toggle visibility Search & Display Options
Select All    Deselect All << 1 2 3 4 5 6 7 >>
List View
 | 
Citations
 | 
Details
  Records Links
Author Alicia Fornes; Gemma Sanchez edit  doi
isbn  openurl
  Title Analysis and Recognition of Music Scores Type Book Chapter
  Year 2014 Publication Handbook of Document Image Processing and Recognition Abbreviated Journal  
  Volume E Issue Pages 749-774  
  Keywords  
  Abstract (up) The analysis and recognition of music scores has attracted the interest of researchers for decades. Optical Music Recognition (OMR) is a classical research field of Document Image Analysis and Recognition (DIAR), whose aim is to extract information from music scores. Music scores contain both graphical and textual information, and for this reason, techniques are closely related to graphics recognition and text recognition. Since music scores use a particular diagrammatic notation that follow the rules of music theory, many approaches make use of context information to guide the recognition and solve ambiguities. This chapter overviews the main Optical Music Recognition (OMR) approaches. Firstly, the different methods are grouped according to the OMR stages, namely, staff removal, music symbol recognition, and syntactical analysis. Secondly, specific approaches for old and handwritten music scores are reviewed. Finally, online approaches and commercial systems are also commented.  
  Address  
  Corporate Author Thesis  
  Publisher Springer London Place of Publication Editor D. Doermann; K. Tombre  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-0-85729-860-7 Medium  
  Area Expedition Conference  
  Notes DAG; ADAS; 600.076; 600.077 Approved no  
  Call Number Admin @ si @ FoS2014 Serial 2484  
Permanent link to this record
 
 
Author Jose Luis Gomez Zurita edit  openurl
  Title Synth-to-real semi-supervised learning for visual tasks Type Book Whole
  Year 2023 Publication Going beyond Classification Problems for the Continual Learning of Deep Neural Networks Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract (up) The curse of data labeling is a costly bottleneck in supervised deep learning, where large amounts of labeled data are needed to train intelligent systems. In onboard perception for autonomous driving, this cost corresponds to the labeling of raw data from sensors such as cameras, LiDARs, RADARs, etc. Therefore, synthetic data with automatically generated ground truth (labels) has aroused as a reliable alternative for training onboard perception models.
However, synthetic data commonly suffers from synth-to-real domain shift, i.e., models trained on the synthetic domain do not show their achievable accuracy when performing in the real world. This shift needs to be addressed by techniques falling in the realm of domain adaptation (DA).
The semi-supervised learning (SSL) paradigm can be followed to address DA. In this case, a model is trained using source data with labels (here synthetic) and leverages minimal knowledge from target data (here the real world) to generate pseudo-labels. These pseudo-labels help the training process to reduce the gap between the source and the target domains. In general, we can assume accessing both, pseudo-labels and a few amounts of human-provided labels for the target-domain data. However, the most interesting and challenging setting consists in assuming that we do not have human-provided labels at all. This setting is known as unsupervised domain adaptation (UDA). This PhD focuses on applying SSL to the UDA setting, for onboard visual tasks related to autonomous driving. We start by addressing the synth-to-real UDA problem on onboard vision-based object detection (pedestrians and cars), a critical task for autonomous driving and driving assistance. In particular, we propose to apply an SSL technique known as co-training, which we adapt to work with deep models that process a multi-modal input. The multi-modality consists of the visual appearance of the images (RGB) and their monocular depth estimation. The synthetic data we use as the source domain contains both, object bounding boxes and depth information. This prior knowledge is the
starting point for the co-training technique, which iteratively labels unlabeled real-world data and uses such pseudolabels (here bounding boxes with an assigned object class) to progressively improve the labeling results. Along this
process, two models collaborate to automatically label the images, in a way that one model compensates for the errors of the other, so avoiding error drift. While this automatic labeling process is done offline, the resulting pseudolabels can be used to train object detection models that must perform in real-time onboard a vehicle. We show that multi-modal co-training improves the labeling results compared to single-modal co-training, remaining competitive compared to human labeling.
Given the success of co-training in the context of object detection, we have also adapted this technique to a more crucial and challenging visual task, namely, onboard semantic segmentation. In fact, providing labels for a single image
can take from 30 to 90 minutes for a human labeler, depending on the content of the image. Thus, developing automatic labeling techniques for this visual task is of great interest to the automotive industry. In particular, the new co-training framework addresses synth-to-real UDA by an initial stage of self-training. Intermediate models arising from this stage are used to start the co-training procedure, for which we have elaborated an accurate collaboration policy between the two models performing the automatic labeling. Moreover, our co-training seamlessly leverages datasets from different synthetic domains. In addition, the co-training procedure is agnostic to the loss function used to train the semantic segmentation models which perform the automatic labeling. We achieve state-of-the-art results on publicly available benchmark datasets, again, remaining competitive compared to human labeling.
Finally, on the ground of our previous experience, we have designed and implemented a new SSL technique for UDA in the context of visual semantic segmentation. In this case, we mimic the labeling methodology followed by human labelers. In particular, rather than labeling full images at a time, categories of semantic classes are defined and only those are labeled in a labeling pass. In fact, different human labelers can become specialists in labeling different categories. Afterward, these per-category-labeled layers are combined to provide fully labeled images. Our technique is inspired by this methodology since we perform synth-to-real UDA per category, using the self-training stage previously developed as part of our co-training framework. The pseudo-labels obtained for each category are finally
fused to obtain fully automatically labeled images. In this context, we have also contributed to the development of a new photo-realistic synthetic dataset based on path-tracing rendering. Our new SSL technique seamlessly leverages publicly available synthetic datasets as well as this new one to obtain state-of-the-art results on synth-to-real UDA for semantic segmentation. We show that the new dataset allows us to reach better labeling accuracy than previously existing datasets, at the same time that it complements well them when combined. Moreover, we also show that the new human-inspired SSL technique outperforms co-training.		  
  Address  
  Corporate Author Thesis Ph.D. thesis  
  Publisher IMPRIMA Place of Publication Editor Antonio Lopez  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes ADAS Approved no  
  Call Number Admin @ si @ Gom2023 Serial 3961  
Permanent link to this record
 
 
Author Monica Piñol edit  isbn
openurl 
  Title Reinforcement Learning of Visual Descriptors for Object Recognition Type Book Whole
  Year 2014 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract (up) The human visual system is able to recognize the object in an image even if the object is partially occluded, from various points of view, in different colors, or with independence of the distance to the object. To do this, the eye obtains an image and extracts features that are sent to the brain, and then, in the brain the object is recognized. In computer vision, the object recognition branch tries to learns from the human visual system behaviour to achieve its goal. Hence, an algorithm is used to identify representative features of the scene (detection), then another algorithm is used to describe these points (descriptor) and finally the extracted information is used for classifying the object in the scene. The selection of this set of algorithms is a very complicated task and thus, a very active research field. In this thesis we are focused on the selection/learning of the best descriptor for a given image. In the state of the art there are several descriptors but we do not know how to choose the best descriptor because depends on scenes that we will use (dataset) and the algorithm chosen to do the classification. We propose a framework based on reinforcement learning and bag of features to choose the best descriptor according to the given image. The system can analyse the behaviour of different learning algorithms and descriptor sets. Furthermore the proposed framework for improving the classification/recognition ratio can be used with minor changes in other computer vision fields, such as video retrieval.  
  Address  
  Corporate Author Thesis Ph.D. thesis  
  Publisher Ediciones Graficas Rey Place of Publication Editor Ricardo Toledo;Angel Sappa  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-84-940902-5-7 Medium  
  Area Expedition Conference  
  Notes ADAS; 600.076 Approved no  
  Call Number Admin @ si @ Piñ2014 Serial 2464  
Permanent link to this record
 
 
Author Angel Sappa; David Geronimo; Fadi Dornaika; Mohammad Rouhani; Antonio Lopez edit   pdf
doi  isbn
openurl 
  Title Moving object detection from mobile platforms using stereo data registration Type Book Chapter
  Year 2012 Publication Computational Intelligence paradigms in advanced pattern classification Abbreviated Journal  
  Volume 386 Issue Pages 25-37  
  Keywords pedestrian detection  
  Abstract (up) This chapter describes a robust approach for detecting moving objects from on-board stereo vision systems. It relies on a feature point quaternion-based registration, which avoids common problems that appear when computationally expensive iterative-based algorithms are used on dynamic environments. The proposed approach consists of three main stages. Initially, feature points are extracted and tracked through consecutive 2D frames. Then, a RANSAC based approach is used for registering two point sets, with known correspondences in the 3D space. The computed 3D rigid displacement is used to map two consecutive 3D point clouds into the same coordinate system by means of the quaternion method. Finally, moving objects correspond to those areas with large 3D registration errors. Experimental results show the viability of the proposed approach to detect moving objects like vehicles or pedestrians in different urban scenarios.  
  Address  
  Corporate Author Thesis  
  Publisher Springer Berlin Heidelberg Place of Publication Editor Marek R. Ogiela; Lakhmi C. Jain  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 1860-949X ISBN 978-3-642-24048-5 Medium  
  Area Expedition Conference  
  Notes ADAS Approved no  
  Call Number Admin @ si @ SGD2012 Serial 2061  
Permanent link to this record
 
 
Author David Geronimo; Angel Sappa; Antonio Lopez edit   pdf
url  openurl
  Title Stereo-based Candidate Generation for Pedestrian Protection Systems Type Book Chapter
  Year 2010 Publication Binocular Vision: Development, Depth Perception and Disorders Abbreviated Journal  
  Volume Issue 9 Pages 189–208  
  Keywords Pedestrian Detection  
  Abstract (up) This chapter describes a stereo-based algorithm that provides candidate image windows to a latter 2D classification stage in an on-board pedestrian detection system. The proposed algorithm, which consists of three stages, is based on the use of both stereo imaging and scene prior knowledge (i.e., pedestrians are on the ground) to reduce the candidate searching space. First, a successful road surface fitting algorithm provides estimates on the relative ground-camera pose. This stage directs the search toward the road area thus avoiding irrelevant regions like the sky. Then, three different schemes are used to scan the estimated road surface with pedestrian-sized windows: (a) uniformly distributed through the road surface (3D); (b) uniformly distributed through the image (2D); (c) not uniformly distributed but according to a quadratic function (combined 2D-3D). Finally, the set of candidate windows is reduced by analyzing their 3D content. Experimental results of the proposed algorithm, together with statistics of searching space reduction are provided.  
  Address  
  Corporate Author Thesis  
  Publisher NOVA Publishers Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes ADAS Approved no  
  Call Number ADAS @ adas @ GSL2010 Serial 1301  
Permanent link to this record
 
 
Author Lluis Pere de las Heras; David Fernandez; Alicia Fornes; Ernest Valveny; Gemma Sanchez; Josep Llados edit  doi
isbn  openurl
  Title Runlength Histogram Image Signature for Perceptual Retrieval of Architectural Floor Plans Type Book Chapter
  Year 2014 Publication Graphics Recognition. Current Trends and Challenges Abbreviated Journal  
  Volume 8746 Issue Pages 135-146  
  Keywords Graphics recognition; Graphics retrieval; Image classification  
  Abstract (up) This paper proposes a runlength histogram signature as a perceptual descriptor of architectural plans in a retrieval scenario. The style of an architectural drawing is characterized by the perception of lines, shapes and texture. Such visual stimuli are the basis for defining semantic concepts as space properties, symmetry, density, etc. We propose runlength histograms extracted in vertical, horizontal and diagonal directions as a characterization of line and space properties in floorplans, so it can be roughly associated to a description of walls and room structure. A retrieval application illustrates the performance of the proposed approach, where given a plan as a query, similar ones are obtained from a database. A ground truth based on human observation has been constructed to validate the hypothesis. Additional retrieval results on sketched building’s facades are reported qualitatively in this paper. Its good description and its adaptability to two different sketch drawings despite its simplicity shows the interest of the proposed approach and opens a challenging research line in graphics recognition.  
  Address  
  Corporate Author Thesis  
  Publisher Springer Berlin Heidelberg Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN 0302-9743 ISBN 978-3-662-44853-3 Medium  
  Area Expedition Conference  
  Notes DAG; ADAS; 600.045; 600.056; 600.061; 600.076; 600.077 Approved no  
  Call Number Admin @ si @ HFF2014 Serial 2536  
Permanent link to this record
 
 
Author Ferran Diego edit  openurl
  Title Probabilistic Alignment of Video Sequences Recorded by Moving Cameras Type Book Whole
  Year 2011 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract (up) Video alignment consists of integrating multiple video sequences recorded independently into a single video sequence. This means to register both in time (synchronize
frames) and space (image registration) so that the two videos sequences can be fused
or compared pixel–wise. In spite of being relatively unknown, many applications today may benefit from the availability of robust and efficient video alignment methods.
For instance, video surveillance requires to integrate video sequences that are recorded
of the same scene at different times in order to detect changes. The problem of aligning videos has been addressed before, but in the relatively simple cases of fixed or rigidly attached cameras and simultaneous acquisition. In addition, most works rely
on restrictive assumptions which reduce its difficulty such as linear time correspondence or the knowledge of the complete trajectories of corresponding scene points on the images; to some extent, these assumptions limit the practical applicability of the solutions developed until now. In this thesis, we focus on the challenging problem of aligning sequences recorded at different times from independent moving cameras following similar but not coincident trajectories. More precisely, this thesis covers four studies that advance the state-of-the-art in video alignment. First, we focus on analyzing and developing a probabilistic framework for video alignment, that is, a principled way to integrate multiple observations and prior information. In this way, two different approaches are presented to exploit the combination of several purely visual features (image–intensities, visual words and dense motion field descriptor), and
global positioning system (GPS) information. Second, we focus on reformulating the
problem into a single alignment framework since previous works on video alignment
adopt a divide–and–conquer strategy, i.e., first solve the synchronization, and then
register corresponding frames. This also generalizes the ’classic’ case of fixed geometric transform and linear time mapping. Third, we focus on exploiting directly the
time domain of the video sequences in order to avoid exhaustive cross–frame search.
This provides relevant information used for learning the temporal mapping between
pairs of video sequences. Finally, we focus on adapting these methods to the on–line
setting for road detection and vehicle geolocation. The qualitative and quantitative
results presented in this thesis on a variety of real–world pairs of video sequences show that the proposed method is: robust to varying imaging conditions, different image
content (e.g., incoming and outgoing vehicles), variations on camera velocity, and
different scenarios (indoor and outdoor) going beyond the state–of–the–art. Moreover, the on–line video alignment has been successfully applied for road detection and
vehicle geolocation achieving promising results.		  
  Address  
  Corporate Author Thesis Ph.D. thesis  
  Publisher Ediciones Graficas Rey Place of Publication Editor Joan Serrat  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes ADAS Approved no  
  Call Number Admin @ si @ Die2011 Serial 1787  
Permanent link to this record
 
 
Author German Ros; Laura Sellart; Gabriel Villalonga; Elias Maidanik; Francisco Molero; Marc Garcia; Adriana Cedeño; Francisco Perez; Didier Ramirez; Eduardo Escobar; Jose Luis Gomez; David Vazquez; Antonio Lopez edit  url
openurl 
  Title Semantic Segmentation of Urban Scenes via Domain Adaptation of SYNTHIA Type Book Chapter
  Year 2017 Publication Domain Adaptation in Computer Vision Applications Abbreviated Journal  
  Volume 12 Issue Pages 227-241  
  Keywords SYNTHIA; Virtual worlds; Autonomous Driving  
  Abstract (up) Vision-based semantic segmentation in urban scenarios is a key functionality for autonomous driving. Recent revolutionary results of deep convolutional neural networks (DCNNs) foreshadow the advent of reliable classifiers to perform such visual tasks. However, DCNNs require learning of many parameters from raw images; thus, having a sufficient amount of diverse images with class annotations is needed. These annotations are obtained via cumbersome, human labour which is particularly challenging for semantic segmentation since pixel-level annotations are required. In this chapter, we propose to use a combination of a virtual world to automatically generate realistic synthetic images with pixel-level annotations, and domain adaptation to transfer the models learnt to correctly operate in real scenarios. We address the question of how useful synthetic data can be for semantic segmentation – in particular, when using a DCNN paradigm. In order to answer this question we have generated a synthetic collection of diverse urban images, named SYNTHIA, with automatically generated class annotations and object identifiers. We use SYNTHIA in combination with publicly available real-world urban images with manually provided annotations. Then, we conduct experiments with DCNNs that show that combining SYNTHIA with simple domain adaptation techniques in the training stage significantly improves performance on semantic segmentation.  
  Address  
  Corporate Author Thesis  
  Publisher Springer Place of Publication Editor Gabriela Csurka  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes ADAS; 600.085; 600.082; 600.076; 600.118 Approved no  
  Call Number ADAS @ adas @ RSV2017 Serial 2882  
Permanent link to this record
Select All    Deselect All << 1 2 3 4 5 6 7 >>
List View
 | 
Citations
 | 
Details
toggle visibility
Save Citations:
Export Records: