| Home | << 1 2 3 4 5 6 7 8 9 10 >> [11–14] |
|
Ignasi Rius. (2010). Motion Priors for Efficient Bayesian Tracking in Human Sequence Evaluation (Jordi Gonzalez, & Xavier Roca, Eds.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: Recovering human motion by visual analysis is a challenging computer vision research
area with a lot of potential applications. Model-based tracking approaches, and in particular particle lters, formulate the problem as a Bayesian inference task whose aim is to sequentially estimate the distribution of the parameters of a human body model over time. These approaches strongly rely on good dynamical and observation models to predict and update con gurations of the human body according to measurements from the image data. However, it is very di cult to design observation models which extract useful and reliable information from image sequences robustly. This results specially challenging in monocular tracking given that only one viewpoint from the scene is available. Therefore, to overcome these limitations strong motion priors are needed to guide the exploration of the state space. The work presented in this Thesis is aimed to retrieve the 3D motion parameters of a human body model from incomplete and noisy measurements of a monocular image sequence. These measurements consist of the 2D positions of a reduced set of joints in the image plane. Towards this end, we present a novel action-speci c model of human motion which is trained from several databases of real motion-captured performances of an action, and is used as a priori knowledge within a particle ltering scheme. Body postures are represented by means of a simple and compact stick gure model which uses direction cosines to represent the direction of body limbs in the 3D Cartesian space. Then, for a given action, Principal Component Analysis is applied to the training data to perform dimensionality reduction over the highly correlated input data. Before the learning stage of the action model, the input motion performances are synchronized by means of a novel dense matching algorithm based on Dynamic Programming. The algorithm synchronizes all the motion sequences of the same action class, nding an optimal solution in real-time. Then, a probabilistic action model is learnt, based on the synchronized motion examples, which captures the variability and temporal evolution of full-body motion within a speci c action. In particular, for each action, the parameters learnt are: a representative manifold for the action consisting of its mean performance, the standard deviation from the mean performance, the mean observed direction vectors from each motion subsequence of a given length and the expected error at a given time instant. Subsequently, the action-speci c model is used as a priori knowledge on human motion which improves the e ciency and robustness of the overall particle filtering tracking framework. First, the dynamic model guides the particles according to similar situations previously learnt. Then, the state space is constrained so only feasible human postures are accepted as valid solutions at each time step. As a result, the state space is explored more e ciently as the particle set covers the most probable body postures. Finally, experiments are carried out using test sequences from several motion databases. Results point out that our tracker scheme is able to estimate the rough 3D con guration of a full-body model providing only the 2D positions of a reduced set of joints. Separate tests on the sequence synchronization method and the subsequence probabilistic matching technique are also provided. |
|
Francesco Ciompi. (2012). Multi-Class Learning for Vessel Characterization in Intravascular Ultrasound (Petia Radeva, & Oriol Pujol, Eds.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: In this thesis we tackle the problem of automatic characterization of human coronary vessel in Intravascular Ultrasound (IVUS) image modality. The basis for the whole characterization process is machine learning applied to multi-class problems. In all the presented approaches, the Error-Correcting Output Codes (ECOC) framework is used as central element for the design of multi-class classifiers.
Two main topics are tackled in this thesis. First, the automatic detection of the vessel borders is presented. For this purpose, a novel context-aware classifier for multi-class classification of the vessel morphology is presented, namely ECOC-DRF. Based on ECOC-DRF, the lumen border and the media-adventitia border in IVUS are robustly detected by means of a novel holistic approach, achieving an error comparable with inter-observer variability and with state of the art methods. The two vessel borders define the atheroma area of the vessel. In this area, tissue characterization is required. For this purpose, we present a framework for automatic plaque characterization by processing both texture in IVUS images and spectral information in raw Radio Frequency data. Furthermore, a novel method for fusing in-vivo and in-vitro IVUS data for plaque characterization is presented, namely pSFFS. The method demonstrates to effectively fuse data generating a classifier that improves the tissue characterization in both in-vitro and in-vivo datasets. A novel method for automatic video summarization in IVUS sequences is also presented. The method aims to detect the key frames of the sequence, i.e., the frames representative of morphological changes. This novel method represents the basis for video summarization in IVUS as well as the markers for the partition of the vessel into morphological and clinically interesting events. Finally, multi-class learning based on ECOC is applied to lung tissue characterization in Computed Tomography. The novel proposed approach, based on supervised and unsupervised learning, achieves accurate tissue classification on a large and heterogeneous dataset. |
|
Jun Wan, Guodong Guo, Sergio Escalera, Hugo Jair Escalante, & Stan Z. Li. (2020). Multi-modal Face Presentation Attach Detection (Vol. 13).
|
|
Alejandro Gonzalez Alzate. (2015). Multi-modal Pedestrian Detection (David Vazquez, Antonio Lopez, &, Ed.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: Pedestrian detection continues to be an extremely challenging problem in real scenarios, in which situations like illumination changes, noisy images, unexpected objects, uncontrolled scenarios and variant appearance of objects occur constantly. All these problems force the development of more robust detectors for relevant applications like vision-based autonomous vehicles, intelligent surveillance, and pedestrian tracking for behavior analysis. Most reliable vision-based pedestrian detectors base their decision on features extracted using a single sensor capturing complementary features, e.g., appearance, and texture. These features usually are extracted from the current frame, ignoring temporal information, or including it in a post process step e.g., tracking or temporal coherence. Taking into account these issues we formulate the following question: can we generate more robust pedestrian detectors by introducing new information sources in the feature extraction step?
In order to answer this question we develop different approaches for introducing new information sources to well-known pedestrian detectors. We start by the inclusion of temporal information following the Stacked Sequential Learning (SSL) paradigm which suggests that information extracted from the neighboring samples in a sequence can improve the accuracy of a base classifier. We then focus on the inclusion of complementary information from different sensors like 3D point clouds (LIDAR – depth), far infrared images (FIR), or disparity maps (stereo pair cameras). For this end we develop a multi-modal framework in which information from different sensors is used for increasing detection accuracy (by increasing information redundancy). Finally we propose a multi-view pedestrian detector, this multi-view approach splits the detection problem in n sub-problems. Each sub-problem will detect objects in a given specific view reducing in that way the variability problem faced when a single detectors is used for the whole problem. We show that these approaches obtain competitive results with other state-of-the-art methods but instead of design new features, we reuse existing ones boosting their performance. |
|
Partha Pratim Roy. (2010). Multi-Oriented and Multi-Scaled Text Character Analysis and Recognition in Graphical Documents and their Applications to Document Image Retrieval (Josep Llados, & Umapada Pal, Eds.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: With the advent research of Document Image Analysis and Recognition (DIAR), an
important line of research is explored on indexing and retrieval of graphics rich documents. It aims at finding relevant documents relying on segmentation and recognition of text and graphics components underlying in non-standard layout where commercial OCRs can not be applied due to complexity. This thesis is focused towards text information extraction approaches in graphical documents and retrieval of such documents using text information. Automatic text recognition in graphical documents (map, engineering drawing, etc.) involves many challenges because text characters are usually printed in multioriented and multi-scale way along with different graphical objects. Text characters are used to annotate the graphical curve lines and hence, many times they follow curvi-linear paths too. For OCR of such documents, individual text lines and their corresponding words/characters need to be extracted. For recognition of multi-font, multi-scale and multi-oriented characters, we have proposed a feature descriptor for character shape using angular information from contour pixels to take care of the invariance nature. To improve the efficiency of OCR, an approach towards the segmentation of multi-oriented touching strings into individual characters is also discussed. Convex hull based background information is used to segment a touching string into possible primitive segments and later these primitive segments are merged to get optimum segmentation using dynamic programming. To overcome the touching/overlapping problem of text with graphical lines, a character spotting approach using SIFT and skeleton information is included. Afterwards, we propose a novel method to extract individual curvi-linear text lines using the foreground and background information of the characters of the text and a water reservoir concept is used to utilize the background information. We have also formulated the methodologies for graphical document retrieval applications using query words and seals. The retrieval approaches are performed using recognition results of individual components in the document. Given a query text, the system extracts positional knowledge from the query word and uses the same to generate hypothetical locations in the document. Indexing of documents is also performed based on automatic detection of seals from documents containing cluttered background. A seal is characterized by scale and rotation invariant spatial feature descriptors computed from labelled text characters and a concept based on the Generalized Hough Transform is used to locate the seal in documents. |
|
Antonio Lopez. (2000). Multilocal Methods for Ridge and Valley Delineation in Image Analysis. (Joan Serrat, Ed.). Ph.D. thesis, , .
|
|
Angel Sappa, & Jordi Vitria. (2013). Multimodal Interaction in Image and Video Applications (Vol. 48). Springer Berlin Heidelberg.
Abstract: Book Series Intelligent Systems Reference Library
|
|
Fernando Barrera. (2012). Multimodal Stereo from Thermal Infrared and Visible Spectrum (Felipe Lumbreras, & Angel Sappa, Eds.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: Recent advances in thermal infrared imaging (LWIR) has allowed its use in applications beyond of the military domain. Nowadays, this new family of sensors is included in different technical and scientific applications. They offer features that facilitate tasks, such as detection of pedestrians, hot spots, differences in temperature, among others, which can significantly improve the performance of a system where the persons are expected to play the principal role. For instance, video surveillance applications, monitoring, and pedestrian detection.
During this dissertation the next question is stated: Could a couple of sensors measuring different bands of the electromagnetic spectrum, as the visible and thermal infrared, be used to extract depth information? Although it is a complex question, we shows that a system of these characteristics is possible as well as their advantages, drawbacks, and potential opportunities. The matching and fusion of data coming from different sensors, as the emissions registered at visible and infrared bands, represents a special challenge, because it has been showed that theses signals are weak correlated. Therefore, many traditional techniques of image processing and computer vision are not helpful, requiring adjustments for their correct performance in every modality. In this research an experimental study that compares different cost functions and matching approaches is performed, in order to build a multimodal stereovision system. Furthermore, the common problems in infrared/visible stereo, specially in the outdoor scenes are identified. Our framework summarizes the architecture of a generic stereo algorithm, at different levels: computational, functional, and structural, which can be extended toward high-level fusion (semantic) and high-order (prior).The proposed framework is intended to explore novel multimodal stereo matching approaches, going from sparse to dense representations (both disparity and depth maps). Moreover, context information is added in form of priors and assumptions. Finally, this dissertation shows a promissory way toward the integration of multiple sensors for recovering three-dimensional information. |
|
Agata Lapedriza. (2009). Multitask Learning Techniques for Automatic Face Classification (Jordi Vitria, & David Masip, Eds.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: Automatic face classification is currently a popular research area in Computer Vision. It involves several subproblems, such as subject recognition, gender classification or subject verification.
Current systems of automatic face classification need a large amount of training data to robustly learn a task. However, the collection of labeled data is usually a difficult issue. For this reason, the research on methods that are able to learn from a small sized training set is essential. The dependency on the abundance of training data is not so evident in human learning processes. We are able to learn from a very small number of examples, given that we use, additionally, some prior knowledge to learn a new task. For example, we frequently find patterns and analogies from other domains to reuse them in new situations, or exploit training data from other experiences. In computer science, Multitask Learning is a new Machine Learning approach that studies this idea of knowledge transfer among different tasks, to overcome the effects of the small sample sized problem. This thesis explores, proposes and tests some Multitask Learning methods specially developed for face classification purposes. Moreover, it presents two more contributions dealing with the small sample sized problem, out of the Multitask Learning context. The first one is a method to extract external face features, to be used as an additional information source in automatic face classification problems. The second one is an empirical study on the most suitable face image resolution to perform automatic subject recognition. |
|
Manuel Carbonell. (2020). Neural Information Extraction from Semi-structured Documents A (Alicia Fornes, Mauricio Villegas, & Josep Llados, Eds.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: Sectors as fintech, legaltech or insurance process an inflow of millions of forms, invoices, id documents, claims or similar every day. Together with these, historical archives provide gigantic amounts of digitized documents containing useful information that needs to be stored in machine encoded text with a meaningful structure. This procedure, known as information extraction (IE) comprises the steps of localizing and recognizing text, identifying named entities contained in it and optionally finding relationships among its elements. In this work we explore multi-task neural models at image and graph level to solve all steps in a unified way. While doing so we find benefits and limitations of these end-to-end approaches in comparison with sequential separate methods. More specifically, we first propose a method to produce textual as well as semantic labels with a unified model from handwritten text line images. We do so with the use of a convolutional recurrent neural model trained with connectionist temporal classification to predict the textual as well as semantic information encoded in the images. Secondly, motivated by the success of this approach we investigate the unification of the localization and recognition tasks of handwritten text in full pages with an end-to-end model, observing benefits in doing so. Having two models that tackle information extraction subsequent task pairs in an end-to-end to end manner, we lastly contribute with a method to put them all together in a single neural network to solve the whole information extraction pipeline in a unified way. Doing so we observe some benefits and some limitations in the approach, suggesting that in certain cases it is beneficial to train specialized models that excel at a single challenging task of the information extraction process, as it can be the recognition of named entities or the extraction of relationships between them. For this reason we lastly study the use of the recently arrived graph neural network architectures for the semantic tasks of the information extraction process, which are recognition of named entities and relation extraction, achieving promising results on the relation extraction part.
|
|
Felipe Codevilla. (2019). On Building End-to-End Driving Models Through Imitation Learning (Antonio Lopez, Ed.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: Autonomous vehicles are now considered as an assured asset in the future. Literally, all the relevant car-markers are now in a race to produce fully autonomous vehicles. These car-makers usually make use of modular pipelines for designing autonomous vehicles. This strategy decomposes the problem in a variety of tasks such as object detection and recognition, semantic and instance segmentation, depth estimation, SLAM and place recognition, as well as planning and control. Each module requires a separate set of expert algorithms, which are costly specially in the amount of human labor and necessity of data labelling. An alternative, that recently has driven considerable interest, is the end-to-end driving. In the end-to-end driving paradigm, perception and control are learned simultaneously using a deep network. These sensorimotor models are typically obtained by imitation learning fromhuman demonstrations. The main advantage is that this approach can directly learn from large fleets of human-driven vehicles without requiring a fixed ontology and extensive amounts of labeling. However, scaling end-to-end driving methods to behaviors more complex than simple lane keeping or lead vehicle following remains an open problem. On this thesis, in order to achieve more complex behaviours, we
address some issues when creating end-to-end driving system through imitation learning. The first of themis a necessity of an environment for algorithm evaluation and collection of driving demonstrations. On this matter, we participated on the creation of the CARLA simulator, an open source platformbuilt from ground up for autonomous driving validation and prototyping. Since the end-to-end approach is purely reactive, there is also the necessity to provide an interface with a global planning system. With this, we propose the conditional imitation learning that conditions the actions produced into some high level command. Evaluation is also a concern and is commonly performed by comparing the end-to-end network output to some pre-collected driving dataset. We show that this is surprisingly weakly correlated to the actual driving and propose strategies on how to better acquire data and a better comparison strategy. Finally, we confirmwell-known generalization issues (due to dataset bias and overfitting), new ones (due to dynamic objects and the lack of a causal model), and training instability; problems requiring further research before end-to-end driving through imitation can scale to real-world driving. |
|
Naveen Onkarappa. (2013). Optical Flow in Driver Assistance Systems (Angel Sappa, Ed.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: Motion perception is one of the most important attributes of the human brain. Visual motion perception consists in inferring speed and direction of elements in a scene based on visual inputs. Analogously, computer vision is assisted by motion cues in the scene. Motion detection in computer vision is useful in solving problems such as segmentation, depth from motion, structure from motion, compression, navigation and many others. These problems are common in several applications, for instance, video surveillance, robot navigation and advanced driver assistance systems (ADAS). One of the most widely used techniques for motion detection is the optical flow estimation. The work in this thesis attempts to make optical flow suitable for the requirements and conditions of driving scenarios. In this context, a novel space-variant representation called reverse log-polar representation is proposed that is shown to be better than the traditional log-polar space-variant representation for ADAS. The space-variant representations reduce the amount of data to be processed. Another major contribution in this research is related to the analysis of the influence of specific characteristics from driving scenarios on the optical flow accuracy. Characteristics such as vehicle speed and
road texture are considered in the aforementioned analysis. From this study, it is inferred that the regularization weight has to be adapted according to the required error measure and for different speeds and road textures. It is also shown that polar represented optical flow suits driving scenarios where predominant motion is translation. Due to the requirements of such a study and by the lack of needed datasets a new synthetic dataset is presented; it contains: i) sequences of different speeds and road textures in an urban scenario; ii) sequences with complex motion of an on-board camera; and iii) sequences with additional moving vehicles in the scene. The ground-truth optical flow is generated by the ray-tracing technique. Further, few applications of optical flow in ADAS are shown. Firstly, a robust RANSAC based technique to estimate horizon line is proposed. Then, an egomotion estimation is presented to compare the proposed space-variant representation with the classical one. As a final contribution, a modification in the regularization term is proposed that notably improves the results in the ADAS applications. This adaptation is evaluated using a state of the art optical flow technique. The experiments on a public dataset (KITTI) validate the advantages of using the proposed modification. |
|
Joan Marti, Jose Miguel Benedi, Ana Maria Mendonça, & Joan Serrat. (2007). Pattern Recognition and Image Analysis (Vol. 6669). LNCS.
|
|
Jordi Vitria, Joao Sanchez, Miguel Raposo, & Mario Hernandez. (2011). Pattern Recognition and Image Analysis (J. Vitrià, J. Sanchez, M. Raposo, & M. Hernandez, Eds.) (Vol. 6669). Berlin: Springer-Verlag.
|
|
F. Pla, Petia Radeva, & Jordi Vitria. (2006). Pattern Recognition: Progress, Directions and Applications.
|