Algorithms for on-line image registration from multiple views

Images of a scene, static or dynamic, are generally acquired at different epochs from different viewpoints. They potentially gather information about the whole scene and its relative motion with respect to the acquisition device. Data from different (in the spatial or temporal domain) visual sources can be fused together to provide a unique consistent representation of the whole scene, even recovering the third dimension, permitting a more complete understanding of the scene content. Moreover, the pose of the acquisition device can be achieved by estimating the relative motion parameters linking different views, thus providing localization information for automatic guidance purposes. Image registration is based on the use of pattern recognition techniques to match among corresponding parts of different views of the acquired scene. Depending on hypotheses or prior information about the sensor model, the motion model and/or the scene model, this information can be used to estimate global or local geometrical mapping functions between different images or different parts of them. These mapping functions contain relative motion parameters between the scene and the sensor(s) and can be used to integrate accordingly informations coming from the different sources to build a wider or even augmented representation of the scene. Accordingly, for their scene reconstruction and pose estimation capabilities, nowadays image registration techniques from multiple views are increasingly stirring up the interest of the scientific and industrial community. Depending on the applicative domain, accuracy, robustness, and computational payload of the algorithms represent important issues to be addressed and generally a trade-off among them has to be reached. Moreover, on-line performance is desirable in order to guarantee the direct interaction of the vision device with human actors or control systems. This thesis follows a general research approach to cope with these issues, almost independently from the scene content, under the constraint of rigid motions. This approach has been motivated by the portability to very different domains as a very desirable property to achieve. A general image registration approach suitable for on-line applications has been devised and assessed through two challenging case studies in different applicative domains. The first case study regards scene reconstruction through on-line mosaicing of optical microscopy cell images acquired with non automated equipment, while moving manually the microscope holder. By registering the images the field of view of the microscope can be widened, preserving the resolution while reconstructing the whole cell culture and permitting the microscopist to interactively explore the cell culture. In the second case study, the registration of terrestrial satellite images acquired by a camera integral with the satellite is utilized to estimate its three-dimensional orientation from visual data, for automatic guidance purposes. Critical aspects of these applications are emphasized and the choices adopted are motivated accordingly. Results are discussed in view of promising future developments.

A Cognitive Science Reasoning in Recognition of Emotions in Audio-Visual Speech

In this report we summarize the state-of-the-art of speech emotion recognition from the signal processing point of view. On the bases of multi-corporal experiments with machine-learning classifiers, the observation is made that existing approaches for supervised machine learning lead to database dependent classifiers which can not be applied for multi-language speech emotion recognition without additional training because they discriminate the emotion classes following the used training language. As there are experimental results showing that Humans can perform language independent categorisation, we made a parallel between machine recognition and the cognitive process and tried to discover the sources of these divergent results. The analysis suggests that the main difference is that the speech perception allows extraction of language independent features although language dependent features are incorporated in all levels of the speech signal and play as a strong discriminative function in human perception. Based on several results in related domains, we have suggested that in addition, the cognitive process of emotion-recognition is based on categorisation, assisted by some hierarchical structure of the emotional categories, existing in the cognitive space of all humans. We propose a strategy for developing language independent machine emotion recognition, related to the identification of language independent speech features and the use of additional information from visual (expression) features.

Geometric Aspects of Visual Object Recognition

This thesis presents there important results in visual object recognition based on shape. (1) A new algorithm (RAST; Recognition by Adaptive Sudivisions of Tranformation space) is presented that has lower average-case complexity than any known recognition algorithm. (2) It is shown, both theoretically and empirically, that representing 3D objects as collections of 2D views (the "View-Based Approximation") is feasible and affects the reliability of 3D recognition systems no more than other commonly made approximations. (3) The problem of recognition in cluttered scenes is considered from a Bayesian perspective; the commonly-used "bounded-error errorsmeasure" is demonstrated to correspond to an independence assumption. It is shown that by modeling the statistical properties of real-scenes better, objects can be recognized more reliably.

A variational method to retrieve the extinction profile in liquid clouds using multiple field-of-view lidar

Liquid clouds play a profound role in the global radiation budget but it is difficult to remotely retrieve their vertical profile. Ordinary narrow field-of-view (FOV) lidars receive a strong return from such clouds but the information is limited to the first few optical depths. Wideangle multiple-FOV lidars can isolate radiation scattered multiple times before returning to the instrument, often penetrating much deeper into the cloud than the singly-scattered signal. These returns potentially contain information on the vertical profile of extinction coefficient, but are challenging to interpret due to the lack of a fast radiative transfer model for simulating them. This paper describes a variational algorithm that incorporates a fast forward model based on the time-dependent two-stream approximation, and its adjoint. Application of the algorithm to simulated data from a hypothetical airborne three-FOV lidar with a maximum footprint width of 600m suggests that this approach should be able to retrieve the extinction structure down to an optical depth of around 6, and total opticaldepth up to at least 35, depending on the maximum lidar FOV. The convergence behavior of Gauss-Newton and quasi-Newton optimization schemes are compared. We then present results from an application of the algorithm to observations of stratocumulus by the 8-FOV airborne “THOR” lidar. It is demonstrated how the averaging kernel can be used to diagnose the effective vertical resolution of the retrieved profile, and therefore the depth to which information on the vertical structure can be recovered. This work enables exploitation of returns from spaceborne lidar and radar subject to multiple scattering more rigorously than previously possible.

Speech Display Simulation System for a Comparative Study of Some Visual Speech Displays.

Includes bibliographic references (216).

A comparative study of some visual speech displays,

Supported by Contract AT(11-1)-1018 and Contract AT(11-1)-2118 with U.S. Atomic Energy Commission.

Auditory-visual speech integration by prelinguistic infants: Perception of an emergent consonant in the McGurk effect

The McGurk effect, in which auditory [ba] dubbed onto [go] lip movements is perceived as da or tha, was employed in a real-time task to investigate auditory-visual speech perception in prelingual infants. Experiments 1A and 1B established the validity of real-time dubbing for producing the effect. In Experiment 2, 4(1)/(2)-month-olds were tested in a habituation-test paradigm, in which 2 an auditory-visual stimulus was presented contingent upon visual fixation of a live face. The experimental group was habituated to a McGurk stimulus (auditory [ba] visual [ga]), and the control group to matching auditory-visual [ba]. Each group was then presented with three auditory-only test trials, [ba], [da], and [deltaa] (as in then). Visual-fixation durations in test trials showed that the experimental group treated the emergent percept in the McGurk effect, [da] or [deltaa], as familiar (even though they had not heard these sounds previously) and [ba] as novel. For control group infants [da] and [deltaa] were no more familiar than [ba]. These results are consistent with infants'perception of the McGurk effect, and support the conclusion that prelinguistic infants integrate auditory and visual speech information. (C) 2004 Wiley Periodicals, Inc.

Contributions to gait recognition using multiple views

Esta tesis se centra en la identificación de personas a través de la forma de caminar. El problema del reconocimiento del paso ha sido tratado mediante diferentes enfoques, en los dominios 2D y 3D, y usando una o varias vistas. Sin embargo, la dependencia con respecto al punto de vista, y por tanto de la trayectoria del sujeto al caminar sigue siendo aún un problema abierto. Se propone hacer frente al problema de la dependencia con respecto a la trayectoria por medio de reconstrucciones 3D de sujetos caminando. El uso de reconstrucciones varias ventajas que cabe destacar. En primer lugar, permite explotar una mayor cantidad de información en contraste con los métodos que extraen los descriptores de la marcha a partir de imágenes, en el dominio 2D. En segundo lugar, las reconstrucciones 3D pueden ser alineadas a lo largo de la marcha como si el sujeto hubiera caminado en una cinta andadora, proporcionando así una forma de analizar el paso independientemente de la trayectoria seguida. Este trabajo propone tres enfoques para resolver el problema de la dependencia a la vista: 1. Mediante la utilización de reconstrucciones volumétricas alineadas. 2. Mediante el uso de reconstrucciones volumétricas no alineadas. 3. Sin usar reconstrucciones. Se proponen además tres tipos de descriptores. El primero se centra en describir el paso mediante análisis morfológico de los volúmenes 3D alineados. El segundo hace uso del concepto de entropa de la información para describir la dinámica del paso humano. El tercero persigue capturar la dinámica de una forma invariante a rotación, lo cual lo hace especialmente interesante para ser aplicado tanto en trayectorias curvas como rectas, incluyendo cambios de dirección. Estos enfoques han sido probados sobre dos bases de datos públicas. Ambas están especialmente diseñadas para tratar el problema de la dependencia con respecto al punto de vista, y por tanto de la dependencia con respecto a la trayectoria. Los resultados experimentales muestran que para el enfoque basado en reconstrucciones volumétricas alineadas, el descriptor del paso basado en entropa consigue los mejores resultados, en comparación con métodos estrechamente relacionados del Estado del Arte actual. No obstante, el descriptor invariante a rotación consigue una tasa de reconocimiento que supera a los métodos actuales sin requerir la etapa previa de alineamiento de las reconstrucciones 3D.

Spectral peak resolution and speech recognition in quiet: Normal hearing, hearing impaired and cochlear implant listeners

Spectral peak resolution was investigated in normal hearing (NH), hearing impaired (HI), and cochlear implant (CI) listeners. The task involved discriminating between two rippled noise stimuli in which the frequency positions of the log-spaced peaks and valleys were interchanged. The ripple spacing was varied adaptively from 0.13 to 11.31 ripples/octave, and the minimum ripple spacing at which a reversal in peak and trough positions could be detected was determined as the spectral peak resolution threshold for each listener. Spectral peak resolution was best, on average, in NH listeners, poorest in CI listeners, and intermediate for HI listeners. There was a significant relationship between spectral peak resolution and both vowel and consonant recognition in quiet across the three listener groups. The results indicate that the degree of spectral peak resolution required for accurate vowel and consonant recognition in quiet backgrounds is around 4 ripples/octave, and that spectral peak resolution poorer than around 1–2 ripples/octave may result in highly degraded speech recognition. These results suggest that efforts to improve spectral peak resolution for HI and CI users may lead to improved speech recognition

Speech recognition in noise for cochlear implant listeners: Benefits of residual hearing

The purpose of this study was to explore the potential advantages, both theoretical and applied, of preserving low-frequency acoustic hearing in cochlear implant patients. Several hypotheses are presented that predict that residual low-frequency acoustic hearing along with electric stimulation for high frequencies will provide an advantage over traditional long-electrode cochlear implants for the recognition of speech in competing backgrounds. A simulation experiment in normal-hearing subjects demonstrated a clear advantage for preserving low-frequency residual acoustic hearing for speech recognition in a background of other talkers, but not in steady noise. Three subjects with an implanted "short-electrode" cochlear implant and preserved low-frequency acoustic hearing were also tested on speech recognition in the same competing backgrounds and compared to a larger group of traditional cochlear implant users. Each of the three short-electrode subjects performed better than any of the traditional long-electrode implant subjects for speech recognition in a background of other talkers, but not in steady noise, in general agreement with the simulation studies. When compared to a subgroup of traditional implant users matched according to speech recognition ability in quiet, the short-electrode patients showed a 9-dB advantage in the multitalker background. These experiments provide strong preliminary support for retaining residual low-frequency acoustic hearing in cochlear implant patients. The results are consistent with the idea that better perception of voice pitch, which can aid in separating voices in a background of other talkers, was responsible for this advantage.

Benefits of amplification for speech recognition in background noise

The purpose of the present study was to examine the benefits of providing audible speech to listeners with sensorineural hearing loss when the speech is presented in a background noise. Previous studies have shown that when listeners have a severe hearing loss in the higher frequencies, providing audible speech (in a quiet background) to these higher frequencies usually results in no improvement in speech recognition. In the present experiments, speech was presented in a background of multitalker babble to listeners with various severities of hearing loss. The signal was low-pass filtered at numerous cutoff frequencies and speech recognition was measured as additional high-frequency speech information was provided to the hearing-impaired listeners. It was found in all cases, regardless of hearing loss or frequency range, that providing audible speech resulted in an increase in recognition score. The change in recognition as the cutoff frequency was increased, along with the amount of audible speech information in each condition (articulation index), was used to calculate the "efficiency" of providing audible speech. Efficiencies were positive for all degrees of hearing loss. However, the gains in recognition were small, and the maximum score obtained by an listener was low, due to the noise background. An analysis of error patterns showed that due to the limited speech audibility in a noise background, even severely impaired listeners used additional speech audibility in the high frequencies to improve their perception of the "easier" features of speech including voicing

Grammatical priming of visual word recognition in fourth-grade children

Previous work examining context effects in children has been limited to semantic context. The current research examined the effects of grammatical priming of word-naming in fourth-grade children. In Experiment 1, children named both inflected and uninflected noun and verb target words faster when they were preceded by grammatically constraining primes than when they were preceded by neutral primes. Experiment 1 used a long stimulus onset asynchrony (SOA) interval of 750 msec. Experiment 2 replicated the grammatical priming effect at two SOA intervals (400 msec and 700 msec), suggesting that the grammatical priming effect does not reflect the operation of any gross strategic effects directly attributable to the long SOA interval employed in Experiment 1. Grammatical context appears to facilitate target word naming by constraining target word class. Further work is required to elucidate the loci of this effect.

What happens in the first 200 ms of word reading : ERP studies on visual word recognition with top-down and bottom-up approaches /

In this thesis, three main questions were addressed using event-related potentials (ERPs): (1) the timing of lexical semantic access, (2) the influence of "top-down" processes on visual word processing, and (3) the influence of "bottom-up" factors on visual word processing. The timing of lexical semantic access was investigated in two studies using different designs. In Study 1,14 participants completed two tasks: a standard lexical decision (LD) task which required a word/nonword decision to each target stimulus, and a semantically primed version (LS) of it using the same category of words (e.g., animal) within each block following which participants made a category judgment. In Study 2, another 12 participants performed a standard semantic priming task, where target stimulus words (e.g., nurse) could be either semantically related or unrelated to their primes (e.g., doctor, tree) but the order of presentation was randomized. We found evidence in both ERP studies that lexical semantic access might occur early within the first 200 ms (at about 170 ms for Study 1 and at about 160 ms for Study 2). Our results were consistent with more recent ERP and eye-tracking studies and are in contrast with the traditional research focus on the N400 component. "Top-down" processes, such as a person's expectation and strategic decisions, were possible in Study 1 because of the blocked design, but they were not for Study 2 with a randomized design. Comparing results from two studies, we found that visual word processing could be affected by a person's expectation and the effect occurred early at a sensory/perceptual stage: a semantic task effect in the PI component at about 100 ms in the ERP was found in Study 1 , but not in Study 2. Furthermore, we found that such "top-down" influence on visual word processing might be mediated through separate mechanisms depending on whether the stimulus was a word or a nonword. "Bottom-up" factors involve inherent characteristics of particular words, such as bigram frequency (the total frequency of two-letter combinations of a word), word frequency (the frequency of the written form of a word), and neighborhood density (the number of words that can be generated by changing one letter of an original word or nonword). A bigram frequency effect was found when comparing the results from Studies 1 and 2, but it was examined more closely in Study 3. Fourteen participants performed a similar standard lexical decision task but the words and nonwords were selected systematically to provide a greater range in the aforementioned factors. As a result, a total of 18 word conditions were created with 18 nonword conditions matched on neighborhood density and neighborhood frequency. Using multiple regression analyses, we foimd that the PI amplitude was significantly related to bigram frequency for both words and nonwords, consistent with results from Studies 1 and 2. In addition, word frequency and neighborhood frequency were also able to influence the PI amplitude separately for words and for nonwords and there appeared to be a spatial dissociation between the two effects: for words, the word frequency effect in PI was found at the left electrode site; for nonwords, the neighborhood frequency effect in PI was fovind at the right elecfrode site. The implications of otir findings are discussed.

A Detailed Look at Scale and Translation Invariance in a Hierarchical Neural Model of Visual Object Recognition

The HMAX model has recently been proposed by Riesenhuber & Poggio as a hierarchical model of position- and size-invariant object recognition in visual cortex. It has also turned out to model successfully a number of other properties of the ventral visual stream (the visual pathway thought to be crucial for object recognition in cortex), and particularly of (view-tuned) neurons in macaque inferotemporal cortex, the brain area at the top of the ventral stream. The original modeling study only used ``paperclip'' stimuli, as in the corresponding physiology experiment, and did not explore systematically how model units' invariance properties depended on model parameters. In this study, we aimed at a deeper understanding of the inner workings of HMAX and its performance for various parameter settings and ``natural'' stimulus classes. We examined HMAX responses for different stimulus sizes and positions systematically and found a dependence of model units' responses on stimulus position for which a quantitative description is offered. Interestingly, we find that scale invariance properties of hierarchical neural models are not independent of stimulus class, as opposed to translation invariance, even though both are affine transformations within the image plane.

Visual Object Recognition Using Deformable Models of Vehicles

This workshop paper reports recent developments to a vision system for traffic interpretation which relies extensively on the use of geometrical and scene context. Firstly, a new approach to pose refinement is reported, based on forces derived from prominent image derivatives found close to an initial hypothesis. Secondly, a parameterised vehicle model is reported, able to represent different vehicle classes. This general vehicle model has been fitted to sample data, and subjected to a Principal Component Analysis to create a deformable model of common car types having 6 parameters. We show that the new pose recovery technique is also able to operate on the PCA model, to allow the structure of an initial vehicle hypothesis to be adapted to fit the prevailing context. We report initial experiments with the model, which demonstrate significant improvements to pose recovery.