Records |
Author |
David Vazquez; Jiaolong Xu; Sebastian Ramos; Antonio Lopez; Daniel Ponsa |
Title |
Weakly Supervised Automatic Annotation of Pedestrian Bounding Boxes |
Type |
Conference Article |
Year |
2013 |
Publication |
CVPR Workshop on Ground Truth – What is a good dataset? |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
706 - 711 |
Keywords |
Pedestrian Detection; Domain Adaptation |
Abstract |
Among the components of a pedestrian detector, its trained pedestrian classifier is crucial for achieving the desired performance. The initial task of the training process consists in collecting samples of pedestrians and background, which involves tiresome manual annotation of pedestrian bounding boxes (BBs). Thus, recent works have assessed the use of automatically collected samples from photo-realistic virtual worlds. However, learning from virtual-world samples and testing in real-world images may suffer the dataset shift problem. Accordingly, in this paper we assess an strategy to collect samples from the real world and retrain with them, thus avoiding the dataset shift, but in such a way that no BBs of real-world pedestrians have to be provided. In particular, we train a pedestrian classifier based on virtual-world samples (no human annotation required). Then, using such a classifier we collect pedestrian samples from real-world images by detection. After, a human oracle rejects the false detections efficiently (weak annotation). Finally, a new classifier is trained with the accepted detections. We show that this classifier is competitive with respect to the counterpart trained with samples collected by manually annotating hundreds of pedestrian BBs. |
Address |
Portland; Oregon; June 2013 |
Corporate Author |
|
Thesis |
|
Publisher |
IEEE |
Place of Publication |
|
Editor |
|
Language |
English |
Summary Language |
English |
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
CVPRW |
Notes |
ADAS; 600.054; 600.057; 601.217 |
Approved |
no |
Call Number |
ADAS @ adas @ VXR2013a |
Serial |
2219 |
Permanent link to this record |
|
|
|
Author |
Jiaolong Xu; David Vazquez; Sebastian Ramos; Antonio Lopez; Daniel Ponsa |
Title |
Adapting a Pedestrian Detector by Boosting LDA Exemplar Classifiers |
Type |
Conference Article |
Year |
2013 |
Publication |
CVPR Workshop on Ground Truth – What is a good dataset? |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
688 - 693 |
Keywords |
Pedestrian Detection; Domain Adaptation |
Abstract |
Training vision-based pedestrian detectors using synthetic datasets (virtual world) is a useful technique to collect automatically the training examples with their pixel-wise ground truth. However, as it is often the case, these detectors must operate in real-world images, experiencing a significant drop of their performance. In fact, this effect also occurs among different real-world datasets, i.e. detectors' accuracy drops when the training data (source domain) and the application scenario (target domain) have inherent differences. Therefore, in order to avoid this problem, it is required to adapt the detector trained with synthetic data to operate in the real-world scenario. In this paper, we propose a domain adaptation approach based on boosting LDA exemplar classifiers from both virtual and real worlds. We evaluate our proposal on multiple real-world pedestrian detection datasets. The results show that our method can efficiently adapt the exemplar classifiers from virtual to real world, avoiding drops in average precision over the 15%. |
Address |
Portland; oregon; June 2013 |
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
English |
Summary Language |
English |
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
CVPRW |
Notes |
ADAS; 600.054; 600.057; 601.217 |
Approved |
yes |
Call Number |
XVR2013; ADAS @ adas @ xvr2013a |
Serial |
2220 |
Permanent link to this record |
|
|
|
Author |
Jiaolong Xu; David Vazquez; Antonio Lopez; Javier Marin; Daniel Ponsa |
Title |
Learning a Multiview Part-based Model in Virtual World for Pedestrian Detection |
Type |
Conference Article |
Year |
2013 |
Publication |
IEEE Intelligent Vehicles Symposium |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
467 - 472 |
Keywords |
Pedestrian Detection; Virtual World; Part based |
Abstract |
State-of-the-art deformable part-based models based on latent SVM have shown excellent results on human detection. In this paper, we propose to train a multiview deformable part-based model with automatically generated part examples from virtual-world data. The method is efficient as: (i) the part detectors are trained with precisely extracted virtual examples, thus no latent learning is needed, (ii) the multiview pedestrian detector enhances the performance of the pedestrian root model, (iii) a top-down approach is used for part detection which reduces the searching space. We evaluate our model on Daimler and Karlsruhe Pedestrian Benchmarks with publicly available Caltech pedestrian detection evaluation framework and the result outperforms the state-of-the-art latent SVM V4.0, on both average miss rate and speed (our detector is ten times faster). |
Address |
Gold Coast; Australia; June 2013 |
Corporate Author |
|
Thesis |
|
Publisher |
IEEE |
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
1931-0587 |
ISBN |
978-1-4673-2754-1 |
Medium |
|
Area |
|
Expedition |
|
Conference |
IV |
Notes |
ADAS; 600.054; 600.057 |
Approved |
no |
Call Number |
XVL2013; ADAS @ adas @ xvl2013a |
Serial |
2214 |
Permanent link to this record |
|
|
|
Author |
Fernando Barrera; Felipe Lumbreras; Angel Sappa |
Title |
Multispectral Piecewise Planar Stereo using Manhattan-World Assumption |
Type |
Journal Article |
Year |
2013 |
Publication |
Pattern Recognition Letters |
Abbreviated Journal |
PRL |
Volume |
34 |
Issue |
1 |
Pages |
52-61 |
Keywords |
Multispectral stereo rig; Dense disparity maps from multispectral stereo; Color and infrared images |
Abstract |
This paper proposes a new framework for extracting dense disparity maps from a multispectral stereo rig. The system is constructed with an infrared and a color camera. It is intended to explore novel multispectral stereo matching approaches that will allow further extraction of semantic information. The proposed framework consists of three stages. Firstly, an initial sparse disparity map is generated by using a cost function based on feature matching in a multiresolution scheme. Then, by looking at the color image, a set of planar hypotheses is defined to describe the surfaces on the scene. Finally, the previous stages are combined by reformulating the disparity computation as a global minimization problem. The paper has two main contributions. The first contribution combines mutual information with a shape descriptor based on gradient in a multiresolution scheme. The second contribution, which is based on the Manhattan-world assumption, extracts a dense disparity representation using the graph cut algorithm. Experimental results in outdoor scenarios are provided showing the validity of the proposed framework. |
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; 600.054; 600.055; 605.203 |
Approved |
no |
Call Number |
Admin @ si @ BLS2013 |
Serial |
2245 |
Permanent link to this record |
|
|
|
Author |
Yainuvis Socarras; Sebastian Ramos; David Vazquez; Antonio Lopez; Theo Gevers |
Title |
Adapting Pedestrian Detection from Synthetic to Far Infrared Images |
Type |
Conference Article |
Year |
2013 |
Publication |
ICCV Workshop on Visual Domain Adaptation and Dataset Bias |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
Domain Adaptation; Far Infrared; Pedestrian Detection |
Abstract |
We present different techniques to adapt a pedestrian classifier trained with synthetic images and the corresponding automatically generated annotations to operate with far infrared (FIR) images. The information contained in this kind of images allow us to develop a robust pedestrian detector invariant to extreme illumination changes. |
Address |
Sydney; Australia; December 2013 |
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
Sydney, Australy |
Editor |
|
Language |
English |
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
ICCVW-VisDA |
Notes |
ADAS; 600.054; 600.055; 600.057; 601.217;ISE |
Approved |
no |
Call Number |
ADAS @ adas @ SRV2013 |
Serial |
2334 |
Permanent link to this record |
|
|
|
Author |
German Ros; J. Guerrero; Angel Sappa; Antonio Lopez |
Title |
VSLAM pose initialization via Lie groups and Lie algebras optimization |
Type |
Conference Article |
Year |
2013 |
Publication |
Proceedings of IEEE International Conference on Robotics and Automation |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
5740 - 5747 |
Keywords |
SLAM |
Abstract |
We present a novel technique for estimating initial 3D poses in the context of localization and Visual SLAM problems. The presented approach can deal with noise, outliers and a large amount of input data and still performs in real time in a standard CPU. Our method produces solutions with an accuracy comparable to those produced by RANSAC but can be much faster when the percentage of outliers is high or for large amounts of input data. On the current work we propose to formulate the pose estimation as an optimization problem on Lie groups, considering their manifold structure as well as their associated Lie algebras. This allows us to perform a fast and simple optimization at the same time that conserve all the constraints imposed by the Lie group SE(3). Additionally, we present several key design concepts related with the cost function and its Jacobian; aspects that are critical for the good performance of the algorithm. |
Address |
Karlsruhe; Germany; May 2013 |
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 |
1050-4729 |
ISBN |
978-1-4673-5641-1 |
Medium |
|
Area |
|
Expedition |
|
Conference |
ICRA |
Notes |
ADAS; 600.054; 600.055; 600.057 |
Approved |
no |
Call Number |
Admin @ si @ RGS2013a; ADAS @ adas @ |
Serial |
2225 |
Permanent link to this record |
|
|
|
Author |
Yainuvis Socarras |
Title |
Image segmentation for improving pedestrian detection |
Type |
Report |
Year |
2011 |
Publication |
CVC Technical Report |
Abbreviated Journal |
|
Volume |
167 |
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
Address |
Bellaterra (Spain) |
Corporate Author |
Computer Vision Center |
Thesis |
Master's 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 |
Admin @ si @ Soc2011 |
Serial |
1933 |
Permanent link to this record |
|
|
|
Author |
A. Pujol; Felipe Lumbreras; Javier Varona; Juan J. Villanueva |
Title |
Template matching through invariant eigenspace projection. |
Type |
Miscellaneous |
Year |
1999 |
Publication |
Proceedings of the VIII Symposium Nacional de Reconocimiento de Formas y Analisis de Imagenes. |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
Address |
Bilbao |
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 @ PLV1999 |
Serial |
6 |
Permanent link to this record |
|
|
|
Author |
Antonio Lopez; David Lloret; Joan Serrat |
Title |
Creaseness measures for CT and MR image registration. |
Type |
Miscellaneous |
Year |
1998 |
Publication |
CVPR’98 , IEEE Computer Society, pgs.694–699 |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
Creases are a type of ridge/valley structures that can be characterized by local conditions. Therefore, creaseness refers to local ridgeness and valleyness. The curvature K of the level curves and the mean curvature kM of the level surfaces are good measures of creaseness for 2-d and 3-d images, respectively. However, the way they are computed gives rise to discontinuities, reducing their usefulness in many applications. We propose a new creaseness measure, based on these curvatures, that avoids the discontinuities. We demonstrate its usefulness in the registration of CT and MR brain volumes, from the same patient, by searching the maximum in the correlation of their creaseness responses (ridgeness from the CT and valleyness from the MR). Due to the high dimensionality of the space of transforms, the search is performed by a hierarchical approach combined with an optimization method at each level of the hierarchy |
Address |
Santa Barbara, USA. |
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 @ LLS1998a |
Serial |
11 |
Permanent link to this record |
|
|
|
Author |
Antonio Lopez; Felipe Lumbreras; Joan Serrat |
Title |
Creaseness form level set extrinsec curvature. |
Type |
Miscellaneous |
Year |
1998 |
Publication |
5th European Conference on Computer Vision (ECCV’98), Lecture Notes in Computer Science,vol 1407, pgs. 156–169 |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
Address |
Freiburg, Germany. |
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 @ LLS1998b |
Serial |
12 |
Permanent link to this record |
|
|
|
Author |
Antonio Lopez; Ricardo Toledo; Joan Serrat; Juan J. Villanueva |
Title |
Extraction of vessel centerlines from 2D coronary angiographies |
Type |
Miscellaneous |
Year |
1999 |
Publication |
Proceedings of the VIII Symposium Nacional de Reconocimiento de Formas y Analisis de Imagenes. pgs. 489–496, volume I |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
Address |
Bilbao |
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 @ LTS1999 |
Serial |
14 |
Permanent link to this record |
|
|
|
Author |
David Lloret; Antonio Lopez; Joan Serrat |
Title |
3-D image Processing and Modeling, workshop on non-linear model-based image analysis. |
Type |
Miscellaneous |
Year |
1998 |
Publication |
NMBIA |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
Address |
Glasgow, U.K. |
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 @ LLS1998c |
Serial |
15 |
Permanent link to this record |
|
|
|
Author |
Antonio Lopez; W. Niessen; Joan Serrat; K. Nicolay; Bart M. Ter Haar Romeny; Juan J. Villanueva; M. Viergever |
Title |
New improvements in the multiscale analysis of trabecular bone patterns. |
Type |
Miscellaneous |
Year |
1999 |
Publication |
Proceedings of the VIII Symposium Nacional de Reconocimiento de Formas y Analisis de Imagenes (SNRFAI’99), pags. 497–504 |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
Address |
Bilbao |
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 @ LNS1999 |
Serial |
17 |
Permanent link to this record |
|
|
|
Author |
David Lloret; Joan Serrat |
Title |
System for calibration of a stereotatic frame. |
Type |
Miscellaneous |
Year |
1999 |
Publication |
Proceeding of the VIII Symposium Nacional de Reconocimiento de Formas y Analisis de Imagenes |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
Address |
Bilbao |
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 @ LlS1999 |
Serial |
20 |
Permanent link to this record |
|
|
|
Author |
A. Pujol; Javier Varona; Joan Serrat |
Title |
A machine vision system for the inspection of industrial sieves. |
Type |
Miscellaneous |
Year |
1997 |
Publication |
VII SNRFAI. |
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 @ PVS1997 |
Serial |
33 |
Permanent link to this record |