| |
Records |
Links |
|
Author |
Idoia Ruiz; Lorenzo Porzi; Samuel Rota Bulo; Peter Kontschieder; Joan Serrat |
|
| |
Title |
Weakly Supervised Multi-Object Tracking and Segmentation |
Type |
Conference Article |
| |
Year |
2021 |
Publication |
IEEE Winter Conference on Applications of Computer Vision Workshops |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
125-133 |
|
| |
Keywords |
|
|
| |
Abstract  |
We introduce the problem of weakly supervised MultiObject Tracking and Segmentation, i.e. joint weakly supervised instance segmentation and multi-object tracking, in which we do not provide any kind of mask annotation.
To address it, we design a novel synergistic training strategy by taking advantage of multi-task learning, i.e. classification and tracking tasks guide the training of the unsupervised instance segmentation. For that purpose, we extract weak foreground localization information, provided by
Grad-CAM heatmaps, to generate a partial ground truth to learn from. Additionally, RGB image level information is employed to refine the mask prediction at the edges of the
objects. We evaluate our method on KITTI MOTS, the most representative benchmark for this task, reducing the performance gap on the MOTSP metric between the fully supervised and weakly supervised approach to just 12% and 12.7 % for cars and pedestrians, respectively. |
|
| |
Address |
Virtual; January 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 |
WACVW |
|
| |
Notes |
ADAS; 600.118; 600.124 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ RPR2021 |
Serial |
3548 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Alexey Dosovitskiy; German Ros; Felipe Codevilla; Antonio Lopez; Vladlen Koltun |
|
| |
Title |
CARLA: An Open Urban Driving Simulator |
Type |
Conference Article |
| |
Year |
2017 |
Publication |
1st Annual Conference on Robot Learning. Proceedings of Machine Learning |
Abbreviated Journal |
|
|
| |
Volume |
78 |
Issue |
|
Pages |
1-16 |
|
| |
Keywords |
Autonomous driving; sensorimotor control; simulation |
|
| |
Abstract |
We introduce CARLA, an open-source simulator for autonomous driving research. CARLA has been developed from the ground up to support development, training, and validation of autonomous urban driving systems. In addition to open-source code and protocols, CARLA provides open digital assets (urban layouts, buildings, vehicles) that were created for this purpose and can be used freely. The simulation platform supports flexible specification of sensor suites and environmental conditions. We use CARLA to study the performance of three approaches to autonomous driving: a classic modular pipeline, an endto-end
model trained via imitation learning, and an end-to-end model trained via
reinforcement learning. The approaches are evaluated in controlled scenarios of
increasing difficulty, and their performance is examined via metrics provided by CARLA, illustrating the platform’s utility for autonomous driving research. |
|
| |
Address |
Mountain View; CA; USA; November 2017 |
|
| |
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 |
CORL |
|
| |
Notes |
ADAS; 600.085; 600.118 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ DRC2017 |
Serial |
2988 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
R. de Nijs; Sebastian Ramos; Gemma Roig; Xavier Boix; Luc Van Gool; K. Kühnlenz. |
|
| |
Title |
On-line Semantic Perception Using Uncertainty |
Type |
Conference Article |
| |
Year |
2012 |
Publication |
International Conference on Intelligent Robots and Systems |
Abbreviated Journal |
IROS |
|
| |
Volume |
|
Issue |
|
Pages |
4185-4191 |
|
| |
Keywords |
Semantic Segmentation |
|
| |
Abstract |
Visual perception capabilities are still highly unreliable in unconstrained settings, and solutions might not beaccurate in all regions of an image. Awareness of the uncertainty of perception is a fundamental requirement for proper high level decision making in a robotic system. Yet, the uncertainty measure is often sacrificed to account for dependencies between object/region classifiers. This is the case of Conditional Random Fields (CRFs), the success of which stems from their ability to infer the most likely world configuration, but they do not directly allow to estimate the uncertainty of the solution. In this paper, we consider the setting of assigning semantic labels to the pixels of an image sequence. Instead of using a CRF, we employ a Perturb-and-MAP Random Field, a recently introduced probabilistic model that allows performing fast approximate sampling from its probability density function. This allows to effectively compute the uncertainty of the solution, indicating the reliability of the most likely labeling in each region of the image. We report results on the CamVid dataset, a standard benchmark for semantic labeling of urban image sequences. In our experiments, we show the benefits of exploiting the uncertainty by putting more computational effort on the regions of the image that are less reliable, and use more efficient techniques for other regions, showing little decrease of performance |
|
| |
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 |
IROS |
|
| |
Notes |
ADAS |
Approved |
no |
|
| |
Call Number |
ADAS @ adas @ NRR2012 |
Serial |
2378 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
German Ros; Laura Sellart; Joanna Materzynska; David Vazquez; Antonio Lopez |
|
| |
Title |
The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes |
Type |
Conference Article |
| |
Year |
2016 |
Publication |
29th IEEE Conference on Computer Vision and Pattern Recognition |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
3234-3243 |
|
| |
Keywords |
Domain Adaptation; Autonomous Driving; Virtual Data; Semantic Segmentation |
|
| |
Abstract |
Vision-based semantic segmentation in urban scenarios is a key functionality for autonomous driving. The irruption of deep convolutional neural networks (DCNNs) allows to foresee obtaining reliable classifiers to perform such a visual task. However, DCNNs require to learn many parameters from raw images; thus, having a sufficient amount of diversified images with this class annotations is needed. These annotations are obtained by a human cumbersome labour specially challenging for semantic segmentation, since pixel-level annotations are required. In this paper, we propose to use a virtual world for automatically generating realistic synthetic images with pixel-level annotations. Then, we address the question of how useful can be such data for the task of semantic segmentation; in particular, when using a DCNN paradigm. In order to answer this question we have generated a synthetic diversified collection of urban images, named SynthCity, with automatically generated class annotations. We use SynthCity in combination with publicly available real-world urban images with manually provided annotations. Then, we conduct experiments on a DCNN setting that show how the inclusion of SynthCity in the training stage significantly improves the performance of the semantic segmentation task |
|
| |
Address |
Las Vegas; USA; June 2016 |
|
| |
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 |
CVPR |
|
| |
Notes |
ADAS; 600.085; 600.082; 600.076 |
Approved |
no |
|
| |
Call Number |
ADAS @ adas @ RSM2016 |
Serial |
2739 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Jose Manuel Alvarez; Theo Gevers; Antonio Lopez |
|
| |
Title |
3D Scene Priors for Road Detection |
Type |
Conference Article |
| |
Year |
2010 |
Publication |
23rd IEEE Conference on Computer Vision and Pattern Recognition |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
57–64 |
|
| |
Keywords |
road detection |
|
| |
Abstract |
Vision-based road detection is important in different areas of computer vision such as autonomous driving, car collision warning and pedestrian crossing detection. However, current vision-based road detection methods are usually based on low-level features and they assume structured roads, road homogeneity, and uniform lighting conditions. Therefore, in this paper, contextual 3D information is used in addition to low-level cues. Low-level photometric invariant cues are derived from the appearance of roads. Contextual cues used include horizon lines, vanishing points, 3D scene layout and 3D road stages. Moreover, temporal road cues are included. All these cues are sensitive to different imaging conditions and hence are considered as weak cues. Therefore, they are combined to improve the overall performance of the algorithm. To this end, the low-level, contextual and temporal cues are combined in a Bayesian framework to classify road sequences. Large scale experiments on road sequences show that the road detection method is robust to varying imaging conditions, road types, and scenarios (tunnels, urban and highway). Further, using the combined cues outperforms all other individual cues. Finally, the proposed method provides highest road detection accuracy when compared to state-of-the-art methods. |
|
| |
Address |
San Francisco; CA; USA; June 2010 |
|
| |
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 |
1063-6919 |
ISBN |
978-1-4244-6984-0 |
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
CVPR |
|
| |
Notes |
ADAS;ISE |
Approved |
no |
|
| |
Call Number |
ADAS @ adas @ AGL2010a |
Serial |
1302 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
David Vazquez; Antonio Lopez; Daniel Ponsa |
|
| |
Title |
Unsupervised Domain Adaptation of Virtual and Real Worlds for Pedestrian Detection |
Type |
Conference Article |
| |
Year |
2012 |
Publication |
21st International Conference on Pattern Recognition |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
3492 - 3495 |
|
| |
Keywords |
Pedestrian Detection; Domain Adaptation; Virtual worlds |
|
| |
Abstract |
Vision-based object detectors are crucial for different applications. They rely on learnt object models. Ideally, we would like to deploy our vision system in the scenario where it must operate, and lead it to self-learn how to distinguish the objects of interest, i.e., without human intervention. However, the learning of each object model requires labelled samples collected through a tiresome manual process. For instance, we are interested in exploring the self-training of a pedestrian detector for driver assistance systems. Our first approach to avoid manual labelling consisted in the use of samples coming from realistic computer graphics, so that their labels are automatically available [12]. This would make possible the desired self-training of our pedestrian detector. However, as we showed in [14], between virtual and real worlds it may be a dataset shift. In order to overcome it, we propose the use of unsupervised domain adaptation techniques that avoid human intervention during the adaptation process. In particular, this paper explores the use of the transductive SVM (T-SVM) learning algorithm in order to adapt virtual and real worlds for pedestrian detection (Fig. 1). |
|
| |
Address |
Tsukuba Science City, Japan |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
IEEE |
Place of Publication |
Tsukuba Science City, JAPAN |
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
1051-4651 |
ISBN |
978-1-4673-2216-4 |
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
ICPR |
|
| |
Notes |
ADAS |
Approved |
no |
|
| |
Call Number |
ADAS @ adas @ VLP2012 |
Serial |
1981 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
G.D. Evangelidis; Ferran Diego; Joan Serrat; Antonio Lopez |
|
| |
Title |
Slice Matching for Accurate Spatio-Temporal Alignment |
Type |
Conference Article |
| |
Year |
2011 |
Publication |
In ICCV Workshop on Visual Surveillance |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
|
|
| |
Keywords |
video alignment |
|
| |
Abstract |
Video synchronization and alignment is a rather recent topic in computer vision. It usually deals with the problem of aligning sequences recorded simultaneously by static, jointly- or independently-moving cameras. In this paper, we investigate the more difficult problem of matching videos captured at different times from independently-moving cameras, whose trajectories are approximately coincident or parallel. To this end, we propose a novel method that pixel-wise aligns videos and allows thus to automatically highlight their differences. This primarily aims at visual surveillance but the method can be adopted as is by other related video applications, like object transfer (augmented reality) or high dynamic range video. We build upon a slice matching scheme to first synchronize the sequences, while we develop a spatio-temporal alignment scheme to spatially register corresponding frames and refine the temporal mapping. We investigate the performance of the proposed method on videos recorded from vehicles driven along different types of roads and compare with related previous works. |
|
| |
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 |
VS |
|
| |
Notes |
ADAS |
Approved |
no |
|
| |
Call Number |
Admin @ si @ EDS2011; ADAS @ adas @ eds2011a |
Serial |
1861 |
|
| 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 |
Patricia Suarez; Angel Sappa; Boris X. Vintimilla |
|
| |
Title |
Infrared Image Colorization based on a Triplet DCGAN Architecture |
Type |
Conference Article |
| |
Year |
2017 |
Publication |
IEEE Conference on Computer Vision and Pattern Recognition Workshops |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
|
|
| |
Keywords |
|
|
| |
Abstract |
This paper proposes a novel approach for colorizing near infrared (NIR) images using Deep Convolutional Generative Adversarial Network (GAN) architectures. The proposed approach is based on the usage of a triplet model for learning each color channel independently, in a more homogeneous way. It allows a fast convergence during the training, obtaining a greater similarity between the given NIR image and the corresponding ground truth. The proposed approach has been evaluated with a large data set of NIR images and compared with a recent approach, which is also based on a GAN architecture but in this case all the
color channels are obtained at the same time. |
|
| |
Address |
Honolulu; Hawaii; USA; July 2017 |
|
| |
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 |
CVPRW |
|
| |
Notes |
ADAS; 600.086; 600.118 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ SSV2017b |
Serial |
2920 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Mohammad Rouhani; Angel Sappa |
|
| |
Title |
Non-Rigid Shape Registration: A Single Linear Least Squares Framework |
Type |
Conference Article |
| |
Year |
2012 |
Publication |
12th European Conference on Computer Vision |
Abbreviated Journal |
|
|
| |
Volume |
7578 |
Issue |
|
Pages |
264-277 |
|
| |
Keywords |
|
|
| |
Abstract |
This paper proposes a non-rigid registration formulation capturing both global and local deformations in a single framework. This formulation is based on a quadratic estimation of the registration distance together with a quadratic regularization term. Hence, the optimal transformation parameters are easily obtained by solving a liner system of equations, which guarantee a fast convergence. Experimental results with challenging 2D and 3D shapes are presented to show the validity of the proposed framework. Furthermore, comparisons with the most relevant approaches are provided. |
|
| |
Address |
Florencia |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
Springer Berlin Heidelberg |
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
0302-9743 |
ISBN |
978-3-642-33785-7 |
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
ECCV |
|
| |
Notes |
ADAS |
Approved |
no |
|
| |
Call Number |
Admin @ si @ RoS2012a |
Serial |
2158 |
|
| Permanent link to this record |
