Emerson Carlos Pedrino

Image convolution processing: A GPU versus FPGA comparison

Convolution is one of the most important operators used in image processing. With the constant need to increase the performance in high-end applications and the rise and popularity of parallel architectures, such as GPUs and the ones implemented in FPGAs, comes the necessity to compare these architectures in order to determine which of them performs better and in what scenario. In this article, convolution was implemented in each of the aforementioned architectures with the following languages: CUDA for GPUs and Verilog for FPGAs. In addition, the same algorithms were also implemented in MATLAB, using predefined operations and in C using a regular x86 quad-core processor. Comparative performance measures, considering the execution time and the clock ratio, were taken and commented in the paper. Overall, it was possible to achieve a CUDA speedup of roughly 200× in comparison to C, 70× in comparison to Matlab and 20× in comparison to FPGA.

Intelligent FPGA based system for shape recognition

Mathematical morphology supplies powerful tools for low level image analysis, with applications in many areas. In this paper, the development of a novel reconfigurable hardware using a genetic algorithm and a pipeline architecture is proposed for the task of shape recognition in binary images. For the recognition process, a large sized convex structuring element representing the object shape to be recognized is decomposed into the architecture stages. Each stage can handle structuring elements of a limited size. In this approach, a genetic algorithm was used to decompose this structuring element. Thus, a simple erosion performed in each stage is used to detect the goal object. The hardware is capable of processing binary images at high speed. The developed system is based on FPGAs. Our approach represents an intelligent mechanism to reconfigure the pipeline architecture, it is different from other systems found in the literature, and the obtained results are promising.

Architecture for binary mathematical morphology reconfigurable by genetic programming

Mathematical morphology supplies powerful tools for low level image analysis, with applications in robotic vision, visual inspection, medicine, texture analysis and many other areas. Many of the mentioned applications require dedicated hardware for real time execution. In this paper, the development of a novel reconfigurable hardware using logical and morphological instructions generated automatically by a linear approach based on genetic programming is proposed. The hardware is capable of processing binary images at high speed. The developed system is based on high-capacity PLDs and has among the possible applications: automatic construction of image filters, intelligent pattern recognition, to name just a few. Some applications using the developed reconfigurable system are presented and the results are discussed and compared with other approaches.

A genetic programming approach to reconfigure a morphological image processing architecture

Mathematical morphology supplies powerful tools for low-level image analysis. Many applications in computer vision require dedicated hardware for real-time execution. The design of morphological operators for a given application is not a trivial one. Genetic programming is a branch of evolutionary computing, and it is consolidating as a promising method for applications of digital image processing. The main objective of genetic programming is to discover how computers can learn to solve problems without being programmed for that. In this paper, the development of an original reconfigurable architecture using logical, arithmetic, and morphological instructions generated automatically by a genetic programming approach is presented. The developed architecture is based on FPGAs and has among the possible applications, automatic image filtering, pattern recognition and emulation of unknown filter. Binary, gray, and color image practical applications using the developed architecture are presented and the results are compared with similar techniques found in the literature.

Automatic construction of image operators using a genetic programming approach

This paper presents a methodology for automatic construction of image operators using a linear genetic programming approach, for binary, gray level and color image processing, where the processing solution for a particular application is expressed in terms of the basic morphological operators, dilation and erosion, in conjunction with convolution and logical operators. Genetic Programming (GP), based on concepts of genetics and Darwins principle of natural selection, to genetically breed and evolve computer programs to solve a wide variety of problems, is a branch of evolutionary computation, and it is consolidating as a promising methodology to be used in applications involving pattern recognition, classification problems and modeling of complex systems. Mathematical morphology is based on the set theory (complete lattice), where the notion of order is very important. This processing technique has proved to be a powerful tool for many computer vision tasks. However, the manual design of complex operations involving image operators is not trivial in practice. Thus, the proposed methodology tries to solve these drawbacks. Some examples of applications are presented and the results are discussed and compared with other methods found in the literature.

Simulated Activation Patterns of Biological Neurons Cultured onto a Multi-Electrode Array Based on a Modified Izhikevich's Model

Recently we have witnessed research efforts into developing real-time hybrid systems implementing interactions between computational models and live tissues, in an attempt to learn more about the functioning of biological neural networks. A fundamental role in the development of such systems is played by Multi-Electrode Array MEA. In vitro cultures of neurons on MEAs, however, have some drawbacks such as: needing a rigorous adherence to sterile techniques, careful choice and replenishment of media and maintenance of pH, temperature, and osmolarity. An alternative way to study and investigate live tissues which partially circumvent some of the problems with in vitro cultures is by simulating them. This paper describes the proposal of Sim-MEA, a system for modeling and simulating neurons communications in a MEA-based in vitro culture. Sim-MEA implements a modified Izhikevich model that takes into account both: distances between neurons and distances between microelectrodes and neurons. The system also provides ways of simulating microelectrodes and their recorded signals as well as recovering experimental MEA culture data, from their images. The soundness of the Sim-MEA simulation procedure was empirically evaluated using data from an experimental in vitro cultured hippocampal neurons of Wistar rat embryos. Results from simulations, compared to those of the in vitro experiment, are presented and discussed. The paper also describes a few experiments varying several parameter values to illustrate and detail the approach.

Embedded Navigation and Classification System for Assisting Visually Impaired People.

Loss of vision has a large detrimental impact on a person’s mobility. Every day, visually impaired people (VIPs) face various challenges just to get around in the most diverse environments. Technological solutions, called Electronic Travel Aids, help a VIP with these challenges, giving greater confidence in the task of getting around in unfamiliar surroundings. Thus, this article presents an embedded navigation and classification system for helping VIPs indoors. Using stereo vision, the system is able to detect obstacles and choose safe ways for the VIP to walk around without colliding. A convolutional neural network using a graphics processing unit (GPU) classifies the obstacles. Acoustic feedback is transmitted to the VIP. The article also features a wearable prototype, to which the system hardware is docked for use. Using the system, the prototype could detect and classify obstacles in real time defining free paths, all with battery autonomy of about 6 hours.

Islanding detection of distributed generation by using multi-gene genetic programming based classifier

Abstract This paper proposed a new method for detecting islanding of distributed generation (DG), using Multi-gene Genetic Programming (MGP). Islanding has been a serious concern among power distribution utilities and distributed generation owners, because it poses risks to the safety of utilities’ workers and consumers, and can cause damage to power distribution systems’ equipment. Therefore, a DG must be disconnected as soon as an islanding is detected. In addition, an islanding detection method must have high degree of dependability to correctly discriminate islanding from other events, such as load switching, in order to avoid unnecessary disconnection of the distributed generator. In this context, the novelty of the proposed method is that the MGP is capable of obtaining a set of mathematical and logic functions employed to detect and classify islanding correctly. This is a new approach among the computational intelligent methods proposed for DG islanding detection. The main idea was to use local voltage measurements as input of the method, eliminating the need of complex and expensive communication infrastructure. The method has been trained with several islanding and non-islanding cases, by using a power distribution system comprising five concentrated loads, a synchronous distributed generator and a wind power plant. The results showed that the proposed method was successful in differentiating the islanding events from other disturbances, revealing its great potential to be applied in anti-islanding protection schemes for distributed generation.

Software review: CGP-Library

CGP-Library is an open-source, cross-platform written in C which implements Cartesian Genetic Programming (CGP) and its variations. It solves both academic and real-world problems. Since its inicial release, it has undergone some refinements, and it is without doubt the best supported toolkit for CGP. In this article it is presented a critical assessment of the CGP-Library features, its main strengths and its weaknesses.

A Data Fusion Architecture Proposal for Visually Impaired People

Based on the difficulties that a Visually Impaired Person (VIP) has in understanding certain contexts, this article proposes a new architecture that aims to contextualize elements of that environment and, thus, help the visually disabled person to move around safely. The main objective of this project is to extract environmental features and to subsequently perform the processes of perception, comprehension and projection of the Situation Awareness (SAW) model. The proposed architecture is composed of Computer Vision techniques (CV) and Data Fusion (DF). The CV techniques were used in order to obtain the necessary characteristics for the DF to perform the search for consistent relationships for pattern recognition and allow for the projection of possible collisions of the VIP with environmental elements. For the collision projection, the specific characteristics of each context were extracted and trained, thus providing the VIP with inferences made in real time.