Automatic estimation of crowd density using texture

This paper considers the role of automatic estimation of crowd density and its importance for the automatic monitoring of areas where crowds are expected to be present. A new technique is proposed which is able to estimate densities ranging from very low to very high concentration of people, which is a difficult problem because in a crowd only parts of people's body appear. The new technique is based on the differences of texture patterns of the images of crowds. Images of low density crowds tend to present coarse textures, while images of dense crowds tend to present fine textures. The image pixels are classified in different texture classes and statistics of such classes are used to estimate the number of people. The texture classification and the estimation of people density are carried out by means of self organising neural networks. Results obtained respectively to the estimation of the number of people in a specific area of Liverpool Street Railway Station in London (UK) are presented. (C) 1998 Elsevier B.V. Ltd. All rights reserved.

On the efficacy of texture analysis for crowd monitoring

The goal of this work is to assess the efficacy of texture measures for estimating levels of crowd densities ill images. This estimation is crucial for the problem of crowd monitoring. and control. The assessment is carried out oil a set of nearly 300 real images captured from Liverpool Street Train Station. London, UK using texture measures extracted from the images through the following four different methods: gray level dependence matrices, straight lille segments. Fourier analysis. and fractal dimensions. The estimations of dowel densities are given in terms of the classification of the input images ill five classes of densities (very low, low. moderate. high and very high). Three types of classifiers are used: neural (implemented according to the Kohonen model). Bayesian. and an approach based on fitting functions. The results obtained by these three classifiers. using the four texture measures. allowed the conclusion that, for the problem of crowd density estimation. texture analysis is very effective.

Texture and Microstructure of Gelatin/Corn Starch-Based Gummy Confections

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Oriented texture classification based on self-organizing neural network and Hough transform

This paper presents a technique for oriented texture classification which is based on the Hough transform and Kohonen's neural network model. In this technique, oriented texture features are extracted from the Hough space by means of two distinct strategies. While the first operates on a non-uniformly sampled Hough space, the second concentrates on the peaks produced in the Hough space. The described technique gives good results for the classification of oriented textures, a common phenomenon in nature underlying an important class of images. Experimental results are presented to demonstrate the performance of the new technique in comparison, with an implemented technique based on Gabor filters.

A regularized nonlinear diffusion approach for texture image denoising

In this paper a new partial differential equation based method is presented with a view to denoising images having textures. The proposed model combines a nonlinear anisotropic diffusion filter with recent harmonic analysis techniques. A wave atom shrinkage allied to detection by gradient technique is used to guide the diffusion process so as to smooth and maintain essential image characteristics. Two forcing terms are used to maintain and improve edges, boundaries and oscillatory features of an image having irregular details and texture. Experimental results show the performance of our model for texture preserving denoising when compared to recent methods in literature. © 2009 IEEE.

Potential use of the veris apparent EC sensor to predict soil texture under the semi-arid conditions of central Arizona

The operational details of the apparent electrical conductivity (ECa) sensor manufactured by Veris Technologies have been extensively documented in literature reports, but the geographical distribution of these research studies indicate a strong regional concentration in the US Mid-west and Southern states. The agricultural lands of these states diverge significantly to the soil conditions and water regime of irrigated land in the US South-western states such as Arizona where there is no previous research reports of the use of this particular sensor. The objectives of the present study were to analyze the performance of this sensor under the conditions of typical soils in irrigated farms of Central Arizona. We tested under static conditions the performance of the sensor on three soils of contrasting texture. Observations were collected as time series data as soil moisture changed from saturation to permanent wilting point. Observations were repeated at the hours of lowest and highest temperatures. In addition, this study included soil penetration resistance and salinity determinations. Preliminary results indicate that soil temperature of the upper layer caused the most dynamic change in the sensor output. The ECa curves of the three soil textures tested had well defined distinctive characteristics. Final multivariate analysis is pending.

Measuring and analyzing color and texture information in anatomical leaf cross sections: An approach using computer vision to aid plant species identification

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Estimate of concrete block texture using image analysis

The texture of concrete blocks is very important and is often the decisive factor when choosing a product, particularly if the building specifications call for high-strength blocks allied to low-cost finish, in which case exposed blocks with a closer texture are often preferred. Furthermore, a closer texture, especially for exteriors, may be a vital factor in ensuring the building's durability. At present, however, there is no standard to quantify the texture of a structural block. Further, when studying masonry blocks compressive strength should never be overlooked. This article discusses a procedure to produce concrete block textures with and without the addition of lime, but still to achieve the required compressive strength. The method used in this study, to evaluate texture, proved to be simpler and cheaper than methods reported by other authors in the literature. The addition of small quantities of lime proved beneficial for both texture and compressive strength. Increasing the amount of lime further, however, only improved texture.

Application of UTHSCSA-Image ToolTM to estimate concrete texture

The texture of concrete blocks is very important and is often the decisive factor when choosing a product, particularly if the building specifications does not dispense with the high resistance of the blocks, but has the purpose of reducing costs with finishing, therefore preferring exposed blocks with a closer texture. Furthermore, a closer texture, especially for exteriors,may be the vital factor of the building's pathology.However, there is so far no standard to quantify the texture of a structural block. This article proposes to apply the freely available UTHSCSA-Image ToolTM program developed by the University of Texas Health Science Center at San Antonio to evaluate the texture of masonry blocks. One aspect that should never be overlooked when studying masonry blocks is compressive strength. Therefore, this work also gets the compressive strength of the blocks with and without the addition of lime. The addition of small quantities of lime proved beneficial for both texture and compressive strength. However, increasing the amount of lime proved to be feasible only to improve texture. © 2012 Taylor & Francis Group.

Characterization of texture in image of skin lesions by support vector machine

Due to the increased incidence of skin cancer, computational methods based on intelligent approaches have been developed to aid dermatologists in the diagnosis of skin lesions. This paper proposes a method to classify texture in images, since it is an important feature for the successfully identification of skin lesions. For this is defined a feature vector, with the fractal dimension of images through the box-counting method (BCM), which is used with a SVM to classify the texture of the lesions in to non-irregular or irregular. With the proposed solution, we could obtain an accuracy of 72.84%. © 2012 AISTI.

Texture profile and correlation between sensory and instrumental analyses on extruded snacks

Instrumental texture analysis on extruded snacks is widely applied, however there is no scientific consensus about the test and probe types that can be correlated with the sensory texture of snacks. Eleven commercial extruded snacks of different shapes were evaluated instrumentally using different probes and sensorially through descriptive analysis. The snack texture was described using the attributes of hardness, crispness, adhesiveness, fracturability and chewiness. Cylindrical snacks were described through crispness and fracturability, pelleted and shell-shaped snacks by chewiness and ring-shaped snacks by adhesiveness and hardness. Hardness and adhesiveness were correlated with a Warner-Bratzler test using a V shape probe (r = 0.718 and r = 0.763, respectively), while fracturability and chewiness were correlated with a Warner-Bratzler test using a guillotine (r = 0.776 and r = 0.662, respectively). The fairly strong good correlations enable application of these instrumental tests as an indication of the sensory texture of extruded snacks. © 2013 Elsevier Ltd. All rights reserved.