Youssef S. G. Nashed

Particle Swarm Optimization and Differential Evolution for model-based object detection

Automatically detecting objects in images or video sequences is one of the most relevant and frequently tackled tasks in computer vision and pattern recognition. The starting point for this work is a very general model-based approach to object detection. The problem is turned into a global continuous optimization one: given a parametric model of the object to be detected within an image, a function is maximized, which represents the similarity between the model and a region of the image under investigation. In particular, in this work, the optimization problem is tackled using Particle Swarm Optimization (PSO) and Differential Evolution (DE). We compare the performances of these optimization techniques on two real-world paradigmatic problems, onto which many other real-world object detection problems can be mapped: hippocampus localization in histological images and human body pose estimation in video sequences. In the former, a 2D deformable model of a section of the hippocampus is fit to the corresponding region of a histological image, to accurately localize such a structure and analyze gene expression in specific sub-regions. In the latter, an articulated 3D model of a human body is matched against a set of images of a human performing some action, taken from different perspectives, to estimate the subjects posture in space. Given the significant computational burden imposed by this approach, we implemented PSO and DE as parallel algorithms within the nVIDIA(TM) CUDA computing architecture.

GPU-based asynchronous particle swarm optimization

This paper describes our latest implementation of Particle Swarm Optimization (PSO) with simple ring topology for modern Graphic Processing Units (GPUs). To achieve both the fastest execution time and the best performance, we designed a parallel version of the algorithm, as fine-grained as possible, without introducing explicit synchronization mechanisms among the particles evolution processes. The results we obtained show a significant speed-up with respect to both the sequential version of the algorithm run on an up-to-date CPU and our previously developed parallel implementation within the nVIDIA CUDA architecture.

libCudaOptimize: an open source library of GPU-based metaheuristics

Evolutionary Computation techniques and other metaheuristics have been increasingly used in the last years for solving many real-world tasks that can be formulated as optimization problems. Among their numerous strengths, a major one is their natural predisposition to parallelization. In this paper, we introduce libCudaOptimize, an open source library which implements some metaheuristics for continuous optimization: presently Particle Swarm Optimization, Differential Evolution, Scatter Search, and Solis&Wets local search. This library allows users either to apply these metaheuristics directly to their own fitness function or to extend it by implementing their own parallel optimization techniques. The library is written in CUDA-C to make extensive use of parallelization, as allowed by Graphics Processing Units.n After describing the library, we consider two practical case studies: the optimization of a fitness function for the automatic localization of anatomical brain structures in histological images, and the parallel implementation of Simulated Annealing as a new module, which extends the library while keeping code compatibility with it, so that the new method can be readily available for future use within the library as an alternative optimization technique.

Real-Time GPU based road sign detection and classification

This paper presents a system for detecting and classifying road signs from video sequences in real time. A model-based approach is used in which a prototype of the sign to be detected is transformed and matched to the image using evolutionary techniques. Then, the sign detected in the previous phase is classified by a neural network. Our system makes extensive use of the parallel computing capabilities offered by modern graphics cards and the CUDA architecture for both detection and classification. We compare detection results achieved by GPU-based parallel versions of Differential Evolution and Particle Swarm Optimization, and classification results obtained by Learning Vector Quantization and Multi-layer Perceptron. The method was tested over two real sequences taken from a camera mounted on-board a car and was able to correctly detect and classify around 70% of the signs at 17.5 fps, a similar result in shorter time, compared to the best results obtained on the same sequences so far.

A comparative study of three GPU-based metaheuristics

In this paper we compare GPU-based implementations of three metaheuristics: Particle Swarm Optimization, Differential Evolution, and Scatter Search. A GPU-based implementation, obviously, does not change the general properties of the algorithms. As well, we give for granted that GPU-based implementation of both algorithm and fitness function produces a significant speed-up with respect to a sequential implementation. Accordingly, the main goal of this work has been to fairly assess the efficiency of the GPU-based implementations of the three metaheuristics, based on the statistical analysis of the results they obtain in optimizing a benchmark of twenty functions within a prefixed limited time.

Gesturing at subswarms: Towards direct human control of robot swarms

The term human-swarm interaction (HSI) refers to the interaction between a human operator and a swarm of robots. In this paper, we investigate HSI in the context of a resource allocation and guidance scenario. We present a framework that enables direct communication between human beings and real robot swarms, without relying on a secondary display. We provide the user with a gesture-based interface that allows him to issue commands to the robots. In addition, we develop algorithms that allow robots receiving the commands to display appropriate feedback to the user. We evaluate our framework both in simulation and with real-world experiments. We conduct a summative usability study based on experiments in which participants must guide multiple subswarms to different task locations.

Algorithm configuration using GPU-based metaheuristics

In this paper, a GPU-based implementation of Differential Evolution (DE) and Particle Swarm Optimization (PSO) in CUDA is used to automatically tune the parameters of PSO.n The parameters were tuned over a set of 8 problems and then tested over 20 problems to assess the generalization ability of the tuners. We compare the results obtained using such parameters with the standard ones proposed in the literature and the ones obtained by state-of-the-art tuning methods (irace). The results are comparable to the ones suggested for the standard version of PSO (SPSO), and the ones obtained by irace, while the GPU implementation makes tuning time acceptable.n To the best of our knowledge, this is the first time that a general purpose library of GPU-based metaheuristics is used to solve this problem, as well as being one of the few cases where DE and PSO are both used as tuners.

GPU Hierarchical Quilted Self Organizing Maps for Multimedia Understanding

It is well established that the human brain outperforms current computers, concerning pattern recognition tasks, through the collaborative processing of simple building units (neurons). In this work we expand an abstracted model of the neocortex called Hierarchical Quilted Self Organizing Map, benefiting from the parallel power of current Graphical Processing Units, to achieve realtime understanding and classification of spatio-temporal sensory information. We also propose an improvement on the original model that allows the learning rate to be automatically adapted according to the input training data available. The overall system is tested on the task of gesture recognition from a Microsoft Kinect publicly available dataset.

First results and future developments of the MIBISOC Project in the IBISlab of the university of parma

Medical Imaging using Bio-Inspired and Soft Computing (MIBISOC) is a Marie Curie Initial Training Network (ITN) within the EU Seventh Framework Programme. MIBISOC is a training programme in which sixteen Early-Stage Researchers (ESRs) are exposed to a wide variety of Soft Computing (SC) and Bio-Inspired Computing (BC) techniques, and face the challenge of applying them to the different situations and problems which characterize medical image processing tasks. Hence, the main goal of the project is to generate new methods and solutions from the combination of the ideas of experts from the area of Medical Imaging (MI) with those working on BC and SC applications.n The Intelligent Bio-Inpired Systems laboratory (IBISlab) in the University of Parma is one of the partners of this ITN. In this paper, we describe the work which is being developed in the IBISlab, as well as its future developments and main objectives, within the framework of this ITN.

Multi-View Human Body Pose Estimation with CUDA-PSO

The authors formulate the body pose estimation as a multi-dimensional nonlinear optimization problem, suitable to be approximately solved by a meta-heuristic, specifically, the particle swarm optimization (PSO). Starting from multi-view video sequences acquired in a studio environment, a full skeletal configuration of the human body is retrieved. They use a generic subdivision-surface body model in 3-D to generate solutions for the optimization problem. PSO then looks for the best match between the silhouettes generated by the projection of the model in a candidate pose and the silhouettes extracted from the original video sequence. The optimization method, in this case PSO, is run in parallel on the Graphics Processing Unit (GPU) and is implemented in Cuda-Câ„¢ on the nVidia CUDAâ„¢ architecture. The authors compare the results obtained by different configurations of the camera setup, fitness function, and PSO neighborhood topologies.