Ricard Borras, Agata Lapedriza, & Laura Igual. (2012). Depth Information in Human Gait Analysis: An Experimental Study on Gender Recognition. In 9th International Conference on Image Analysis and Recognition (Vol. 7325, pp. 98–105). Springer Berlin Heidelberg.
Abstract: This work presents DGait, a new gait database acquired with a depth camera. This database contains videos from 53 subjects walking in different directions. The intent of this database is to provide a public set to explore whether the depth can be used as an additional information source for gait classification purposes. Each video is labelled according to subject, gender and age. Furthermore, for each subject and view point, we provide initial and final frames of an entire walk cycle. On the other hand, we perform gait-based gender classification experiments with DGait database, in order to illustrate the usefulness of depth information for this purpose. In our experiments, we extract 2D and 3D gait features based on shape descriptors, and compare the performance of these features for gender identification, using a Kernel SVM. The obtained results show that depth can be an information source of great relevance for gait classification problems.
|
Jordi Roca. (2012). Constancy and inconstancy in categorical colour perception (Maria Vanrell, & C. Alejandro Parraga, Eds.). Ph.D. thesis, , .
Abstract: To recognise objects is perhaps the most important task an autonomous system, either biological or artificial needs to perform. In the context of human vision, this is partly achieved by recognizing the colour of surfaces despite changes in the wavelength distribution of the illumination, a property called colour constancy. Correct surface colour recognition may be adequately accomplished by colour category matching without the need to match colours precisely, therefore categorical colour constancy is likely to play an important role for object identification to be successful. The main aim of this work is to study the relationship between colour constancy and categorical colour perception. Previous studies of colour constancy have shown the influence of factors such the spatio-chromatic properties of the background, individual observer's performance, semantics, etc. However there is very little systematic study of these influences. To this end, we developed a new approach to colour constancy which includes both individual observers' categorical perception, the categorical structure of the background, and their interrelations resulting in a more comprehensive characterization of the phenomenon. In our study, we first developed a new method to analyse the categorical structure of 3D colour space, which allowed us to characterize individual categorical colour perception as well as quantify inter-individual variations in terms of shape and centroid location of 3D categorical regions. Second, we developed a new colour constancy paradigm, termed chromatic setting, which allows measuring the precise location of nine categorically-relevant points in colour space under immersive illumination. Additionally, we derived from these measurements a new colour constancy index which takes into account the magnitude and orientation of the chromatic shift, memory effects and the interrelations among colours and a model of colour naming tuned to each observer/adaptation state. Our results lead to the following conclusions: (1) There exists large inter-individual variations in the categorical structure of colour space, and thus colour naming ability varies significantly but this is not well predicted by low-level chromatic discrimination ability; (2) Analysis of the average colour naming space suggested the need for an additional three basic colour terms (turquoise, lilac and lime) for optimal colour communication; (3) Chromatic setting improved the precision of more complex linear colour constancy models and suggested that mechanisms other than cone gain might be best suited to explain colour constancy; (4) The categorical structure of colour space is broadly stable under illuminant changes for categorically balanced backgrounds; (5) Categorical inconstancy exists for categorically unbalanced backgrounds thus indicating that categorical information perceived in the initial stages of adaptation may constrain further categorical perception.
|
Petia Radeva, Michal Drozdzal, Santiago Segui, Laura Igual, Carolina Malagelada, Fernando Azpiroz, et al. (2012). Active labeling: Application to wireless endoscopy analysis. In High Performance Computing and Simulation, International Conference on (pp. 174–181).
Abstract: Today, robust learners trained in a real supervised machine learning application should count with a rich collection of positive and negative examples. Although in many applications, it is not difficult to obtain huge amount of data, labeling those data can be a very expensive process, especially when dealing with data of high variability and complexity. A good example of such cases are data from medical imaging applications where annotating anomalies like tumors, polyps, atherosclerotic plaque or informative frames in wireless endoscopy need highly trained experts. Building a representative set of training data from medical videos (e.g. Wireless Capsule Endoscopy) means that thousands of frames to be labeled by an expert. It is quite normal that data in new videos come different and thus are not represented by the training set. In this paper, we review the main approaches on active learning and illustrate how active learning can help to reduce expert effort in constructing the training sets. We show that applying active learning criteria, the number of human interventions can be significantly reduced. The proposed system allows the annotation of informative/non-informative frames of Wireless Capsule Endoscopy video containing more than 30000 frames each one with less than 100 expert ”clicks”.
|
Xavier Otazu. (2012). Perceptual tone-mapping operator based on multiresolution contrast decomposition. In Perception (Vol. 41, 86).
Abstract: Tone-mapping operators (TMO) are used to display high dynamic range(HDR) images in low dynamic range (LDR) displays. Many computational and biologically inspired approaches have been used in the literature, being many of them based on multiresolution decompositions. In this work, a simple two stage model for TMO is presented. The first stage is a novel multiresolution contrast decomposition, which is inspired in a pyramidal contrast decomposition (Peli, 1990 Journal of the Optical Society of America7(10), 2032-2040).
This novel multiresolution decomposition represents the Michelson contrast of the image at different spatial scales. This multiresolution contrast representation, applied on the intensity channel of an opponent colour decomposition, is processed by a non-linear saturating model of V1 neurons (Albrecht et al, 2002 Journal ofNeurophysiology 88(2) 888-913). This saturation model depends on the visual frequency, and it has been modified in order to include information from the extended Contrast Sensitivity Function (e-CSF) (Otazu et al, 2010 Journal ofVision10(12) 5).
A set of HDR images in Radiance RGBE format (from CIS HDR Photographic Survey and Greg Ward database) have been used to test the model, obtaining a set of LDR images. The resulting LDR images do not show the usual halo or color modification artifacts.
|
Volkmar Frinken, Francisco Zamora, Salvador España, Maria Jose Castro, Andreas Fischer, & Horst Bunke. (2012). Long-Short Term Memory Neural Networks Language Modeling for Handwriting Recognition. In 21st International Conference on Pattern Recognition (pp. 701–704).
Abstract: Unconstrained handwritten text recognition systems maximize the combination of two separate probability scores. The first one is the observation probability that indicates how well the returned word sequence matches the input image. The second score is the probability that reflects how likely a word sequence is according to a language model. Current state-of-the-art recognition systems use statistical language models in form of bigram word probabilities. This paper proposes to model the target language by means of a recurrent neural network with long-short term memory cells. Because the network is recurrent, the considered context is not limited to a fixed size especially as the memory cells are designed to deal with long-term dependencies. In a set of experiments conducted on the IAM off-line database we show the superiority of the proposed language model over statistical n-gram models.
|
Josep M. Gonfaus. (2012). Towards Deep Image Understanding: From pixels to semantics (Jordi Gonzalez, & Theo Gevers, Eds.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: Understanding the content of the images is one of the greatest challenges of computer vision. Recognition of objects appearing in images, identifying and interpreting their actions are the main purposes of Image Understanding. This thesis seeks to identify what is present in a picture by categorizing and locating all the objects in the scene.
Images are composed by pixels, and one possibility consists of assigning to each pixel an object category, which is commonly known as semantic segmentation. By incorporating information as a contextual cue, we are able to resolve the ambiguity within categories at the pixel-level. We propose three levels of scale in order to resolve such ambiguity.
Another possibility to represent the objects is the object detection task. In this case, the aim is to recognize and localize the whole object by accurately placing a bounding box around it. We present two new approaches. The first one is focused on improving the object representation of deformable part models with the concept of factorized appearances. The second approach addresses the issue of reducing the computational cost for multi-class recognition. The results given have been validated on several commonly used datasets, reaching international recognition and state-of-the-art within the field
|
Carles Sanchez, F. Javier Sanchez, Antoni Rosell, & Debora Gil. (2012). An illumination model of the trachea appearance in videobronchoscopy images. In Image Analysis and Recognition (Vol. 7325, pp. 313–320). LNCS. Springer Berlin Heidelberg.
Abstract: Videobronchoscopy is a medical imaging technique that allows interactive navigation inside the respiratory pathways. This imaging modality provides realistic images and allows non-invasive minimal intervention procedures. Tracheal procedures are routinary interventions that require assessment of the percentage of obstructed pathway for injury (stenosis) detection. Visual assessment in videobronchoscopic sequences requires high expertise of trachea anatomy and is prone to human error.
This paper introduces an automatic method for the estimation of steneosed trachea percentage reduction in videobronchoscopic images. We look for tracheal rings , whose deformation determines the degree of obstruction. For ring extraction , we present a ring detector based on an illumination and appearance model. This model allows us to parametrise the ring detection. Finally, we can infer optimal estimation parameters for any video resolution.
Keywords: Bronchoscopy, tracheal ring, stenosis assesment, trachea appearance model, segmentation
|
David Vazquez, Antonio Lopez, & Daniel Ponsa. (2012). Unsupervised Domain Adaptation of Virtual and Real Worlds for Pedestrian Detection. In 21st International Conference on Pattern Recognition (pp. 3492–3495). Tsukuba Science City, JAPAN: IEEE.
Abstract: Vision-based object detectors are crucial for different applications. They rely on learnt object models. Ideally, we would like to deploy our vision system in the scenario where it must operate, and lead it to self-learn how to distinguish the objects of interest, i.e., without human intervention. However, the learning of each object model requires labelled samples collected through a tiresome manual process. For instance, we are interested in exploring the self-training of a pedestrian detector for driver assistance systems. Our first approach to avoid manual labelling consisted in the use of samples coming from realistic computer graphics, so that their labels are automatically available [12]. This would make possible the desired self-training of our pedestrian detector. However, as we showed in [14], between virtual and real worlds it may be a dataset shift. In order to overcome it, we propose the use of unsupervised domain adaptation techniques that avoid human intervention during the adaptation process. In particular, this paper explores the use of the transductive SVM (T-SVM) learning algorithm in order to adapt virtual and real worlds for pedestrian detection (Fig. 1).
Keywords: Pedestrian Detection; Domain Adaptation; Virtual worlds
|
R. de Nijs, Sebastian Ramos, Gemma Roig, Xavier Boix, Luc Van Gool, & K. Kühnlenz. (2012). On-line Semantic Perception Using Uncertainty. In International Conference on Intelligent Robots and Systems (pp. 4185–4191).
Abstract: Visual perception capabilities are still highly unreliable in unconstrained settings, and solutions might not beaccurate in all regions of an image. Awareness of the uncertainty of perception is a fundamental requirement for proper high level decision making in a robotic system. Yet, the uncertainty measure is often sacrificed to account for dependencies between object/region classifiers. This is the case of Conditional Random Fields (CRFs), the success of which stems from their ability to infer the most likely world configuration, but they do not directly allow to estimate the uncertainty of the solution. In this paper, we consider the setting of assigning semantic labels to the pixels of an image sequence. Instead of using a CRF, we employ a Perturb-and-MAP Random Field, a recently introduced probabilistic model that allows performing fast approximate sampling from its probability density function. This allows to effectively compute the uncertainty of the solution, indicating the reliability of the most likely labeling in each region of the image. We report results on the CamVid dataset, a standard benchmark for semantic labeling of urban image sequences. In our experiments, we show the benefits of exploiting the uncertainty by putting more computational effort on the regions of the image that are less reliable, and use more efficient techniques for other regions, showing little decrease of performance
Keywords: Semantic Segmentation
|
Antonio Hernandez, Miguel Angel Bautista, Xavier Perez Sala, Victor Ponce, Xavier Baro, Oriol Pujol, et al. (2012). BoVDW: Bag-of-Visual-and-Depth-Words for Gesture Recognition. In 21st International Conference on Pattern Recognition.
Abstract: We present a Bag-of-Visual-and-Depth-Words (BoVDW) model for gesture recognition, an extension of the Bag-of-Visual-Words (BoVW) model, that benefits from the multimodal fusion of visual and depth features. State-of-the-art RGB and depth features, including a new proposed depth descriptor, are analysed and combined in a late fusion fashion. The method is integrated in a continuous gesture recognition pipeline, where Dynamic Time Warping (DTW) algorithm is used to perform prior segmentation of gestures. Results of the method in public data sets, within our gesture recognition pipeline, show better performance in comparison to a standard BoVW model.
|
Antonio Hernandez, Nadezhda Zlateva, Alexander Marinov, Miguel Reyes, Petia Radeva, Dimo Dimov, et al. (2012). Human Limb Segmentation in Depth Maps based on Spatio-Temporal Graph Cuts Optimization. JAISE - Journal of Ambient Intelligence and Smart Environments, 4(6), 535–546.
Abstract: We present a framework for object segmentation using depth maps based on Random Forest and Graph-cuts theory, and apply it to the segmentation of human limbs. First, from a set of random depth features, Random Forest is used to infer a set of label probabilities for each data sample. This vector of probabilities is used as unary term in α−β swap Graph-cuts algorithm. Moreover, depth values of spatio-temporal neighboring data points are used as boundary potentials. Results on a new multi-label human depth data set show high performance in terms of segmentation overlapping of the novel methodology compared to classical approaches.
Keywords: Multi-modal vision processing; Random Forest; Graph-cuts; multi-label segmentation; human body segmentation
|
Laura Igual, Joan Carles Soliva, Sergio Escalera, Roger Gimeno, Oscar Vilarroya, & Petia Radeva. (2012). Automatic Brain Caudate Nuclei Segmentation and Classification in Diagnostic of Attention-Deficit/Hyperactivity Disorder. CMIG - Computerized Medical Imaging and Graphics, 36(8), 591–600.
Abstract: We present a fully automatic diagnostic imaging test for Attention-Deficit/Hyperactivity Disorder diagnosis assistance based on previously found evidences of caudate nucleus volumetric abnormalities. The proposed method consists of different steps: a new automatic method for external and internal segmentation of caudate based on Machine Learning methodologies; the definition of a set of new volume relation features, 3D Dissociated Dipoles, used for caudate representation and classification. We separately validate the contributions using real data from a pediatric population and show precise internal caudate segmentation and discrimination power of the diagnostic test, showing significant performance improvements in comparison to other state-of-the-art methods.
Keywords: Automatic caudate segmentation; Attention-Deficit/Hyperactivity Disorder; Diagnostic test; Machine learning; Decision stumps; Dissociated dipoles
|
Francesco Ciompi, Oriol Pujol, Carlo Gatta, Marina Alberti, Simone Balocco, Xavier Carrillo, et al. (2012). HoliMab: A Holistic Approach for Media-Adventitia Border Detection in Intravascular Ultrasound. MIA - Medical Image Analysis, 16(6), 1085–1100.
Abstract: We present a fully automatic methodology for the detection of the Media-Adventitia border (MAb) in human coronary artery in Intravascular Ultrasound (IVUS) images. A robust border detection is achieved by means of a holistic interpretation of the detection problem where the target object, i.e. the media layer, is considered as part of the whole vessel in the image and all the relationships between tissues are learnt. A fairly general framework exploiting multi-class tissue characterization as well as contextual information on the morphology and the appearance of the tissues is presented. The methodology is (i) validated through an exhaustive comparison with both Inter-observer variability on two challenging databases and (ii) compared with state-of-the-art methods for the detection of the MAb in IVUS. The obtained averaged values for the mean radial distance and the percentage of area difference are 0.211 mm and 10.1%, respectively. The applicability of the proposed methodology to clinical practice is also discussed.
Keywords: Media–Adventitia border detection; Intravascular ultrasound; Multi-Scale Stacked Sequential Learning; Error-correcting output codes; Holistic segmentation
|
Antonio Hernandez, Nadezhda Zlateva, Alexander Marinov, Miguel Reyes, Petia Radeva, Dimo Dimov, et al. (2012). Graph Cuts Optimization for Multi-Limb Human Segmentation in Depth Maps. In 25th IEEE Conference on Computer Vision and Pattern Recognition (pp. 726–732). IEEE Xplore.
Abstract: We present a generic framework for object segmentation using depth maps based on Random Forest and Graph-cuts theory, and apply it to the segmentation of human limbs in depth maps. First, from a set of random depth features, Random Forest is used to infer a set of label probabilities for each data sample. This vector of probabilities is used as unary term in α-β swap Graph-cuts algorithm. Moreover, depth of spatio-temporal neighboring data points are used as boundary potentials. Results on a new multi-label human depth data set show high performance in terms of segmentation overlapping of the novel methodology compared to classical approaches.
|
Wenjuan Gong, Jordi Gonzalez, & Xavier Roca. (2012). Human Action Recognition based on Estimated Weak Poses. EURASIPJ - EURASIP Journal on Advances in Signal Processing, .
Abstract: We present a novel method for human action recognition (HAR) based on estimated poses from image sequences. We use 3D human pose data as additional information and propose a compact human pose representation, called a weak pose, in a low-dimensional space while still keeping the most discriminative information for a given pose. With predicted poses from image features, we map the problem from image feature space to pose space, where a Bag of Poses (BOP) model is learned for the final goal of HAR. The BOP model is a modified version of the classical bag of words pipeline by building the vocabulary based on the most representative weak poses for a given action. Compared with the standard k-means clustering, our vocabulary selection criteria is proven to be more efficient and robust against the inherent challenges of action recognition. Moreover, since for action recognition the ordering of the poses is discriminative, the BOP model incorporates temporal information: in essence, groups of consecutive poses are considered together when computing the vocabulary and assignment. We tested our method on two well-known datasets: HumanEva and IXMAS, to demonstrate that weak poses aid to improve action recognition accuracies. The proposed method is scene-independent and is comparable with the state-of-art method.
|