Home << 1 2 3 4 5 6 7 8 9 >>
List View
 | 
Citations
 | 
Details
   web
Records
Author David Aldavert
Title Efficient and Scalable Handwritten Word Spotting on Historical Documents using Bag of Visual Words Type Book Whole
Year 2021 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Word spotting can be defined as the pattern recognition tasked aimed at locating and retrieving a specific keyword within a document image collection without explicitly transcribing the whole corpus. Its use is particularly interesting when applied in scenarios where Optical Character Recognition performs poorly or can not be used at all. This thesis focuses on such a scenario, word spotting on historical handwritten documents that have been written by a single author or by multiple authors with a similar calligraphy.
This problem requires a visual signature that is robust to image artifacts, flexible to accommodate script variations and efficient to retrieve information in a rapid manner. For this, we have developed a set of word spotting methods that on their foundation use the well known Bag-of-Visual-Words (BoVW) representation. This representation has gained popularity among the document image analysis community to characterize handwritten words
in an unsupervised manner. However, most approaches on this field rely on a basic BoVW configuration and disregard complex encoding and spatial representations. We determine which BoVW configurations provide the best performance boost to a spotting system.
Then, we extend the segmentation-based word spotting, where word candidates are given a priori, to segmentation-free spotting. The proposed approach seeds the document images with overlapping word location candidates and characterizes them with a BoVW signature. Retrieval is achieved comparing the query and candidate signatures and returning the locations that provide a higher consensus. This is a simple but powerful approach that requires a more compact signature than in a segmentation-based scenario. We first
project the BoVW signature into a reduced semantic topics space and then compress it further using Product Quantizers. The resulting signature only requires a few dozen bytes, allowing us to index thousands of pages on a common desktop computer. The final system still yields a performance comparable to the state-of-the-art despite all the information loss during the compression phases.
Afterwards, we also study how to combine different modalities of information in order to create a query-by-X spotting system where, words are indexed using an information modality and queries are retrieved using another. We consider three different information modalities: visual, textual and audio. Our proposal is to create a latent feature space where features which are semantically related are projected onto the same topics. Creating thus a new feature space where information from different modalities can be compared. Later, we consider the codebook generation and descriptor encoding problem. The codebooks used to encode the BoVW signatures are usually created using an unsupervised clustering algorithm and, they require to test multiple parameters to determine which configuration is best for a certain document collection. We propose a semantic clustering algorithm which allows to estimate the best parameter from data. Since gather annotated data is costly, we use synthetically generated word images. The resulting codebook is database agnostic, i. e. a codebook that yields a good performance on document collections that use the same script. We also propose the use of an additional codebook to approximate descriptors and reduce the descriptor encoding
complexity to sub-linear.
Finally, we focus on the problem of signatures dimensionality. We propose a new symbol probability signature where each bin represents the probability that a certain symbol is present a certain location of the word image. This signature is extremely compact and combined with compression techniques can represent word images with just a few bytes per signature.
Address April 2021
Corporate Author Thesis Ph.D. thesis
Publisher Ediciones Graficas Rey Place of Publication Editor Marçal Rusiñol;Josep Llados
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-122714-5-4 Medium
Area Expedition Conference (up)
Notes DAG; 600.121 Approved no
Call Number Admin @ si @ Ald2021 Serial 3601
Permanent link to this record
 
 
Author Md. Mostafa Kamal Sarker; Hatem A. Rashwan; Farhan Akram; Vivek Kumar Singh; Syeda Furruka Banu; Forhad U H Chowdhury; Kabir Ahmed Choudhury; Sylvie Chambon; Petia Radeva; Domenec Puig; Mohamed Abdel-Nasser
Title SLSNet: Skin lesion segmentation using a lightweight generative adversarial network Type Journal Article
Year 2021 Publication Expert Systems With Applications Abbreviated Journal ESWA
Volume 183 Issue Pages 115433
Keywords
Abstract The determination of precise skin lesion boundaries in dermoscopic images using automated methods faces many challenges, most importantly, the presence of hair, inconspicuous lesion edges and low contrast in dermoscopic images, and variability in the color, texture and shapes of skin lesions. Existing deep learning-based skin lesion segmentation algorithms are expensive in terms of computational time and memory. Consequently, running such segmentation algorithms requires a powerful GPU and high bandwidth memory, which are not available in dermoscopy devices. Thus, this article aims to achieve precise skin lesion segmentation with minimum resources: a lightweight, efficient generative adversarial network (GAN) model called SLSNet, which combines 1-D kernel factorized networks, position and channel attention, and multiscale aggregation mechanisms with a GAN model. The 1-D kernel factorized network reduces the computational cost of 2D filtering. The position and channel attention modules enhance the discriminative ability between the lesion and non-lesion feature representations in spatial and channel dimensions, respectively. A multiscale block is also used to aggregate the coarse-to-fine features of input skin images and reduce the effect of the artifacts. SLSNet is evaluated on two publicly available datasets: ISBI 2017 and the ISIC 2018. Although SLSNet has only 2.35 million parameters, the experimental results demonstrate that it achieves segmentation results on a par with the state-of-the-art skin lesion segmentation methods with an accuracy of 97.61%, and Dice and Jaccard similarity coefficients of 90.63% and 81.98%, respectively. SLSNet can run at more than 110 frames per second (FPS) in a single GTX1080Ti GPU, which is faster than well-known deep learning-based image segmentation models, such as FCN. Therefore, SLSNet can be used for practical dermoscopic applications.
Address
Corporate Author Thesis
Publisher 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 (up)
Notes MILAB; no proj Approved no
Call Number Admin @ si @ SRA2021 Serial 3633
Permanent link to this record
 
 
Author Giuseppe Pezzano; Oliver Diaz; Vicent Ribas Ripoll; Petia Radeva
Title CoLe-CNN+: Context learning – Convolutional neural network for COVID-19-Ground-Glass-Opacities detection and segmentation Type Journal Article
Year 2021 Publication Computers in Biology and Medicine Abbreviated Journal CBM
Volume 136 Issue Pages 104689
Keywords
Abstract The most common tool for population-wide COVID-19 identification is the Reverse Transcription-Polymerase Chain Reaction test that detects the presence of the virus in the throat (or sputum) in swab samples. This test has a sensitivity between 59% and 71%. However, this test does not provide precise information regarding the extension of the pulmonary infection. Moreover, it has been proven that through the reading of a computed tomography (CT) scan, a clinician can provide a more complete perspective of the severity of the disease. Therefore, we propose a comprehensive system for fully-automated COVID-19 detection and lesion segmentation from CT scans, powered by deep learning strategies to support decision-making process for the diagnosis of COVID-19.
Address
Corporate Author Thesis
Publisher 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 (up)
Notes MILAB; no menciona Approved no
Call Number Admin @ si @ PDR2021 Serial 3635
Permanent link to this record
 
 
Author Jorge Charco; Angel Sappa; Boris X. Vintimilla; Henry Velesaca
Title Camera pose estimation in multi-view environments: From virtual scenarios to the real world Type Journal Article
Year 2021 Publication Image and Vision Computing Abbreviated Journal IVC
Volume 110 Issue Pages 104182
Keywords
Abstract This paper presents a domain adaptation strategy to efficiently train network architectures for estimating the relative camera pose in multi-view scenarios. The network architectures are fed by a pair of simultaneously acquired images, hence in order to improve the accuracy of the solutions, and due to the lack of large datasets with pairs of overlapped images, a domain adaptation strategy is proposed. The domain adaptation strategy consists on transferring the knowledge learned from synthetic images to real-world scenarios. For this, the networks are firstly trained using pairs of synthetic images, which are captured at the same time by a pair of cameras in a virtual environment; and then, the learned weights of the networks are transferred to the real-world case, where the networks are retrained with a few real images. Different virtual 3D scenarios are generated to evaluate the relationship between the accuracy on the result and the similarity between virtual and real scenarios—similarity on both geometry of the objects contained in the scene as well as relative pose between camera and objects in the scene. Experimental results and comparisons are provided showing that the accuracy of all the evaluated networks for estimating the camera pose improves when the proposed domain adaptation strategy is used, highlighting the importance on the similarity between virtual-real scenarios.
Address
Corporate Author Thesis
Publisher 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 (up)
Notes MSIAU; 600.130; 600.122 Approved no
Call Number Admin @ si @ CSV2021 Serial 3577
Permanent link to this record
 
 
Author Ricardo Dario Perez Principi; Cristina Palmero; Julio C. S. Jacques Junior; Sergio Escalera
Title On the Effect of Observed Subject Biases in Apparent Personality Analysis from Audio-visual Signals Type Journal Article
Year 2021 Publication IEEE Transactions on Affective Computing Abbreviated Journal TAC
Volume 12 Issue 3 Pages 607-621
Keywords
Abstract Personality perception is implicitly biased due to many subjective factors, such as cultural, social, contextual, gender and appearance. Approaches developed for automatic personality perception are not expected to predict the real personality of the target, but the personality external observers attributed to it. Hence, they have to deal with human bias, inherently transferred to the training data. However, bias analysis in personality computing is an almost unexplored area. In this work, we study different possible sources of bias affecting personality perception, including emotions from facial expressions, attractiveness, age, gender, and ethnicity, as well as their influence on prediction ability for apparent personality estimation. To this end, we propose a multi-modal deep neural network that combines raw audio and visual information alongside predictions of attribute-specific models to regress apparent personality. We also analyse spatio-temporal aggregation schemes and the effect of different time intervals on first impressions. We base our study on the ChaLearn First Impressions dataset, consisting of one-person conversational videos. Our model shows state-of-the-art results regressing apparent personality based on the Big-Five model. Furthermore, given the interpretability nature of our network design, we provide an incremental analysis on the impact of each possible source of bias on final network predictions.
Address 1 July-Sept. 2021
Corporate Author Thesis
Publisher 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 (up)
Notes HuPBA; no proj Approved no
Call Number Admin @ si @ PPJ2019 Serial 3312
Permanent link to this record
 
 
Author Lei Kang; Pau Riba; Mauricio Villegas; Alicia Fornes; Marçal Rusiñol
Title Candidate Fusion: Integrating Language Modelling into a Sequence-to-Sequence Handwritten Word Recognition Architecture Type Journal Article
Year 2021 Publication Pattern Recognition Abbreviated Journal PR
Volume 112 Issue Pages 107790
Keywords
Abstract Sequence-to-sequence models have recently become very popular for tackling
handwritten word recognition problems. However, how to effectively integrate an external language model into such recognizer is still a challenging
problem. The main challenge faced when training a language model is to
deal with the language model corpus which is usually different to the one
used for training the handwritten word recognition system. Thus, the bias
between both word corpora leads to incorrectness on the transcriptions, providing similar or even worse performances on the recognition task. In this
work, we introduce Candidate Fusion, a novel way to integrate an external
language model to a sequence-to-sequence architecture. Moreover, it provides suggestions from an external language knowledge, as a new input to
the sequence-to-sequence recognizer. Hence, Candidate Fusion provides two
improvements. On the one hand, the sequence-to-sequence recognizer has
the flexibility not only to combine the information from itself and the language model, but also to choose the importance of the information provided
by the language model. On the other hand, the external language model
has the ability to adapt itself to the training corpus and even learn the
most commonly errors produced from the recognizer. Finally, by conducting
comprehensive experiments, the Candidate Fusion proves to outperform the
state-of-the-art language models for handwritten word recognition tasks.
Address
Corporate Author Thesis
Publisher 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 (up)
Notes DAG; 600.140; 601.302; 601.312; 600.121 Approved no
Call Number Admin @ si @ KRV2021 Serial 3343
Permanent link to this record
 
 
Author Arka Ujjal Dey; Suman Ghosh; Ernest Valveny; Gaurav Harit
Title Beyond Visual Semantics: Exploring the Role of Scene Text in Image Understanding Type Journal Article
Year 2021 Publication Pattern Recognition Letters Abbreviated Journal PRL
Volume 149 Issue Pages 164-171
Keywords
Abstract Images with visual and scene text content are ubiquitous in everyday life. However, current image interpretation systems are mostly limited to using only the visual features, neglecting to leverage the scene text content. In this paper, we propose to jointly use scene text and visual channels for robust semantic interpretation of images. We do not only extract and encode visual and scene text cues, but also model their interplay to generate a contextual joint embedding with richer semantics. The contextual embedding thus generated is applied to retrieval and classification tasks on multimedia images, with scene text content, to demonstrate its effectiveness. In the retrieval framework, we augment our learned text-visual semantic representation with scene text cues, to mitigate vocabulary misses that may have occurred during the semantic embedding. To deal with irrelevant or erroneous recognition of scene text, we also apply query-based attention to our text channel. We show how the multi-channel approach, involving visual semantics and scene text, improves upon state of the art.
Address
Corporate Author Thesis
Publisher 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 (up)
Notes DAG; 600.121 Approved no
Call Number Admin @ si @ DGV2021 Serial 3364
Permanent link to this record
 
 
Author Manisha Das; Deep Gupta; Petia Radeva; Ashwini M. Bakde
Title Optimized CT-MR neurological image fusion framework using biologically inspired spiking neural model in hybrid ℓ1 - ℓ0 layer decomposition domain Type Journal Article
Year 2021 Publication Biomedical Signal Processing and Control Abbreviated Journal BSPC
Volume 68 Issue Pages 102535
Keywords
Abstract Medical image fusion plays an important role in the clinical diagnosis of several critical neurological diseases by merging complementary information available in multimodal images. In this paper, a novel CT-MR neurological image fusion framework is proposed using an optimized biologically inspired feedforward neural model in two-scale hybrid ℓ1 − ℓ0 decomposition domain using gray wolf optimization to preserve the structural as well as texture information present in source CT and MR images. Initially, the source images are subjected to two-scale ℓ1 − ℓ0 decomposition with optimized parameters, giving a scale-1 detail layer, a scale-2 detail layer and a scale-2 base layer. Two detail layers at scale-1 and 2 are fused using an optimized biologically inspired neural model and weighted average scheme based on local energy and modified spatial frequency to maximize the preservation of edges and local textures, respectively, while the scale-2 base layer gets fused using choose max rule to preserve the background information. To optimize the hyper-parameters of hybrid ℓ1 − ℓ0 decomposition and biologically inspired neural model, a fitness function is evaluated based on spatial frequency and edge index of the resultant fused image obtained by adding all the fused components. The fusion performance is analyzed by conducting extensive experiments on different CT-MR neurological images. Experimental results indicate that the proposed method provides better-fused images and outperforms the other state-of-the-art fusion methods in both visual and quantitative assessments.
Address
Corporate Author Thesis
Publisher 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 (up)
Notes MILAB; no proj Approved no
Call Number Admin @ si @ DGR2021b Serial 3636
Permanent link to this record
 
 
Author Andreea Glavan; Alina Matei; Petia Radeva; Estefania Talavera
Title Does our social life influence our nutritional behaviour? Understanding nutritional habits from egocentric photo-streams Type Journal Article
Year 2021 Publication Expert Systems with Applications Abbreviated Journal ESWA
Volume 171 Issue Pages 114506
Keywords
Abstract Nutrition and social interactions are both key aspects of the daily lives of humans. In this work, we propose a system to evaluate the influence of social interaction in the nutritional habits of a person from a first-person perspective. In order to detect the routine of an individual, we construct a nutritional behaviour pattern discovery model, which outputs routines over a number of days. Our method evaluates similarity of routines with respect to visited food-related scenes over the collected days, making use of Dynamic Time Warping, as well as considering social engagement and its correlation with food-related activities. The nutritional and social descriptors of the collected days are evaluated and encoded using an LSTM Autoencoder. Later, the obtained latent space is clustered to find similar days unaffected by outliers using the Isolation Forest method. Moreover, we introduce a new score metric to evaluate the performance of the proposed algorithm. We validate our method on 104 days and more than 100 k egocentric images gathered by 7 users. Several different visualizations are evaluated for the understanding of the findings. Our results demonstrate good performance and applicability of our proposed model for social-related nutritional behaviour understanding. At the end, relevant applications of the model are discussed by analysing the discovered routine of particular individuals.
Address
Corporate Author Thesis
Publisher 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 (up)
Notes MILAB; no proj Approved no
Call Number Admin @ si @ GMR2021 Serial 3634
Permanent link to this record
 
 
Author Yaxing Wang; Abel Gonzalez-Garcia; Luis Herranz; Joost Van de Weijer
Title Controlling biases and diversity in diverse image-to-image translation Type Journal Article
Year 2021 Publication Computer Vision and Image Understanding Abbreviated Journal CVIU
Volume 202 Issue Pages 103082
Keywords
Abstract JCR 2019 Q2, IF=3.121
The task of unpaired image-to-image translation is highly challenging due to the lack of explicit cross-domain pairs of instances. We consider here diverse image translation (DIT), an even more challenging setting in which an image can have multiple plausible translations. This is normally achieved by explicitly disentangling content and style in the latent representation and sampling different styles codes while maintaining the image content. Despite the success of current DIT models, they are prone to suffer from bias. In this paper, we study the problem of bias in image-to-image translation. Biased datasets may add undesired changes (e.g. change gender or race in face images) to the output translations as a consequence of the particular underlying visual distribution in the target domain. In order to alleviate the effects of this problem we propose the use of semantic constraints that enforce the preservation of desired image properties. Our proposed model is a step towards unbiased diverse image-to-image translation (UDIT), and results in less unwanted changes in the translated images while still performing the wanted transformation. Experiments on several heavily biased datasets show the effectiveness of the proposed techniques in different domains such as faces, objects, and scenes.
Address
Corporate Author Thesis
Publisher 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 (up)
Notes LAMP; 600.141; 600.109; 600.147 Approved no
Call Number Admin @ si @ WGH2021 Serial 3464
Permanent link to this record
 
 
Author Akhil Gurram; Ahmet Faruk Tuna; Fengyi Shen; Onay Urfalioglu; Antonio Lopez
Title Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision Type Journal Article
Year 2021 Publication IEEE Transactions on Intelligent Transportation Systems Abbreviated Journal TITS
Volume 23 Issue 8 Pages 12738-12751
Keywords
Abstract Depth information is essential for on-board perception in autonomous driving and driver assistance. Monocular depth estimation (MDE) is very appealing since it allows for appearance and depth being on direct pixelwise correspondence without further calibration. Best MDE models are based on Convolutional Neural Networks (CNNs) trained in a supervised manner, i.e., assuming pixelwise ground truth (GT). Usually, this GT is acquired at training time through a calibrated multi-modal suite of sensors. However, also using only a monocular system at training time is cheaper and more scalable. This is possible by relying on structure-from-motion (SfM) principles to generate self-supervision. Nevertheless, problems of camouflaged objects, visibility changes, static-camera intervals, textureless areas, and scale ambiguity, diminish the usefulness of such self-supervision. In this paper, we perform monocular depth estimation by virtual-world supervision (MonoDEVS) and real-world SfM self-supervision. We compensate the SfM self-supervision limitations by leveraging virtual-world images with accurate semantic and depth supervision and addressing the virtual-to-real domain gap. Our MonoDEVSNet outperforms previous MDE CNNs trained on monocular and even stereo sequences.
Address
Corporate Author Thesis
Publisher 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 (up)
Notes ADAS; 600.118 Approved no
Call Number Admin @ si @ GTS2021 Serial 3598
Permanent link to this record
 
 
Author Carola Figueroa Flores
Title Visual Saliency for Object Recognition, and Object Recognition for Visual Saliency Type Book Whole
Year 2021 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords computer vision; visual saliency; fine-grained object recognition; convolutional neural networks; images classification
Abstract For humans, the recognition of objects is an almost instantaneous, precise and
extremely adaptable process. Furthermore, we have the innate capability to learn
new object classes from only few examples. The human brain lowers the complexity
of the incoming data by filtering out part of the information and only processing
those things that capture our attention. This, mixed with our biological predisposition to respond to certain shapes or colors, allows us to recognize in a simple
glance the most important or salient regions from an image. This mechanism can
be observed by analyzing on which parts of images subjects place attention; where
they fix their eyes when an image is shown to them. The most accurate way to
record this behavior is to track eye movements while displaying images.
Computational saliency estimation aims to identify to what extent regions or
objects stand out with respect to their surroundings to human observers. Saliency
maps can be used in a wide range of applications including object detection, image
and video compression, and visual tracking. The majority of research in the field has
focused on automatically estimating saliency maps given an input image. Instead, in
this thesis, we set out to incorporate saliency maps in an object recognition pipeline:
we want to investigate whether saliency maps can improve object recognition
results.
In this thesis, we identify several problems related to visual saliency estimation.
First, to what extent the estimation of saliency can be exploited to improve the
training of an object recognition model when scarce training data is available. To
solve this problem, we design an image classification network that incorporates
saliency information as input. This network processes the saliency map through a
dedicated network branch and uses the resulting characteristics to modulate the
standard bottom-up visual characteristics of the original image input. We will refer to this technique as saliency-modulated image classification (SMIC). In extensive
experiments on standard benchmark datasets for fine-grained object recognition,
we show that our proposed architecture can significantly improve performance,
especially on dataset with scarce training data.
Next, we address the main drawback of the above pipeline: SMIC requires an
explicit saliency algorithm that must be trained on a saliency dataset. To solve this,
we implement a hallucination mechanism that allows us to incorporate the saliency
estimation branch in an end-to-end trained neural network architecture that only
needs the RGB image as an input. A side-effect of this architecture is the estimation
of saliency maps. In experiments, we show that this architecture can obtain similar
results on object recognition as SMIC but without the requirement of ground truth
saliency maps to train the system.
Finally, we evaluated the accuracy of the saliency maps that occur as a sideeffect of object recognition. For this purpose, we use a set of benchmark datasets
for saliency evaluation based on eye-tracking experiments. Surprisingly, the estimated saliency maps are very similar to the maps that are computed from human
eye-tracking experiments. Our results show that these saliency maps can obtain
competitive results on benchmark saliency maps. On one synthetic saliency dataset
this method even obtains the state-of-the-art without the need of ever having seen
an actual saliency image for training.
Address March 2021
Corporate Author Thesis Ph.D. thesis
Publisher Ediciones Graficas Rey Place of Publication Editor Joost Van de Weijer;Bogdan Raducanu
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-122714-4-7 Medium
Area Expedition Conference (up)
Notes LAMP; 600.120 Approved no
Call Number Admin @ si @ Fig2021 Serial 3600
Permanent link to this record
 
 
Author Gabriel Villalonga
Title Leveraging Synthetic Data to Create Autonomous Driving Perception Systems Type Book Whole
Year 2021 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Manually annotating images to develop vision models has been a major bottleneck
since computer vision and machine learning started to walk together. This has
been more evident since computer vision falls on the shoulders of data-hungry
deep learning techniques. When addressing on-board perception for autonomous
driving, the curse of data annotation is exacerbated due to the use of additional
sensors such as LiDAR. Therefore, any approach aiming at reducing such a timeconsuming and costly work is of high interest for addressing autonomous driving
and, in fact, for any application requiring some sort of artificial perception. In the
last decade, it has been shown that leveraging from synthetic data is a paradigm
worth to pursue in order to minimizing manual data annotation. The reason is
that the automatic process of generating synthetic data can also produce different
types of associated annotations (e.g. object bounding boxes for synthetic images
and LiDAR pointclouds, pixel/point-wise semantic information, etc.). Directly
using synthetic data for training deep perception models may not be the definitive
solution in all circumstances since it can appear a synth-to-real domain shift. In
this context, this work focuses on leveraging synthetic data to alleviate manual
annotation for three perception tasks related to driving assistance and autonomous
driving. In all cases, we assume the use of deep convolutional neural networks
(CNNs) to develop our perception models.
The first task addresses traffic sign recognition (TSR), a kind of multi-class
classification problem. We assume that the number of sign classes to be recognized
must be suddenly increased without having annotated samples to perform the
corresponding TSR CNN re-training. We show that leveraging synthetic samples of
such new classes and transforming them by a generative adversarial network (GAN)
trained on the known classes (i.e. without using samples from the new classes), it is
possible to re-train the TSR CNN to properly classify all the signs for a ∼ 1/4 ratio of
new/known sign classes. The second task addresses on-board 2D object detection,
focusing on vehicles and pedestrians. In this case, we assume that we receive a set
of images without the annotations required to train an object detector, i.e. without
object bounding boxes. Therefore, our goal is to self-annotate these images so
that they can later be used to train the desired object detector. In order to reach
this goal, we leverage from synthetic data and propose a semi-supervised learning
approach based on the co-training idea. In fact, we use a GAN to reduce the synthto-real domain shift before applying co-training. Our quantitative results show
that co-training and GAN-based image-to-image translation complement each
other up to allow the training of object detectors without manual annotation, and still almost reaching the upper-bound performances of the detectors trained from
human annotations. While in previous tasks we focus on vision-based perception,
the third task we address focuses on LiDAR pointclouds. Our initial goal was to
develop a 3D object detector trained on synthetic LiDAR-style pointclouds. While
for images we may expect synth/real-to-real domain shift due to differences in
their appearance (e.g. when source and target images come from different camera
sensors), we did not expect so for LiDAR pointclouds since these active sensors
factor out appearance and provide sampled shapes. However, in practice, we have
seen that it can be domain shift even among real-world LiDAR pointclouds. Factors
such as the sampling parameters of the LiDARs, the sensor suite configuration onboard the ego-vehicle, and the human annotation of 3D bounding boxes, do induce
a domain shift. We show it through comprehensive experiments with different
publicly available datasets and 3D detectors. This redirected our goal towards the
design of a GAN for pointcloud-to-pointcloud translation, a relatively unexplored
topic.
Finally, it is worth to mention that all the synthetic datasets used for these three
tasks, have been designed and generated in the context of this PhD work and will
be publicly released. Overall, we think this PhD presents several steps forward to
encourage leveraging synthetic data for developing deep perception models in the
field of driving assistance and autonomous driving.
Address February 2021
Corporate Author Thesis Ph.D. thesis
Publisher Ediciones Graficas Rey Place of Publication Editor Antonio Lopez;German Ros
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-122714-2-3 Medium
Area Expedition Conference (up)
Notes ADAS; 600.118 Approved no
Call Number Admin @ si @ Vil2021 Serial 3599
Permanent link to this record
 
 
Author Andres Mafla; Ruben Tito; Sounak Dey; Lluis Gomez; Marçal Rusiñol; Ernest Valveny; Dimosthenis Karatzas
Title Real-time Lexicon-free Scene Text Retrieval Type Journal Article
Year 2021 Publication Pattern Recognition Abbreviated Journal PR
Volume 110 Issue Pages 107656
Keywords
Abstract In this work, we address the task of scene text retrieval: given a text query, the system returns all images containing the queried text. The proposed model uses a single shot CNN architecture that predicts bounding boxes and builds a compact representation of spotted words. In this way, this problem can be modeled as a nearest neighbor search of the textual representation of a query over the outputs of the CNN collected from the totality of an image database. Our experiments demonstrate that the proposed model outperforms previous state-of-the-art, while offering a significant increase in processing speed and unmatched expressiveness with samples never seen at training time. Several experiments to assess the generalization capability of the model are conducted in a multilingual dataset, as well as an application of real-time text spotting in videos.
Address
Corporate Author Thesis
Publisher 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 (up)
Notes DAG; 600.121; 600.129; 601.338 Approved no
Call Number Admin @ si @ MTD2021 Serial 3493
Permanent link to this record
 
 
Author Gemma Rotger
Title Lifelike Humans: Detailed Reconstruction of Expressive Human Faces Type Book Whole
Year 2021 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Developing human-like digital characters is a challenging task since humans are used to recognizing our fellows, and find the computed generated characters inadequately humanized. To fulfill the standards of the videogame and digital film productions it is necessary to model and animate these characters the most closely to human beings. However, it is an arduous and expensive task, since many artists and specialists are required to work on a single character. Therefore, to fulfill these requirements we found an interesting option to study the automatic creation of detailed characters through inexpensive setups. In this work, we develop novel techniques to bring detailed characters by combining different aspects that stand out when developing realistic characters, skin detail, facial hairs, expressions, and microexpressions. We examine each of the mentioned areas with the aim of automatically recover each of the parts without user interaction nor training data. We study the problems for their robustness but also for the simplicity of the setup, preferring single-image with uncontrolled illumination and methods that can be easily computed with the commodity of a standard laptop. A detailed face with wrinkles and skin details is vital to develop a realistic character. In this work, we introduce our method to automatically describe facial wrinkles on the image and transfer to the recovered base face. Then we advance to facial hair recovery by resolving a fitting problem with a novel parametrization model. As of last, we develop a mapping function that allows transfer expressions and microexpressions between different meshes, which provides realistic animations to our detailed mesh. We cover all the mentioned points with the focus on key aspects as (i) how to describe skin wrinkles in a simple and straightforward manner, (ii) how to recover 3D from 2D detections, (iii) how to recover and model facial hair from 2D to 3D, (iv) how to transfer expressions between models holding both skin detail and facial hair, (v) how to perform all the described actions without training data nor user interaction. In this work, we present our proposals to solve these aspects with an efficient and simple setup. We validate our work with several datasets both synthetic and real data, prooving remarkable results even in challenging cases as occlusions as glasses, thick beards, and indeed working with different face topologies like single-eyed cyclops.
Address
Corporate Author Thesis Ph.D. thesis
Publisher Ediciones Graficas Rey Place of Publication Editor Felipe Lumbreras;Antonio Agudo
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-122714-3-0 Medium
Area Expedition Conference (up)
Notes ADAS Approved no
Call Number Admin @ si @ Rot2021 Serial 3513
Permanent link to this record