Raúl Cabido

Linguistic description of traffic in a roundabout

The linguistic description of a physical phenomenon is a summary of the available information where certain relevant aspects are remarked while other irrelevant aspects remain hidden. This paper deals with the development of computational systems capable to generate linguistic descriptions from images captured by a video camera. The problem of linguistically labeling images in a database is a challenge where still much work remains to be done. In this paper, we contribute to this field using a model of the observed phenomenon that allows us to interpret the content of images. We build the model by combining techniques from Computer Vision with ideas from the Zadehs Computational Theory of Perceptions. We include a practical application consisting of a computational system capable to provide a linguistic description of the behavior of traffic in a roundabout.

A low-level hybridization between memetic algorithm and VNS for the max-cut problem

The Max-Cut problem consists of finding a partition of the graph nodes into two subsets, such that the sum of the edge weights having endpoints in different subsets is maximized. This NP-hard problem for non planar graphs has different applications in areas such as VLSI and ASIC design. This paper proposes an evolutionary hybrid algorithm based on low-level hybridization between Memetic Algorithms and Variable Neighborhood Search. This algorithm is tested and compared with the results, found in the bibliography, obtained by other hybrid metaheuristics for the same problem. Achieved experimental results show the suitability of the approach, and that the proposed hybrid evolutionary algorithm finds near-optimal solutions. Moreover, on a set of standard test problems, new best known solutions were produced for several instances.

Scatter search particle filter for 2d real-time hands and face tracking

This paper presents the scatter search particle filter (SSPF) algorithm and its application to real-time hands and face tracking. SSPF combines sequential Monte Carlo (particle filter) and combinatorial optimization (scatter search) methods. Hands and face are characterized using a skin-color model based on explicit RGB region definition. The hybrid SSPF approach enhances the performance of classical particle filter, reducing the required evaluations of the weighting function and increasing the quality of the estimated solution. The system operates on 320x240 live video in real-time.

Convolutional Neural Networks and Long Short-Term Memory for skeleton-based human activity and hand gesture recognition

Combination of a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) recurrent network for skeleton-based human activity and hand gesture recognition.Two-stage training strategy which firstly focuses on the CNN training and, secondly, adjusts the full method CNN+LSTM.A method for data augmentation in the context of spatiotemporal 3D data sequences.An exhaustive experimental study on publicly available data benchmarks with respect to the state-of-the-art most representative methods.Comparison among different CPU and GPU platforms. In this work, we address human activity and hand gesture recognition problems using 3D data sequences obtained from full-body and hand skeletons, respectively. To this aim, we propose a deep learning-based approach for temporal 3D pose recognition problems based on a combination of a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) recurrent network. We also present a two-stage training strategy which firstly focuses on CNN training and, secondly, adjusts the full method (CNN+LSTM). Experimental testing demonstrated that our training method obtains better results than a single-stage training strategy. Additionally, we propose a data augmentation method that has also been validated experimentally. Finally, we perform an extensive experimental study on publicly available data benchmarks. The results obtained show how the proposed approach reaches state-of-the-art performance when compared to the methods identified in the literature. The best results were obtained for small datasets, where the proposed data augmentation strategy has greater impact.

Improving GPU particle filter with shader model 3.0 for visual tracking

Human-Computer Interaction is evolving towards non-contact devices using perceptual user interfaces. Recent research in human motion analysis and visual object tracking make use of the Particle Filter (PF) framework. The PF algorithm enables the modeling of a stochastic process with an arbitrary probability density function, by approximating it numerically with a set of samples called particles. The DirectX Shader Model is a common framework for accessing graphics hardware features in terms of shading functionality. In particular, Shader Model 3.0 compliant graphics cards must support features such as dynamic branching, longer shader programs and texture lookups from vertex buffers, among others. In this work, we propose new improvements on previous CPU/GPU Particle Filter frameworks [Montemayor et al. 2004; Lanvin et al. 2005]. In particular, we have reduced bandwidth requirements in the data allocation stage using GPU texture reads instead of CPUGPU memory transfers. But more importantly, using new features in Shader Model 3.0 we can move all the previous particle filtering CPU stages to the GPU, keeping all the computation on the video card and avoiding expensive data readback.

High Speed Articulated Object Tracking Using GPUs: A Particle Filter Approach

This paper presents a novel application of the GPU processing power to a very computationally demanding articulated human body tracking problem in a view-based approach. This work includes some optimizations at the algorithmic level as well as some tricks at the implementation level using OpenGL and shader programming. An underlying particle filter framework is combined with a novel particle weight computation, where heterogeneous templates are considered for distribution mode recovering. Also, a form of elitism is taking into account to prevent flickering when the best candidate of the particle population is chosen. Impressive performance up to 317-713 frames per second is guaranteed for common configurations of about 1024-256 particles and 320×240 video resolutions.

Hardware-Accelerated template matching

In the last decade, consumer graphics cards have increased their power because of the computer games industry. These cards are now programmable and capable of processing huge amounts of data in a SIMD fashion. In this work, we propose an alternative implementation of a very intuitive and well known 2D template matching, where the most computationally expensive task is accomplished by the graphics hardware processor. This computation approach is not new, but in this work we resume the method step-by-step to better understand the underlying complexity. Experimental results show an extraordinary performance trade-off, even working with obsolete hardware.

Real-time human body tracking based on data fusion from multiple RGB-D sensors

In this work we present a human pose estimation method based on the skeleton fusion and tracking using multiple RGB-D sensors. The proposed method considers the skeletons provided by each RGB-D device and constructs an improved skeleton, taking into account the quality measures provided by the sensors at two different levels: the whole skeleton and each joint individually. Then, each joint is tracked by a Kalman filter, resulting in a smooth tracking performance. We have also developed a new dataset consisting of six subjects performing seven different gestures, recorded with four Kinect devices simultaneously. Experimental results performed on this dataset show that the system obtains better smoothness results than the most representative methods found in the literature. The proposed system operates at a processing rate of 25 frames per second (including the whole algorithm loop, i.e., data acquisition and processing) without the explicit use of the multithreading capabilities of the system.

Performance evaluation of a 3D multi-view-based particle filter for visual object tracking using GPUs and multicore CPUs

This paper presents a deep and extensive performance analysis of the particle filter (PF) algorithm for a very compute intensive 3D multi-view visual tracking problem. We compare different implementations and parameter settings of the PF algorithm in a CPU platform taking advantage of the multithreading capabilities of the modern processors and a graphics processing unit (GPU) platform using NVIDIA CUDA computing environment as developing framework. We extend our experimental study to each individual stage of the PF algorithm, and evaluate the quality versus performance trade-off among different ways to design these stages. We have observed that the GPU platform performs better than the multithreaded CPU platform when handling a large number of particles, but we also demonstrate that hybrid CPU/GPU implementations can run almost as fast as only GPU solutions.

Urban Traffic Surveillance in Smart Cities Using Radar Images

The Smart City concept arises from the need to provide more intelligent and optimized applications for the development of future urban centers. Traffic monitoring including surveillance is becoming a problem as cities are getting larger and crowded with vehicles. Intelligent video applications for outdoor scenarios need for good quality, stable and robust signal in every moment or climate condition. In this paper we present a radar signal surveillance application that works in real-time, in 360 degrees, with long range up to 400 meters away from the detector, with daylight or night, or even with adverse climatology like fog presence, detecting and tracking high speed vehicles in urban areas.