el proceso experimental de la Tesis, se aplican 16 barnices sobre 20 tipos de maderas, obteniéndose los histogramas de las campañas de fotografías realizadas con cinco años de diferencia, obteniéndose no solo la variación de color que producen los barnices sobre el original de la madera, sino además la influencia de un envejecimiento a los cinco años. La Tesis relaciona el tipo de barniz idóneo para cada tipo de madera, de modo que produzca la menor variación cromática. La Tesis además obtiene un modelo matemático que permite predecir el color final de la madera tratada en función del color inicial de la madera sin barnizar. Se propone en esta Tesis una recomendación de los productos a utilizar en cada uno de los tipos de madera en base a su color inicial. This Thesis quantifies the chromatic variation caused by varnishes in the colour of different types of timbers, obtaining a mathematical model for predicting the timber’s colour. The performance of sixteen varnishes, supposedly colourless, is analysed, applied on twenty types of timber, angiosperms and gymnosperms, of different densities and latitudes. Both materials are of frequent use in the construction field and easily located in the stores and warehouses of both sectors. Chromatic decomposition techniques are used, through the utilization of a reflection optical microscope, in order to obtain a graphic range of histograms with numerical values of luminosity and chromatic composition, and this way confirm that the alleged varnishes sold as colourless are not completely colourless but are prone to shift towards one of the basic colours. During the Thesis’ experimental procedure 16 varnishes are applied on 20 types of timber, obtaining the colour histograms of the photography campaigns carried out with a five years difference, resulting in not only the colour variation caused by the varnishes on the original timber, but also the influence of its ageing five years later. The Thesis links the right type of varnish for each kind of timber, so that as little chromatic variation as possible occurs. The Thesis obtains as well a mathematical model, which makes it possible to predict the final colour of the treated timber depending on the original colour of the timber with no varnish. This Thesis proposes a recommendation of the products to use on each type of timber on the basis of its original colour.

Mealiness assessment in apples and peaches using MRI techniques

Mealiness (woolliness in peaches) is a negative attribute of sensory texture that combines the sensation of a desegregated tissue with the sensation of lack of juiciness. In this study, 24 apples cv. Top Red and 8 peaches cv. Maycrest, submitted to 3 and 2 different storage conditions respectively have been tested by mechanical and MRI techniques to assess mealiness. With this study, the results obtained on apples in a previous work have been validated using mathematical features from the histograms of the T2 maps: more skewed and the presence of a tail in mealy apples, similar to internal breakdown. In peaches, MRI techniques can also be used to identify woolly fruits. Not all the changes found in the histograms of woolly peaches are similar from those observed in mealy apples pointing to a different underlying physiological change in both disorders.

Relationship between solar radiation on watercore on apple fruit assessed with MRI

This work is a preliminary studio of the possibility of assess a relationship between solar radiation and watercore development on apple fruit, during maturation, using a non destructive method such as Magnetic Resonance Imaging (MRI). For such purpose, several low cost solar radiation sensors were designed for the trial and placed at 2 different heights (1.5 and 2.5 m) on 6 adult ?Esperiega? apple trees, in a commercial orchard in Ademuz (Valencia). Sensors were connected along 27 days, during the end of the growth period and start of the fruit maturation process, and radiation measurements of the a-Si sensors were recorded every 1 minute. At the end of this period, fruits from the upper and the lower part of the canopy of each tree were harvested. In all, 152 apples were collected and images with MRI. A Principal Component Analysis, perfomed over the histograms of the images, as well as segmentation methods were performed on the MR images in order to find a pattern involving solar radiation and watercore incidence.

Methodology of image analysis for study of the vertisols moisture content

The main problem to study vertical drainage from the moisture distribution, on a vertisol profile, is searching for suitable methods using these procedures. Our aim was to design a digital image processing methodology and its analysis to characterize the moisture content distribution of a vertisol profile. In this research, twelve soil pits were excavated on a ba re Mazic Pellic Vertisols ix of them in May 13/2011 and the rest in May 19 /2011 after a moderate rainfall event. Digital RGB images were taken from each vertisol pit using a Kodak? camera selecting a size of 1600x945 pixels. Each soil image was processed to homogenized brightness and then a spatial filter with several window sizes was applied to select the optimum one. The RGB image obtained were divided in each matrix color selecting the best thresholds for each one, maximum and minimum, to be applied and get a digital binary pattern. This one was analyzed by estimating two fractal scaling exponents box counting dimension D BC) and interface fractal dimension (D) In addition, three pre-fractal scaling coefficients were determinate at maximum resolution: total number of boxes intercepting the foreground pattern (A), fractal lacunarity (?1) and Shannon entropy S1). For all the images processed the spatial filter 9x9 was the optimum based on entropy, cluster and histogram criteria. Thresholds for each color were selected based on bimodal histograms.

A study of feature combination for vehicle detection based on image processing

Video analytics play a critical role in most recent traffic monitoring and driver assistance systems. In this context, the correct detection and classification of surrounding vehicles through image analysis has been the focus of extensive research in the last years. Most of the pieces of work reported for image-based vehicle verification make use of supervised classification approaches and resort to techniques, such as histograms of oriented gradients (HOG), principal component analysis (PCA), and Gabor filters, among others. Unfortunately, existing approaches are lacking in two respects: first, comparison between methods using a common body of work has not been addressed; second, no study of the combination potentiality of popular features for vehicle classification has been reported. In this study the performance of the different techniques is first reviewed and compared using a common public database. Then, the combination capabilities of these techniques are explored and a methodology is presented for the fusion of classifiers built upon them, taking into account also the vehicle pose. The study unveils the limitations of single-feature based classification and makes clear that fusion of classifiers is highly beneficial for vehicle verification.