| |
Records |
Links |
|
Author |
Sudeep Katakol; Basem Elbarashy; Luis Herranz; Joost Van de Weijer; Antonio Lopez |
|
| |
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 |
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 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ KEH2021 |
Serial |
3543 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Jiaolong Xu; Sebastian Ramos; David Vazquez; Antonio Lopez |
|
| |
Title |
Domain Adaptation of Deformable Part-Based Models |
Type |
Journal Article |
| |
Year |
2014 |
Publication |
IEEE Transactions on Pattern Analysis and Machine Intelligence |
Abbreviated Journal |
TPAMI |
|
| |
Volume |
36 |
Issue |
12 |
Pages |
2367-2380 |
|
| |
Keywords |
Domain Adaptation; Pedestrian Detection |
|
| |
Abstract |
The accuracy of object classifiers can significantly drop when the training data (source domain) and the application scenario (target domain) have inherent differences. Therefore, adapting the classifiers to the scenario in which they must operate is of paramount importance. We present novel domain adaptation (DA) methods for object detection. As proof of concept, we focus on adapting the state-of-the-art deformable part-based model (DPM) for pedestrian detection. We introduce an adaptive structural SVM (A-SSVM) that adapts a pre-learned classifier between different domains. By taking into account the inherent structure in feature space (e.g., the parts in a DPM), we propose a structure-aware A-SSVM (SA-SSVM). Neither A-SSVM nor SA-SSVM needs to revisit the source-domain training data to perform the adaptation. Rather, a low number of target-domain training examples (e.g., pedestrians) are used. To address the scenario where there are no target-domain annotated samples, we propose a self-adaptive DPM based on a self-paced learning (SPL) strategy and a Gaussian Process Regression (GPR). Two types of adaptation tasks are assessed: from both synthetic pedestrians and general persons (PASCAL VOC) to pedestrians imaged from an on-board camera. Results show that our proposals avoid accuracy drops as high as 15 points when comparing adapted and non-adapted detectors. |
|
| |
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; 601.217; 600.076 |
Approved |
no |
|
| |
Call Number |
ADAS @ adas @ XRV2014b |
Serial |
2436 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Joan Serrat; Ferran Diego; Felipe Lumbreras; Jose Manuel Alvarez; Antonio Lopez; C. Elvira |
|
| |
Title |
Dynamic Comparison of Headlights |
Type |
Journal Article |
| |
Year |
2008 |
Publication |
Journal of Automobile Engineering |
Abbreviated Journal |
|
|
| |
Volume |
222 |
Issue |
5 |
Pages |
643–656 |
|
| |
Keywords |
video alignment |
|
| |
Abstract |
|
|
| |
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 |
Approved |
no |
|
| |
Call Number |
ADAS @ adas @ SDL2008a |
Serial |
958 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
A. Restrepo; Angel Sappa; M. Devy |
|
| |
Title |
Edge registration versus triangular mesh registration, a comparative study |
Type |
Journal |
| |
Year |
2005 |
Publication |
Signal Processing: Image Communication 20: 853–868 (IF: 1.264) |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
|
|
| |
Keywords |
|
|
| |
Abstract |
|
|
| |
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 |
Approved |
no |
|
| |
Call Number |
ADAS @ adas @ RSD2005 |
Serial |
567 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Marçal Rusiñol; David Aldavert; Ricardo Toledo; Josep Llados |
|
| |
Title |
Efficient segmentation-free keyword spotting in historical document collections |
Type |
Journal Article |
| |
Year |
2015 |
Publication |
Pattern Recognition |
Abbreviated Journal |
PR |
|
| |
Volume |
48 |
Issue |
2 |
Pages |
545–555 |
|
| |
Keywords |
Historical documents; Keyword spotting; Segmentation-free; Dense SIFT features; Latent semantic analysis; Product quantization |
|
| |
Abstract |
In this paper we present an efficient segmentation-free word spotting method, applied in the context of historical document collections, that follows the query-by-example paradigm. We use a patch-based framework where local patches are described by a bag-of-visual-words model powered by SIFT descriptors. By projecting the patch descriptors to a topic space with the latent semantic analysis technique and compressing the descriptors with the product quantization method, we are able to efficiently index the document information both in terms of memory and time. The proposed method is evaluated using four different collections of historical documents achieving good performances on both handwritten and typewritten scenarios. The yielded performances outperform the recent state-of-the-art keyword spotting 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 |
DAG; ADAS; 600.076; 600.077; 600.061; 601.223; 602.006; 600.055 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ RAT2015a |
Serial |
2544 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Enrique Cabello; Cristina Conde; Angel Serrano; Licesio Rodriguez; David Vazquez |
|
| |
Title |
Empleo de sistemas biométricos para el reconocimiento de personas en aeropuertos |
Type |
Journal Article |
| |
Year |
2006 |
Publication |
Instituto Universitario de Investigación sobre Seguridad Interior (IUSI 2006) |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
|
|
| |
Keywords |
Surveillance; Face detection; Face recognition |
|
| |
Abstract |
El presente proyecto se desarrolló a lo largo del año 2005, probando un prototipo de un sistema de verificación facial con imágenes extraídas de las cámaras de video vigilancia del aeropuerto de Barajas. Se diseñaron varios experimentos, agrupados en dos clases. En el primer tipo, el sistema es entrenado con imágenes obtenidas en condiciones de laboratorio y luego probado con imágenes extraídas de las cámaras de video vigilancia del aeropuerto de Barajas. En el segundo caso, tanto las imágenes de entrenamiento como las de prueba corresponden a imágenes extraídas de Barajas. Se ha desarrollado un sistema completo, que incluye adquisición y digitalización de las imágenes, localización y recorte de las caras en escena, verificación de sujetos y obtención de resultados. Los resultados muestran, que, en general, un sistema de verificación facial basado en imágenes puede ser una ayuda a un operario que deba estar vigilando amplias zonas. |
|
| |
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 |
invisible;ADAS |
Approved |
no |
|
| |
Call Number |
ADAS @ adas @ CCS2006a |
Serial |
1672 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Fadi Dornaika; Angel Sappa |
|
| |
Title |
Evaluation of an Appearance-based 3D Face Tracker using Dense 3D Data |
Type |
Journal |
| |
Year |
2008 |
Publication |
Machine Vision and Applications |
Abbreviated Journal |
|
|
| |
Volume |
19 |
Issue |
5-6 |
Pages |
427–441 |
|
| |
Keywords |
|
|
| |
Abstract |
|
|
| |
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 |
Approved |
no |
|
| |
Call Number |
ADAS @ adas @ DoS2008b |
Serial |
1018 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Arnau Ramisa; David Aldavert; Shrihari Vasudevan; Ricardo Toledo; Ramon Lopez de Mantaras |
|
| |
Title |
Evaluation of Three Vision Based Object Perception Methods for a Mobile Robot |
Type |
Journal Article |
| |
Year |
2012 |
Publication |
Journal of Intelligent and Robotic Systems |
Abbreviated Journal |
JIRC |
|
| |
Volume |
68 |
Issue |
2 |
Pages |
185-208 |
|
| |
Keywords |
|
|
| |
Abstract |
This paper addresses visual object perception applied to mobile robotics. Being able to perceive household objects in unstructured environments is a key capability in order to make robots suitable to perform complex tasks in home environments. However, finding a solution for this task is daunting: it requires the ability to handle the variability in image formation in a moving camera with tight time constraints. The paper brings to attention some of the issues with applying three state of the art object recognition and detection methods in a mobile robotics scenario, and proposes methods to deal with windowing/segmentation. Thus, this work aims at evaluating the state-of-the-art in object perception in an attempt to develop a lightweight solution for mobile robotics use/research in typical indoor settings. |
|
| |
Address |
|
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
Springer Netherlands |
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
0921-0296 |
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
ADAS |
Approved |
no |
|
| |
Call Number |
Admin @ si @ RAV2012 |
Serial |
2150 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Katerine Diaz; Jesus Martinez del Rincon; Aura Hernandez-Sabate; Marçal Rusiñol; Francesc J. Ferri |
|
| |
Title |
Fast Kernel Generalized Discriminative Common Vectors for Feature Extraction |
Type |
Journal Article |
| |
Year |
2018 |
Publication |
Journal of Mathematical Imaging and Vision |
Abbreviated Journal |
JMIV |
|
| |
Volume |
60 |
Issue |
4 |
Pages |
512-524 |
|
| |
Keywords |
|
|
| |
Abstract |
This paper presents a supervised subspace learning method called Kernel Generalized Discriminative Common Vectors (KGDCV), as a novel extension of the known Discriminative Common Vectors method with Kernels. Our method combines the advantages of kernel methods to model complex data and solve nonlinear
problems with moderate computational complexity, with the better generalization properties of generalized approaches for large dimensional data. These attractive combination makes KGDCV specially suited for feature extraction and classification in computer vision, image processing and pattern recognition applications. Two different approaches to this generalization are proposed, a first one based on the kernel trick (KT) and a second one based on the nonlinear projection trick (NPT) for even higher efficiency. Both methodologies
have been validated on four different image datasets containing faces, objects and handwritten digits, and compared against well known non-linear state-of-art methods. Results show better discriminant properties than other generalized approaches both linear or kernel. In addition, the KGDCV-NPT approach presents a considerable computational gain, without compromising the accuracy of the model. |
|
| |
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 |
DAG; ADAS; 600.086; 600.130; 600.121; 600.118; 600.129 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ DMH2018a |
Serial |
3062 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Katerine Diaz; Jesus Martinez del Rincon; Marçal Rusiñol; Aura Hernandez-Sabate |
|
| |
Title |
Feature Extraction by Using Dual-Generalized Discriminative Common Vectors |
Type |
Journal Article |
| |
Year |
2019 |
Publication |
Journal of Mathematical Imaging and Vision |
Abbreviated Journal |
JMIV |
|
| |
Volume |
61 |
Issue |
3 |
Pages |
331-351 |
|
| |
Keywords |
Online feature extraction; Generalized discriminative common vectors; Dual learning; Incremental learning; Decremental learning |
|
| |
Abstract |
In this paper, a dual online subspace-based learning method called dual-generalized discriminative common vectors (Dual-GDCV) is presented. The method extends incremental GDCV by exploiting simultaneously both the concepts of incremental and decremental learning for supervised feature extraction and classification. Our methodology is able to update the feature representation space without recalculating the full projection or accessing the previously processed training data. It allows both adding information and removing unnecessary data from a knowledge base in an efficient way, while retaining the previously acquired knowledge. The proposed method has been theoretically proved and empirically validated in six standard face recognition and classification datasets, under two scenarios: (1) removing and adding samples of existent classes, and (2) removing and adding new classes to a classification problem. Results show a considerable computational gain without compromising the accuracy of the model in comparison with both batch methodologies and other state-of-art adaptive methods. |
|
| |
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 |
DAG; ADAS; 600.084; 600.118; 600.121; 600.129 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ DRR2019 |
Serial |
3172 |
|
| Permanent link to this record |
