Real-time detection of parked vehicles from multiple image streams

We present a system to detect parked vehicles in a typical commercial parking complex using multiple streams of images captured through IP connected devices. Compared to traditional object detection techniques and machine learning methods, our approach is significantly faster in detection speed in the presence of multiple image streams. It is also capable of comparable accuracy when put to test against existing methods. And this is achieved without the need to train the system that machine learning methods require. Our approach uses a combination of psychological insights obtained from human detection and an algorithm replicating the outcomes of a SVM learner but without the noise that compromises accuracy in the normal learning process. The result is faster detection with comparable accuracy. Our experiments on images captured from a local test site shows very promising results for an implementation that is not only effective and low cost but also opens doors to new parking applications when combined with other technologies.

Gestión de vídeo distribuido

[ES] El principal objetivo de este Trabajo Final de Grado (TFG) fue la creación de un sistema de gestión de vídeo distribuido utilizando cámaras de videovigilancia IP. Esta propuesta surgió a partir de la idea de ofrecer un acceso simultáneo, tanto online como offline, a las secuencias de vídeo generadas por una red de cámaras IP en un entorno dado. El resultado obtenido fue una infraestructura software ampliable  que ofrece al usuario una serie de funcionalidades con cámaras de red, abstrayéndolo de detalles internos. El trabajo está compuesto por tres elementos claramente diferenciados: integración de cámaras IP, almacenamiento en vídeo y creación del sistema de vídeo distribuido. La integración de cámaras IP tiene como objetivo comunicar al equipo con la cámara de red para la obtención del flujo de imágenes que transmite. Dicha comunicación se establece vía HTTP (Hypertext Transfer Protocol) gracias a la interfaz de programación (API) de la que disponen estos dispositivos. El segundo elemento, el almacenamiento en vídeo, tiene como función guardar las imágenes de la cámara IP en archivos de vídeo. De esta manera se ofrece su posterior visualización en diferido. Finalmente, el sistema de vídeo distribuido permite la reproducción simultánea de múltiples vídeos grabados por la red de cámaras IP. Adicionalmente, vídeos grabados por otros dispositivos también son admitidos. El material desarrollado dispone del potencial necesario para convertirse en una herramienta libre de amplio uso en sistemas UNIX para cámaras IP, así como suponer la base de futuros proyectos relacionados con estos dispositivos.

Real-time image streaming over a low-bandwidth wireless camera network

In this paper we describe the recent development of a low-bandwidth wireless camera sensor network. We propose a simple, yet effective, network architecture which allows multiple cameras to be connected to the network and synchronize their communication schedules. Image compression of greater than 90% is performed at each node running on a local DSP coprocessor, resulting in nodes using 1/8th the energy compared to streaming uncompressed images. We briefly introduce the Fleck wireless node and the DSP/camera sensor, and then outline the network architecture and compression algorithm. The system is able to stream color QVGA images over the network to a base station at up to 2 frames per second. © 2007 IEEE.

The use of temporal speech and lip information for multi-modal speaker identification via multi-stream HMMs

Investigates the use of temporal lip information, in conjunction with speech information, for robust, text-dependent speaker identification. We propose that significant speaker-dependent information can be obtained from moving lips, enabling speaker recognition systems to be highly robust in the presence of noise. The fusion structure for the audio and visual information is based around the use of multi-stream hidden Markov models (MSHMM), with audio and visual features forming two independent data streams. Recent work with multi-modal MSHMMs has been performed successfully for the task of speech recognition. The use of temporal lip information for speaker identification has been performed previously (T.J. Wark et al., 1998), however this has been restricted to output fusion via single-stream HMMs. We present an extension to this previous work, and show that a MSHMM is a valid structure for multi-modal speaker identification

Image segmentation and pose estimation of humans in video

This thesis introduces improved techniques towards automatically estimating the pose of humans from video. It examines a complete workflow to estimating pose, from the segmentation of the raw video stream to extract silhouettes, to using the silhouettes in order to determine the relative orientation of parts of the human body. The proposed segmentation algorithms have improved performance and reduced complexity, while the pose estimation shows superior accuracy during difficult cases of self occlusion.

A study on boundary-layer transition induced by free-stream turbulence

Boundary-layer transition at different free-stream turbulence levels has been investigated using the particle-image velocimetry technique. The measurements show organized positive and negative fluctuations of the streamwise fluctuating velocity component, which resemble the forward and backward jet-like structures reported in the direct numerical simulation of bypass transition. These fluctuations are associated with unsteady streaky structures. Large inclined high shear-layer regions are also observed and the organized negative fluctuations are found to appear consistently with these inclined shear layers, along with highly inflectional instantaneous streamwise velocity profiles. These inflectional velocity profiles are similar to those in the ribbon-induced boundary-layer transition. An oscillating-inclined shear layer appears to be the turbulent spot-precursor. The measurements also enabled to compare the actual turbulent spot in bypass transition with the simulated one. A proper orthogonal decomposition analysis of the fluctuating velocity field is carried out. The dominant flow structures of the organized positive and negative fluctuations are captured by the first few eigenfunction modes carrying most of the fluctuating energy. The similarity in the dominant eigenfunctions at different Reynolds numbers suggests that the flow prevails its structural identity even in intermittent flows. This analysis also indicates the possibility of the existence of a spatio-temporal symmetry associated with a travelling wave in the flow.

Flexibility in flapping foil suppresses meandering of induced jet in absence of free stream

Thrust-generating flapping foils are known to produce jets inclined to the free stream at high Strouhal numbers St = fA/U-infinity, where f is the frequency and A is the amplitude of flapping and U-infinity is the free-stream velocity. Our experiments, in the limiting case of St —> infinity (zero free-stream speed), show that a purely oscillatory pitching motion of a chordwise flexible foil produces a coherent jet composed of a reverse Benard-Karman vortex street along the centreline, albeit over a specific range of effective flap stiffnesses. We obtain flexibility by attaching a thin flap to the trailing edge of a rigid NACA0015 foil; length of flap is 0.79 c where c is rigid foil chord length. It is the time-varying deflections of the flexible flap that suppress the meandering found in the jets produced by a pitching rigid foil for zero free-stream condition. Recent experiments (Marais et al., J. Fluid Mech., vol. 710, 2012, p. 659) have also shown that the flexibility increases the St at which non-deflected jets are obtained. Analysing the near-wake vortex dynamics from flow visualization and particle image velocimetry (PIV) measurements, we identify the mechanisms by which flexibility suppresses jet deflection and meandering. A convenient characterization of flap deformation, caused by fluid-flap interaction, is through a non-dimensional effective stiffness', EI* = 8 EI/(rho V-TEmax(2) s(f) c(f)(3)/2), representing the inverse of the flap deflection due to the fluid-dynamic loading; here, EI is the bending stiffness of flap, rho is fluid density, V-TEmax is the maximum velocity of rigid foil trailing edge, s(f) is span and c(f) is chord length of the flexible flap. By varying the amplitude and frequency of pitching, we obtain a variation in EI* over nearly two orders of magnitude and show that only moderate EI*. (0.1 less than or similar to EI * less than or similar to 1 generates a sustained, coherent, orderly jet. Relatively `stiff' flaps (EI* greater than or similar to 1), including the extreme case of no flap, produce meandering jets, whereas highly `flexible' flaps (EI* less than or similar to 0.1) produce spread-out jets. Obtained from the measured mean velocity fields, we present values of thrust coefficients for the cases for which orderly jets are observed.

Some Extensions of the K-Means Algorithm for Image Segmentation and Pattern Classification

In this paper we present some extensions to the k-means algorithm for vector quantization that permit its efficient use in image segmentation and pattern classification tasks. It is shown that by introducing state variables that correspond to certain statistics of the dynamic behavior of the algorithm, it is possible to find the representative centers fo the lower dimensional maniforlds that define the boundaries between classes, for clouds of multi-dimensional, mult-class data; this permits one, for example, to find class boundaries directly from sparse data (e.g., in image segmentation tasks) or to efficiently place centers for pattern classification (e.g., with local Gaussian classifiers). The same state variables can be used to define algorithms for determining adaptively the optimal number of centers for clouds of data with space-varying density. Some examples of the applicatin of these extensions are also given.

Towards an Example-Based Image Compression Architecture for Video-Conferencing

This paper consists of two major parts. First, we present the outline of a simple approach to very-low bandwidth video-conferencing system relying on an example-based hierarchical image compression scheme. In particular, we discuss the use of example images as a model, the number of required examples, faces as a class of semi-rigid objects, a hierarchical model based on decomposition into different time-scales, and the decomposition of face images into patches of interest. In the second part, we present several algorithms for image processing and animation as well as experimental evaluations. Among the original contributions of this paper is an automatic algorithm for pose estimation and normalization. We also review and compare different algorithms for finding the nearest neighbors in a database for a new input as well as a generalized algorithm for blending patches of interest in order to synthesize new images. Finally, we outline the possible integration of several algorithms to illustrate a simple model-based video-conference system.

The What-And-Where Filter: A Spatial Mapping Neural Network for Object Recognition and Image Understanding

The What-and-Where filter forms part of a neural network architecture for spatial mapping, object recognition, and image understanding. The Where fllter responds to an image figure that has been separated from its background. It generates a spatial map whose cell activations simultaneously represent the position, orientation, ancl size of all tbe figures in a scene (where they are). This spatial map may he used to direct spatially localized attention to these image features. A multiscale array of oriented detectors, followed by competitve and interpolative interactions between position, orientation, and size scales, is used to define the Where filter. This analysis discloses several issues that need to be dealt with by a spatial mapping system that is based upon oriented filters, such as the role of cliff filters with and without normalization, the double peak problem of maximum orientation across size scale, and the different self-similar interpolation properties across orientation than across size scale. Several computationally efficient Where filters are proposed. The Where filter rnay be used for parallel transformation of multiple image figures into invariant representations that are insensitive to the figures' original position, orientation, and size. These invariant figural representations form part of a system devoted to attentive object learning and recognition (what it is). Unlike some alternative models where serial search for a target occurs, a What and Where representation can he used to rapidly search in parallel for a desired target in a scene. Such a representation can also be used to learn multidimensional representations of objects and their spatial relationships for purposes of image understanding. The What-and-Where filter is inspired by neurobiological data showing that a Where processing stream in the cerebral cortex is used for attentive spatial localization and orientation, whereas a What processing stream is used for attentive object learning and recognition.

Joined Spectral Trees for Scalable SPIHT-Based Multispectral Image Compression

In this paper, the compression of multispectral images is addressed. Such 3-D data are characterized by a high correlation across the spectral components. The efficiency of the state-of-the-art wavelet-based coder 3-D SPIHT is considered. Although the 3-D SPIHT algorithm provides the obvious way to process a multispectral image as a volumetric block and, consequently, maintain the attractive properties exhibited in 2-D (excellent performance, low complexity, and embeddedness of the bit-stream), its 3-D trees structure is shown to be not adequately suited for 3-D wavelet transformed (DWT) multispectral images. The fact that each parent has eight children in the 3-D structure considerably increases the list of insignificant sets (LIS) and the list of insignificant pixels (LIP) since the partitioning of any set produces eight subsets which will be processed similarly during the sorting pass. Thus, a significant portion from the overall bit-budget is wastedly spent to sort insignificant information. Through an investigation based on results analysis, we demonstrate that a straightforward 2-D SPIHT technique, when suitably adjusted to maintain the rate scalability and carried out in the 3-D DWT domain, overcomes this weakness. In addition, a new SPIHT-based scalable multispectral image compression algorithm is used in the initial iterations to exploit the redundancies within each group of two consecutive spectral bands. Numerical experiments on a number of multispectral images have shown that the proposed scheme provides significant improvements over related works.

Use of Short Time-on-Stream Attenuated Total Internal Reflection Infrared Spectroscopy To Probe Changes in Adsorption Geometry for Determination of Selectivity in the Hydrogenation of Citral

Abstract Image

A new experimental procedure based on attenuated total reflection infrared spectroscopy has been developed to investigate surface species under liquid phase reaction conditions. The technique has been tested by investigating the enhanced selectivity in the hydrogenation of α,β-unsaturated aldehyde citral over a 5% Pt/SiO2 catalyst toward unsaturated alcohols geraniol/nerol, which occurs when citronellal is added to the reaction. The change in selectivity is proposed to be the result of a change in the citral adsorption mode in the presence of citronellal. Short time on stream attenuated total internal reflection infrared spectroscopy has allowed identification of the adsorption modes of citral. With no citronellal, citral adsorbs through both the C═C and C═O groups; however, in the presence of citronellal, citral adsorption occurs through the C═O group only, which is proposed to be the cause of the altered reaction selectivity.

Example Based Image Analysis and Synthesis

Image analysis and graphics synthesis can be achieved with learning techniques using directly image examples without physically-based, 3D models. In our technique: -- the mapping from novel images to a vector of "pose" and "expression" parameters can be learned from a small set of example images using a function approximation technique that we call an analysis network; -- the inverse mapping from input "pose" and "expression" parameters to output images can be synthesized from a small set of example images and used to produce new images using a similar synthesis network. The techniques described here have several applications in computer graphics, special effects, interactive multimedia and very low bandwidth teleconferencing.

Gender and public relations: critical perspectives on voice, image and identity

Although there is a small body of feminist scholarship that problematizes gender in public relations, gender is a relatively undefined area of thinking in the field and there have been few serious studies of the socially constructed roles defining women and men in public relations. This book is positioned within the critical public relations stream. Through the prism of 'gender and public relations', it examines not only the manipulatory, but also the emancipatory, subversive and transformatory potential of public relations for the construction of meaning. Its focus is on the dynamic interrelationships arising from public relations activities in society and the gendered, lived experiences of people working in the occupation of public relations. There are many previously unexplored areas within and through public relations which the book examines. These include: • the production of social meaning and power relations. • advocacy and activist campaigns for social and political change. • the negotiation of identity, diversity and cultural practice. • celebrity, bodies, fashion and harassment in the workplace. • notions of managing reputation and communicating policy. In extending the field of inquiry, this edited collection highlights how gender is accomplished and transformed, and, thus how power is exercised and inequality (re)produced or challenged in public relations. The book will expand thinking about power relations and privilege for both women and men and how these are affected by the interplay of social, cultural and institutional practices. Winner of the Outstanding Book PRide Award, awarded by the National Communication Association (NCA).