Search

An improved unsupervised classification method to extract and link places features and cluster recurrent physical locations (key-places) within a movie is presented. Our approach finds links between key frames of a common key-place based on the use of a probabilistic latent space model over the possible local matches between the key frames image set. This allows the extraction of significant groups of local matching descriptors that may represent characteristic elements of a key-place. An exhaustive evaluation of our approach was conducted on in-house and public image datasets, as well as on full-length movies. Results revealed that our method is very efficient for near-duplicate object/background detection with weak overlap. Performance measurements on full-length movies indicate a recognition rate of about 75% on the key-places clustering with a false alarm rate (FAR) of approximately 2%.

This paper presents the status of a R&D project targeting the development of computer-vision tools to assist humans in generating and rendering video description for people with vision loss. Three principal issues are discussed: (1) production practices, (2) needs of people with vision loss, and (3) current system design, core technologies and implementation. The paper provides the main conclusions of consultations with producers of video description regarding their practices and with end-users regarding their needs, as well as an analysis of described productions that lead to propose a video description typology. The current status of a prototype software is also presented (audio-vision manager) that uses many computer-vision technologies (shot transition detection, key-frame identification, key-face recognition, key-text spotting, visual motion, gait/gesture characterization, key-place identification, key-object spotting and image categorization) to automatically extract visual content, associate textual descriptions and add them to the audio track with a synthetic voice. A proof of concept is also briefly described for a first adaptive video description player which allows end users to select various levels of video description.

A new, simple and practical way of fusing audio and visual information to enhance audiovisual automatic speech recognition within the framework of an application of large-vocabulary speech recognition of French Canadian speech is presented, and the experimental methodology is described in detail. The visual information about mouth shape is extracted off-line using a cascade of weak classifiers and a Kalman filter, and is combined with the large-vocabulary speech recognition system of the Centre de Recherche Informatique de Montreal. The visual classification is performed by a pair-wise kernel-based linear discriminant analysis (KLDA) applied on a principal component analysis (PCA) subspace, followed by a binary combination and voting algorithm on 35 French phonetic classes. Three fusion approaches are compared: (1) standard low-level feature-based fusion, (2) decision-based fusion within the framework of the transferable belief model (an interpretation of the Dempster-Shafer evidential theory), and (3) a combination of (1) and (2). For decision-based fusion, the audio information is considered to be a precise Bayesian source, while the visual information is considered an imprecise evidential source. This treatment ensures that the visual information does not significantly degrade the audio information in situations where the audio performs well (e.g., a controlled noise-free environment). Results show significant improvement in the word error rate to a level comparable to that of more sophisticated systems. To the authors' knowledge, this work is the first to address large-vocabulary audiovisual recognition of French Canadian speech and decision-based audiovisual fusion within the transferable belief model.

(1) egalisation locale de l'histogramme de l'image, (2) creation d'images de texture selon la methode d'Unser, (3) classification dirigee et (4) filtrage post-classification. L'experimentation avec une image IKONOS couvrant une zone periurbaine de la Region metropolitaine de Montreal a demontre que les quatre mesures de texture qui permettent la meilleure delimitation des surfaces boisees sont la moyenne, le contraste, la correlation et l'ecart type, generees a partir de fenetres de dimension entre 17 × 17 et 35 × 35 pixels, avec des pas de 1 ou 2 pixels. Le taux de detection des boises d'une etendue minimale de 1000 m2 est eleve (pres de 90 %), et les confusions avec les autres classes d'occupation du sol sont reduites (coefficients Kappa d'environ 0,8). Bien que l'etude se concentre sur des mesures de texture du deuxieme ordre, les resultats pourraient servir de base a l'etablissement d'une methode plus generique pour l'inventaire et le suivi des surfaces boisees en milieu urbain.

We present the results of a study on the application of registration and pixel-level fusion techniques to retinal images. The images are of different modalities (color, fluorescein angiogram), different resolutions, and taken at different times (from a few minutes during an angiography examination to several years between two examinations). We propose a new registration method based on global point mapping with blood vessel bifurcations as control points and a search for control point matches that uses local structural information of the retinal network. Three transformation types (similarity, affine, and second-order polynomial) are evaluated on each image pair. Fourteen pixel-level fusion techniques have been tested and classified according to their qualitative and quantitative performance. Four quantitative fusion performance criteria are used to evaluate the gain obtained with the grayscale fusion.

Reports on the design and test of an image processing algorithm for the localization of the optic disk (OD) in low-resolution (about 20 /spl mu//pixel) color fundus images. The design relies on the combination of two procedures: 1) a Hausdorff-based template matching technique on edge map, guided by 2) a pyramidal decomposition for large scale object tracking. The two approaches are tested against a database of 40 images of various visual quality and retinal pigmentation, as well as of normal and small pupils. An average error of 7% on OD center positioning is reached with no false detection. In addition, a confidence level is associated to the final detection that indicates the "level of difficulty" the detector has to identify the OD position and shape.

This paper presents a GIS-centric computer vision system for tracking high-speed skaters in competition and training situations. This system outputs spatio-temporal trajectories that are analyzed through presented geometric, physical and power-based models in order to evaluate sports performance. Through spatial SQL and shared database access, the GIS enables the manipulation of the trajectories and offer, amongst other, selection, fusion and completion of tracks, as well as automatic computation of distances between competitors. We propose a new method for (1) calibrating the cameras using a GIS-like image rectification method; 2) simulating trajectories and their associated power profiles to model the sport's domain; 3) incorporating the instant center of rotation in both the particle filter's dynamic model and the simulator and 4) leveraging several GIS advanced capabilities in a client-server application. Experimental results show that our rectification methology is very precise, that our tracking performance is acceptable and that the proposed power balance model is very close to the state of the art.

Facial expressions (FE) are one of the important cognitive load markers in the context of car driving. Any muscular activity can be coded as an action unit (AU) which are the building blocks of FE. Precise facial point tracking is crucial since it is a necessary step for AU detection. Here, we present our progress in FE analysis based on AU detection on face infrared videos in the context of a car driving simulator. First, we propose a real-time facial points tracking method (HCPF-AAM) using a modified particle filter (PF) based on Harris corner samples which is optimized and combined with an Active Appearance Model (AAM) approach. Robustness of PF, precision of Harris corner-based samples, and optimization of AAM result in a powerful facial points tracking on very low-contrast images acquired under near-infrared (NIR) illumination. Second, detection of the most common AUs in the context of car driving, identified by a certified Facial Action Coding System coder is presented. For detection of each specified AU, the spatio-temporal analysis of related tracked facial points is performed. Then, a combination of rule-based scheme with Probabilistic Actively Learned Support Vector Machines is developed to classify the features calculated from the related tracked facial points. Results show that with such a scheme, we can obtain more than 91% of precision in the detection of the five most common AUs for low-contrast NIR images and 90% of precision in the MMI dataset.

We report results on video copy detection using nearest-neighbor (NN) mapping that has been used successfully in audio copy detection. For copy detection search, we use a sliding window to move the query video over the test video, and count the number of frames of query that match the frames in the test segment. The feature in the test frame that we match is the frame number of the query that is closest to that test frame. This leads to good matching scores even when the query video is distorted and contains occlusions. We test the NN mapping algorithm and the video features that map test frame to the closest query frame on TRECVID 2009 and 2010 content-based copy detection (CBCD) evaluation data. For both these tasks, the NN mapping for video copy detection gives minimal normalized detection cost rate (min NDCR) comparable to that achieved with audio copy detection for the same task. For the TRECVID 2011 CBCD evaluation data we got the lowest min NDCR for 26 out of 56 transforms for actual no false alarm case.

A variable-coefficient nonlinear Schrodinger (VCNLS) equation, involving three arbitrary complex functions of space-time (in 1 + 1 dimensions) is analysed from the point of view of its symmetries. All equations of the type studied having non-trivial Lie point symmetry groups G are identified. The symmetry group is shown to be at most five-dimensional and only when the equation is equivalent to the NLS equation itself or to a rather special complex Ginzburg-Landau equation. Lie point transformations are used to obtain solutions of specific VCNLS equations that should be of interest in nonlinear optics or other branches of physics.