toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
  Records Links
Author Sudeep Katakol; Basem Elbarashy; Luis Herranz; Joost Van de Weijer; Antonio Lopez edit   pdf
url  doi
openurl 
  Title Distributed Learning and Inference with Compressed Images Type Journal Article
  Year 2021 Publication IEEE Transactions on Image Processing Abbreviated Journal TIP  
  Volume 30 Issue Pages 3069 - 3083  
  Keywords  
  Abstract (up) Modern computer vision requires processing large amounts of data, both while training the model and/or during inference, once the model is deployed. Scenarios where images are captured and processed in physically separated locations are increasingly common (e.g. autonomous vehicles, cloud computing). In addition, many devices suffer from limited resources to store or transmit data (e.g. storage space, channel capacity). In these scenarios, lossy image compression plays a crucial role to effectively increase the number of images collected under such constraints. However, lossy compression entails some undesired degradation of the data that may harm the performance of the downstream analysis task at hand, since important semantic information may be lost in the process. Moreover, we may only have compressed images at training time but are able to use original images at inference time, or vice versa, and in such a case, the downstream model suffers from covariate shift. In this paper, we analyze this phenomenon, with a special focus on vision-based perception for autonomous driving as a paradigmatic scenario. We see that loss of semantic information and covariate shift do indeed exist, resulting in a drop in performance that depends on the compression rate. In order to address the problem, we propose dataset restoration, based on image restoration with generative adversarial networks (GANs). Our method is agnostic to both the particular image compression method and the downstream task; and has the advantage of not adding additional cost to the deployed models, which is particularly important in resource-limited devices. The presented experiments focus on semantic segmentation as a challenging use case, cover a broad range of compression rates and diverse datasets, and show how our method is able to significantly alleviate the negative effects of compression on the downstream visual task.  
  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  
  Notes LAMP; ADAS; 600.120; 600.118;CIC Approved no  
  Call Number Admin @ si @ KEH2021 Serial 3543  
Permanent link to this record
 

 
Author Fahad Shahbaz Khan; Joost Van de Weijer; Muhammad Anwer Rao; Andrew Bagdanov; Michael Felsberg; Jorma edit   pdf
url  openurl
  Title Scale coding bag of deep features for human attribute and action recognition Type Journal Article
  Year 2018 Publication Machine Vision and Applications Abbreviated Journal MVAP  
  Volume 29 Issue 1 Pages 55-71  
  Keywords Action recognition; Attribute recognition; Bag of deep features  
  Abstract (up) Most approaches to human attribute and action recognition in still images are based on image representation in which multi-scale local features are pooled across scale into a single, scale-invariant encoding. Both in bag-of-words and the recently popular representations based on convolutional neural networks, local features are computed at multiple scales. However, these multi-scale convolutional features are pooled into a single scale-invariant representation. We argue that entirely scale-invariant image representations are sub-optimal and investigate approaches to scale coding within a bag of deep features framework. Our approach encodes multi-scale information explicitly during the image encoding stage. We propose two strategies to encode multi-scale information explicitly in the final image representation. We validate our two scale coding techniques on five datasets: Willow, PASCAL VOC 2010, PASCAL VOC 2012, Stanford-40 and Human Attributes (HAT-27). On all datasets, the proposed scale coding approaches outperform both the scale-invariant method and the standard deep features of the same network. Further, combining our scale coding approaches with standard deep features leads to consistent improvement over the 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  
  Notes LAMP; 600.068; 600.079; 600.106; 600.120;CIC;ADAS Approved no  
  Call Number Admin @ si @ KWR2018 Serial 3107  
Permanent link to this record
 

 
Author Carme Julia; Angel Sappa; Felipe Lumbreras; Joan Serrat; Antonio Lopez edit   pdf
doi  openurl
  Title An Iterative Multiresolution Scheme for SFM with Missing Data: single and multiple object scenes Type Journal Article
  Year 2010 Publication Image and Vision Computing Abbreviated Journal IMAVIS  
  Volume 28 Issue 1 Pages 164-176  
  Keywords  
  Abstract (up) Most of the techniques proposed for tackling the Structure from Motion problem (SFM) cannot deal with high percentages of missing data in the matrix of trajectories. Furthermore, an additional problem should be faced up when working with multiple object scenes: the rank of the matrix of trajectories should be estimated. This paper presents an iterative multiresolution scheme for SFM with missing data to be used in both the single and multiple object cases. The proposed scheme aims at recovering missing entries in the original input matrix. The objective is to improve the results by applying a factorization technique to the partially or totally filled in matrix instead of to the original input one. Experimental results obtained with synthetic and real data sequences, containing single and multiple objects, are presented to show the viability of the proposed approach.  
  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 0262-8856 ISBN Medium  
  Area Expedition Conference  
  Notes ADAS Approved no  
  Call Number ADAS @ adas @ JSL2010 Serial 1278  
Permanent link to this record
 

 
Author Xavier Soria; Angel Sappa; Riad I. Hammoud edit   pdf
url  doi
openurl 
  Title Wide-Band Color Imagery Restoration for RGB-NIR Single Sensor Images Type Journal Article
  Year 2018 Publication Sensors Abbreviated Journal SENS  
  Volume 18 Issue 7 Pages 2059  
  Keywords RGB-NIR sensor; multispectral imaging; deep learning; CNNs  
  Abstract (up) Multi-spectral RGB-NIR sensors have become ubiquitous in recent years. These sensors allow the visible and near-infrared spectral bands of a given scene to be captured at the same time. With such cameras, the acquired imagery has a compromised RGB color representation due to near-infrared bands (700–1100 nm) cross-talking with the visible bands (400–700 nm).
This paper proposes two deep learning-based architectures to recover the full RGB color images, thus removing the NIR information from the visible bands. The proposed approaches directly restore the high-resolution RGB image by means of convolutional neural networks. They are evaluated with several outdoor images; both architectures reach a similar performance when evaluated in different
scenarios and using different similarity metrics. Both of them improve the state of the art approaches.
 
  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  
  Notes ADAS; MSIAU; 600.086; 600.130; 600.122; 600.118 Approved no  
  Call Number Admin @ si @ SSH2018 Serial 3145  
Permanent link to this record
 

 
Author Jaume Amores edit   pdf
doi  openurl
  Title Multiple Instance Classification: review, taxonomy and comparative study Type Journal Article
  Year 2013 Publication Artificial Intelligence Abbreviated Journal AI  
  Volume 201 Issue Pages 81-105  
  Keywords Multi-instance learning; Codebook; Bag-of-Words  
  Abstract (up) Multiple Instance Learning (MIL) has become an important topic in the pattern recognition community, and many solutions to this problemhave been proposed until now. Despite this fact, there is a lack of comparative studies that shed light into the characteristics and behavior of the different methods. In this work we provide such an analysis focused on the classification task (i.e.,leaving out other learning tasks such as regression). In order to perform our study, we implemented
fourteen methods grouped into three different families. We analyze the performance of the approaches across a variety of well-known databases, and we also study their behavior in synthetic scenarios in order to highlight their characteristics. As a result of this analysis, we conclude that methods that extract global bag-level information show a clearly superior performance in general. In this sense, the analysis permits us to understand why some types of methods are more successful than others, and it permits us to establish guidelines in the design of new MIL
methods.
 
  Address  
  Corporate Author Thesis  
  Publisher Elsevier Science Publishers Ltd. Essex, UK Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 0004-3702 ISBN Medium  
  Area Expedition Conference  
  Notes ADAS; 601.042; 600.057 Approved no  
  Call Number Admin @ si @ Amo2013 Serial 2273  
Permanent link to this record
 

 
Author Gabriel Villalonga; Joost Van de Weijer; Antonio Lopez edit  url
doi  openurl
  Title Recognizing new classes with synthetic data in the loop: application to traffic sign recognition Type Journal Article
  Year 2020 Publication Sensors Abbreviated Journal SENS  
  Volume 20 Issue 3 Pages 583  
  Keywords  
  Abstract (up) On-board vision systems may need to increase the number of classes that can be recognized in a relatively short period. For instance, a traffic sign recognition system may suddenly be required to recognize new signs. Since collecting and annotating samples of such new classes may need more time than we wish, especially for uncommon signs, we propose a method to generate these samples by combining synthetic images and Generative Adversarial Network (GAN) technology. In particular, the GAN is trained on synthetic and real-world samples from known classes to perform synthetic-to-real domain adaptation, but applied to synthetic samples of the new classes. Using the Tsinghua dataset with a synthetic counterpart, SYNTHIA-TS, we have run an extensive set of experiments. The results show that the proposed method is indeed effective, provided that we use a proper Convolutional Neural Network (CNN) to perform the traffic sign recognition (classification) task as well as a proper GAN to transform the synthetic images. Here, a ResNet101-based classifier and domain adaptation based on CycleGAN performed extremely well for a ratio∼ 1/4 for new/known classes; even for more challenging ratios such as∼ 4/1, the results are also very positive.  
  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  
  Notes LAMP; ADAS; 600.118; 600.120;CIC Approved no  
  Call Number Admin @ si @ VWL2020 Serial 3405  
Permanent link to this record
 

 
Author Miguel Oliveira; Victor Santos; Angel Sappa edit  doi
openurl 
  Title Multimodal Inverse Perspective Mapping Type Journal Article
  Year 2015 Publication Information Fusion Abbreviated Journal IF  
  Volume 24 Issue Pages 108–121  
  Keywords Inverse perspective mapping; Multimodal sensor fusion; Intelligent vehicles  
  Abstract (up) Over the past years, inverse perspective mapping has been successfully applied to several problems in the field of Intelligent Transportation Systems. In brief, the method consists of mapping images to a new coordinate system where perspective effects are removed. The removal of perspective associated effects facilitates road and obstacle detection and also assists in free space estimation. There is, however, a significant limitation in the inverse perspective mapping: the presence of obstacles on the road disrupts the effectiveness of the mapping. The current paper proposes a robust solution based on the use of multimodal sensor fusion. Data from a laser range finder is fused with images from the cameras, so that the mapping is not computed in the regions where obstacles are present. As shown in the results, this considerably improves the effectiveness of the algorithm and reduces computation time when compared with the classical inverse perspective mapping. Furthermore, the proposed approach is also able to cope with several cameras with different lenses or image resolutions, as well as dynamic viewpoints.  
  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  
  Notes ADAS; 600.055; 600.076 Approved no  
  Call Number Admin @ si @ OSS2015c Serial 2532  
Permanent link to this record
 

 
Author David Vazquez; Javier Marin; Antonio Lopez; Daniel Ponsa; David Geronimo edit   pdf
doi  openurl
  Title Virtual and Real World Adaptation for Pedestrian Detection Type Journal Article
  Year 2014 Publication IEEE Transactions on Pattern Analysis and Machine Intelligence Abbreviated Journal TPAMI  
  Volume 36 Issue 4 Pages 797-809  
  Keywords Domain Adaptation; Pedestrian Detection  
  Abstract (up) Pedestrian detection is of paramount interest for many applications. Most promising detectors rely on discriminatively learnt classifiers, i.e., trained with annotated samples. However, the annotation step is a human intensive and subjective task worth to be minimized. By using virtual worlds we can automatically obtain precise and rich annotations. Thus, we face the question: can a pedestrian appearance model learnt in realistic virtual worlds work successfully for pedestrian detection in realworld images?. Conducted experiments show that virtual-world based training can provide excellent testing accuracy in real world, but it can also suffer the dataset shift problem as real-world based training does. Accordingly, we have designed a domain adaptation framework, V-AYLA, in which we have tested different techniques to collect a few pedestrian samples from the target domain (real world) and combine them with the many examples of the source domain (virtual world) in order to train a domain adapted pedestrian classifier that will operate in the target domain. V-AYLA reports the same detection accuracy than when training with many human-provided pedestrian annotations and testing with real-world images of the same domain. To the best of our knowledge, this is the first work demonstrating adaptation of virtual and real worlds for developing an object detector.  
  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 0162-8828 ISBN Medium  
  Area Expedition Conference  
  Notes ADAS; 600.057; 600.054; 600.076 Approved no  
  Call Number ADAS @ adas @ VML2014 Serial 2275  
Permanent link to this record
 

 
Author Fahad Shahbaz Khan; Joost Van de Weijer; Muhammad Anwer Rao; Michael Felsberg; Carlo Gatta edit   pdf
doi  openurl
  Title Semantic Pyramids for Gender and Action Recognition Type Journal Article
  Year 2014 Publication IEEE Transactions on Image Processing Abbreviated Journal TIP  
  Volume 23 Issue 8 Pages 3633-3645  
  Keywords  
  Abstract (up) Person description is a challenging problem in computer vision. We investigated two major aspects of person description: 1) gender and 2) action recognition in still images. Most state-of-the-art approaches for gender and action recognition rely on the description of a single body part, such as face or full-body. However, relying on a single body part is suboptimal due to significant variations in scale, viewpoint, and pose in real-world images. This paper proposes a semantic pyramid approach for pose normalization. Our approach is fully automatic and based on combining information from full-body, upper-body, and face regions for gender and action recognition in still images. The proposed approach does not require any annotations for upper-body and face of a person. Instead, we rely on pretrained state-of-the-art upper-body and face detectors to automatically extract semantic information of a person. Given multiple bounding boxes from each body part detector, we then propose a simple method to select the best candidate bounding box, which is used for feature extraction. Finally, the extracted features from the full-body, upper-body, and face regions are combined into a single representation for classification. To validate the proposed approach for gender recognition, experiments are performed on three large data sets namely: 1) human attribute; 2) head-shoulder; and 3) proxemics. For action recognition, we perform experiments on four data sets most used for benchmarking action recognition in still images: 1) Sports; 2) Willow; 3) PASCAL VOC 2010; and 4) Stanford-40. Our experiments clearly demonstrate that the proposed approach, despite its simplicity, outperforms state-of-the-art methods for gender and action recognition.  
  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 1057-7149 ISBN Medium  
  Area Expedition Conference  
  Notes CIC; LAMP; 601.160; 600.074; 600.079;MILAB;ADAS Approved no  
  Call Number Admin @ si @ KWR2014 Serial 2507  
Permanent link to this record
 

 
Author Enric Marti; Carme Julia; Debora Gil edit  doi
openurl 
  Title A PBL Experience in the Teaching of Computer Graphics Type Journal Article
  Year 2006 Publication Computer Graphics Forum Abbreviated Journal CGF  
  Volume 25 Issue 1 Pages 95-103  
  Keywords  
  Abstract (up) Project-Based Learning (PBL) is an educational strategy to improve student’s learning capability that, in recent years, has had a progressive acceptance in undergraduate studies. This methodology is based on solving a problem or project in a student working group. In this way, PBL focuses on learning the necessary tools to correctly find a solution to given problems. Since the learning initiative is transferred to the student, the PBL method promotes students own abilities. This allows a better assessment of the true workload that carries out the student in the subject. It follows that the methodology conforms to the guidelines of the Bologna document, which quantifies the student workload in a subject by means of the European credit transfer system (ECTS). PBL is currently applied in undergraduate studies needing strong practical training such as medicine, nursing or law sciences. Although this is also the case in engineering studies, amazingly, few experiences have been reported. In this paper we propose to use PBL in the educational organization of the Computer Graphics subjects in the Computer Science degree. Our PBL project focuses in the development of a C++ graphical environment based on the OpenGL libraries for visualization and handling of different graphical objects. The starting point is a basic skeleton that already includes lighting functions, perspective projection with mouse interaction to change the point of view and three predefined objects. Students have to complete this skeleton by adding their own functions to solve the project. A total number of 10 projects have been proposed and successfully solved. The exercises range from human face rendering to articulated objects, such as robot arms or puppets. In the present paper we extensively report the statement and educational objectives for two of the projects: solar system visualization and a chess game. We report our earlier educational experience based on the standard classroom theoretical, problem and practice sessions and the reasons that motivated searching for other learning methods. We have mainly chosen PBL because it improves the student learning initiative. We have applied the PBL educational model since the beginning of the second semester. The student’s feedback increases in his interest for the subject. We present a comparative study of the teachers’ and students’ workload between PBL and the classic teaching approach, which suggests that the workload increase in PBL is not as high as it seems.  
  Address  
  Corporate Author Thesis  
  Publisher Computer Graphics Forum Place of Publication Computer Vision CenterComputer Science Department Escola Tcnica Superior d’Enginyeria (UAB), Edifi 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 IAM;ADAS; Approved no  
  Call Number IAM @ iam @ MJG2006a Serial 1607  
Permanent link to this record
Select All    Deselect All
 |   | 
Details

Save Citations:
Export Records: