Bruno Brandoli Machado

Mice and larvae tracking using a particle filter with an auto-adjustable observation model

This paper proposes a novel way to combine different observation models in a particle filter framework. This, so called, auto-adjustable observation model, enhance the particle filter accuracy when the tracked objects overlap without infringing a great runtime penalty to the whole tracking system. The approach has been tested under two important real world situations related to animal behavior: mice and larvae tracking. The proposal was compared to some state-of-art approaches and the results show, under the datasets tested, that a good trade-off between accuracy and runtime can be achieved using an auto-adjustable observation model.

A complex network approach for dynamic texture recognition

Abstract In this paper, we propose a novel approach for dynamic texture representation based on complex networks. In the proposed approach, each pixel of the video is mapped into a node of the complex network. Initially, a regular complex network is obtained by connecting two nodes if the Euclidean distance between their related pixels is equal or less than a given radius. For each connection, a weight is defined by the difference of the pixel intensities. Given the regular complex network, a function is applied to remove connections whose weight is equal to or below a given threshold. Finally, a feature vector is obtained by calculating the spatial and temporal average degree for networks transformed by different values of threshold and radius. The number of connections of pixels from the same frame and from different frames, respectively, gives the spatial and temporal degrees. Experimental results using synthetic and real dynamic textures have demonstrated the effectiveness of the proposed approach.

Texture descriptor combining fractal dimension and artificial crawlers

Texture is an important visual attribute used to describe images. There are many methods available for texture analysis. However, they do not capture the detail richness of the image surface. In this paper, we propose a new method to describe textures using the artificial crawler model. This model assumes that agents can interact with the environment and each other. Since this swarm system alone does not achieve a good discrimination, we developed a new method to increase the discriminatory power of artificial crawlers, together with the fractal dimension theory. Here, we estimated the fractal dimension by the Bouligand–Minkowski method due to its precision in quantifying structural properties of images. We validate our method on two texture datasets and the experimental results reveal that our method leads to highly discriminative textural features. The results indicate that our method can be used in different texture applications.

Partial differential equations and fractal analysis to plant leaf identification

Texture is an important visual attribute used to plant leaf identification. Although there are many methods of texture analysis, some of them specifically for interpreting leaf images is still a challenging task because of the huge pattern variation found in nature. In this paper, we investigate the leaf texture modeling based on the partial differential equations and fractal dimension theory. Here, we are first interested in decomposing the original texture image into two components f = u + v, such that u represents a cartoon component, while v represents the oscillatory component. We demonstrate how this procedure enhance the texture component on images. Our modeling uses the non-linear partial differential equation (PDE) of Perona-Malik. Based on the enhanced texture component, we estimated the fractal dimension by the Bouligand-Minkowski method due to its precision in quantifying structural properties of images. The feature vectors are then used as inputs to our classification system, based on linear discriminant analysis. We validate our approach on a benchmark with 8000 leaf samples. Experimental results indicate that the proposed approach improves average classification rates in comparison with traditional methods. The results suggest that the proposed approach can be a feasible step for plant leaf identification, as well as different real-world applications.

Local descriptors for soybean disease recognition

A novel approach is proposed for soybean disease recognition using leaf images.It is based on local descriptors and bag-of-visual words.Experimental results on an image dataset with 1200 samples validate its effectiveness.Results also show that color increases the correct classification rate. The detection of diseases is of vital importance to increase the productivity of soybean crops. The presence of the diseases is usually conducted visually, which is time-consuming and imprecise. To overcome these issues, there is a growing demand for technologies that aim at early and automated disease detection. In this line of work, we introduce an effective (over 98% of accuracy) and efficient (an average time of 0.1s per image) method to computationally detect soybean diseases. Our method is based on image local descriptors and on the summarization technique Bag of Visual Words. We tested our approach on a dataset composed of 1200 scanned soybean leaves considering healthy samples, and samples with evidence of three diseases commonly observed in soybean crops - Mildew, Rust Tan, and Rust RB. The experimental results demonstrated the accuracy of the proposed approach and suggested that it can be easily applied to other kinds of crops.

Cloth Simulation Using AABB Hierarchies and GPU Parallelism

Providing realistic, high-resolution and highfidelityrepresentation of motions ia essential in the clothsimulation problem. In order to make high resolution simulationstractable, several algorithms have been developed thatmanage cloth-object interactions efficiently through specializeddata structures such as AABB trees. However, implementationrestrictions on single CPU architectures impose certain limitson quality and performance in high-demanding simulations,motivating the study of new implementation techniques. Inthis paper we address several critical issues in high resolutioncloth simulation, enabling us to represent and simulateintricate folds and wrinkles. We employ AABB hierarchiesto optimize detection and response in cloth-object collisions.By employing a multi-processor approach on multi-threadedCPU and an emerging multi-core GPU-CUDA architecture, wequantitatively evaluate the workload and computational effortof the cloth simulation application. In addition to this quantitativeperformance evaluation on multi-processor architectureswe illustrate the potential of our approach by presenting avariety of high-quality and high-resolution simulations of clothbehavior under different cloth-object interactions.

Material quality assessment of silk nanofibers based on swarm intelligence

In this paper, we propose a novel approach for texture analysis based on artificial crawler model. Our method assumes that each agent can interact with the environment and each other. The evolution process converges to an equilibrium state according to the set of rules. For each textured image, the feature vector is composed by signatures of the live agents curve at each time. Experimental results revealed that combining the minimum and maximum signatures into one increase the classification rate. In addition, we pioneer the use of autonomous agents for characterizing silk fibroin scaffolds. The results strongly suggest that our approach can be successfully employed for texture analysis.

Enhancing the texture attribute with partial differential equations: a case of study with Gabor filters

Texture is an important visual attribute used to discriminate images. Although statistical features have been successful, texture descriptors do not capture the richness of details present in the images. In this paper we propose a novel approach for texture analysis based on partial differential equations (PDE) of Perona and Malik. Basically, an input image f is decomposed into two components f = u + v, where u represents the cartoon component and v represents the textural component. We show how this procedure can be employed to enhance the texture attribute. Based on the enhanced texture information, Gabor filters are applied in order to compose a feature vector. Experiments on two benchmark datasets demonstrate the superior performance of our approach with an improvement of almost 6%. The results strongly suggest that the proposed approach can be successfully combined with different methods of texture analysis.

Complex-Network Tools to Understand the Behavior of Criminality in Urban Areas

Complex networks are nowadays employed in several applications. Modeling urban street networks is one of them, and in particular to analyze criminal aspects of a city. Several research groups have focused on such application, but until now, there is a lack of a well-defined methodology for employing complex networks in a whole crime analysis process, i.e. from data preparation to a deep analysis of criminal communities. Furthermore, the “toolset” available for those works is not complete enough, also lacking techniques to maintain up-to-date, complete crime datasets and proper assessment measures. In this sense, we propose a threefold methodology for employing complex networks in the detection of highly criminal areas within a city. Our methodology comprises three tasks: (i) Mapping of Urban Crimes; (ii) Criminal Community Identification; and (iii) Crime Analysis. Moreover, it provides a proper set of assessment measures for analyzing intrinsic criminality of communities, especially when considering different crime types. We show our methodology by applying it to a real crime dataset from the city of San Francisco—CA, USA. The results confirm its effectiveness to identify and analyze high criminality areas within a city. Hence, our contributions provide a basis for further developments on complex networks applied to crime analysis.

BioLeaf: A professional mobile application to measure foliar damage caused by insect herbivory

Abstract Soybean is one of the ten greatest crops in the world, answering for billion-dollar businesses every year. This crop suffers from insect herbivory that costs millions from producers. Hence, constant monitoring of the crop foliar damage is necessary to guide the application of insecticides. However, current methods to measure foliar damage are expensive and dependent on laboratory facilities, in some cases, depending on complex devices. To cope with these shortcomings, we introduce an image processing methodology to measure the foliar damage in soybean leaves. We developed a non-destructive imaging method based on two techniques, Otsu segmentation and Bezier curves, to estimate the foliar loss in leaves with or without border damage. We instantiate our methodology in a mobile application named BioLeaf, which is freely distributed for smartphone users. We experimented with real-world leaves collected from a soybean crop in Brazil. Our results demonstrated that BioLeaf achieves foliar damage quantification with precision comparable to that of human specialists. With these results, our proposal might assist soybean producers, reducing the time to measure foliar damage, reducing analytical costs, and defining a commodity application that is applicable not only to soy, but also to different crops such as cotton, bean, potato, coffee, and vegetables.