toggle visibility Search & Display Options
Select All    Deselect All << 1 2 3 4 5 6 7 8 9 10 >> [11–13]
List View
 | 
Citations
 | 
Details
  Records Links
Author Adrien Gaidon; Antonio Lopez; Florent Perronnin edit  url
openurl 
  Title The Reasonable Effectiveness of Synthetic Visual Data Type Journal Article
  Year 2018 Publication International Journal of Computer Vision Abbreviated Journal IJCV  
  Volume 126 Issue 9 Pages 899–901  
  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 (up) ISBN Medium  
  Area Expedition Conference  
  Notes ADAS; 600.118 Approved no  
  Call Number Admin @ si @ GLP2018 Serial 3180  
Permanent link to this record
 
 
Author Jiaolong Xu; Liang Xiao; Antonio Lopez edit  doi
openurl 
  Title Self-supervised Domain Adaptation for Computer Vision Tasks Type Journal Article
  Year 2019 Publication IEEE ACCESS Abbreviated Journal ACCESS  
  Volume 7 Issue Pages 156694 - 156706  
  Keywords  
  Abstract Recent progress of self-supervised visual representation learning has achieved remarkable success on many challenging computer vision benchmarks. However, whether these techniques can be used for domain adaptation has not been explored. In this work, we propose a generic method for self-supervised domain adaptation, using object recognition and semantic segmentation of urban scenes as use cases. Focusing on simple pretext/auxiliary tasks (e.g. image rotation prediction), we assess different learning strategies to improve domain adaptation effectiveness by self-supervision. Additionally, we propose two complementary strategies to further boost the domain adaptation accuracy on semantic segmentation within our method, consisting of prediction layer alignment and batch normalization calibration. The experimental results show adaptation levels comparable to most studied domain adaptation methods, thus, bringing self-supervision as a new alternative for reaching domain adaptation. The code is available at this link. https://github.com/Jiaolong/self-supervised-da.  
  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 (up) ISBN Medium  
  Area Expedition Conference  
  Notes ADAS; 600.118 Approved no  
  Call Number Admin @ si @ XXL2019 Serial 3302  
Permanent link to this record
 
 
Author Cesar de Souza; Adrien Gaidon; Yohann Cabon; Naila Murray; Antonio Lopez edit  doi
openurl 
  Title Generating Human Action Videos by Coupling 3D Game Engines and Probabilistic Graphical Models Type Journal Article
  Year 2019 Publication International Journal of Computer Vision Abbreviated Journal IJCV  
  Volume 128 Issue Pages 1505–1536  
  Keywords Procedural generation; Human action recognition; Synthetic data; Physics  
  Abstract Deep video action recognition models have been highly successful in recent years but require large quantities of manually-annotated data, which are expensive and laborious to obtain. In this work, we investigate the generation of synthetic training data for video action recognition, as synthetic data have been successfully used to supervise models for a variety of other computer vision tasks. We propose an interpretable parametric generative model of human action videos that relies on procedural generation, physics models and other components of modern game engines. With this model we generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for “Procedural Human Action Videos”. PHAV contains a total of 39,982 videos, with more than 1000 examples for each of 35 action categories. Our video generation approach is not limited to existing motion capture sequences: 14 of these 35 categories are procedurally-defined synthetic actions. In addition, each video is represented with 6 different data modalities, including RGB, optical flow and pixel-level semantic labels. These modalities are generated almost simultaneously using the Multiple Render Targets feature of modern GPUs. In order to leverage PHAV, we introduce a deep multi-task (i.e. that considers action classes from multiple datasets) representation learning architecture that is able to simultaneously learn from synthetic and real video datasets, even when their action categories differ. Our experiments on the UCF-101 and HMDB-51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance. Our approach also significantly outperforms video representations produced by fine-tuning state-of-the-art unsupervised generative models of 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 (up) ISBN Medium  
  Area Expedition Conference  
  Notes ADAS; 600.124; 600.118 Approved no  
  Call Number Admin @ si @ SGC2019 Serial 3303  
Permanent link to this record
 
 
Author Daniel Hernandez; Lukas Schneider; P. Cebrian; A. Espinosa; David Vazquez; Antonio Lopez; Uwe Franke; Marc Pollefeys; Juan Carlos Moure edit  url
openurl 
  Title Slanted Stixels: A way to represent steep streets Type Journal Article
  Year 2019 Publication International Journal of Computer Vision Abbreviated Journal IJCV  
  Volume 127 Issue Pages 1643–1658  
  Keywords  
  Abstract This work presents and evaluates a novel compact scene representation based on Stixels that infers geometric and semantic information. Our approach overcomes the previous rather restrictive geometric assumptions for Stixels by introducing a novel depth model to account for non-flat roads and slanted objects. Both semantic and depth cues are used jointly to infer the scene representation in a sound global energy minimization formulation. Furthermore, a novel approximation scheme is introduced in order to significantly reduce the computational complexity of the Stixel algorithm, and then achieve real-time computation capabilities. The idea is to first perform an over-segmentation of the image, discarding the unlikely Stixel cuts, and apply the algorithm only on the remaining Stixel cuts. This work presents a novel over-segmentation strategy based on a fully convolutional network, which outperforms an approach based on using local extrema of the disparity map. We evaluate the proposed methods in terms of semantic and geometric accuracy as well as run-time on four publicly available benchmark datasets. Our approach maintains accuracy on flat road scene datasets while improving substantially on a novel non-flat road dataset.  
  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 (up) ISBN Medium  
  Area Expedition Conference  
  Notes ADAS; 600.118; 600.124 Approved no  
  Call Number Admin @ si @ HSC2019 Serial 3304  
Permanent link to this record
 
 
Author Zhijie Fang; Antonio Lopez edit  url
doi  openurl
  Title Intention Recognition of Pedestrians and Cyclists by 2D Pose Estimation Type Journal Article
  Year 2019 Publication IEEE Transactions on Intelligent Transportation Systems Abbreviated Journal TITS  
  Volume Issue Pages  
  Keywords  
  Abstract Anticipating the intentions of vulnerable road users (VRUs) such as pedestrians and cyclists is critical for performing safe and comfortable driving maneuvers. This is the case for human driving and, thus, should be taken into account by systems providing any level of driving assistance, from advanced driver assistant systems (ADAS) to fully autonomous vehicles (AVs). In this paper, we show how the latest advances on monocular vision-based human pose estimation, i.e. those relying on deep Convolutional Neural Networks (CNNs), enable to recognize the intentions of such VRUs. In the case of cyclists, we assume that they follow traffic rules to indicate future maneuvers with arm signals. In the case of pedestrians, no indications can be assumed. Instead, we hypothesize that the walking pattern of a pedestrian allows to determine if he/she has the intention of crossing the road in the path of the ego-vehicle, so that the ego-vehicle must maneuver accordingly (e.g. slowing down or stopping). In this paper, we show how the same methodology can be used for recognizing pedestrians and cyclists' intentions. For pedestrians, we perform experiments on the JAAD dataset. For cyclists, we did not found an analogous dataset, thus, we created our own one by acquiring and annotating videos which we share with the research community. Overall, the proposed pipeline provides new state-of-the-art results on the intention recognition of VRUs.  
  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 (up) ISBN Medium  
  Area Expedition Conference  
  Notes ADAS; 600.118 Approved no  
  Call Number Admin @ si @ FaL2019 Serial 3305  
Permanent link to this record
 
 
Author Akhil Gurram; Onay Urfalioglu; Ibrahim Halfaoui; Fahd Bouzaraa; Antonio Lopez edit  url
doi  openurl
  Title Semantic Monocular Depth Estimation Based on Artificial Intelligence Type Journal Article
  Year 2020 Publication IEEE Intelligent Transportation Systems Magazine Abbreviated Journal ITSM  
  Volume Issue Pages  
  Keywords  
  Abstract Depth estimation provides essential information to perform autonomous driving and driver assistance. A promising line of work consists of introducing additional semantic information about the traffic scene when training CNNs for depth estimation. In practice, this means that the depth data used for CNN training is complemented with images having pixel-wise semantic labels where the same raw training data is associated with both types of ground truth, i.e., depth and semantic labels. The main contribution of this paper is to show that this hard constraint can be circumvented, i.e., that we can train CNNs for depth estimation by leveraging the depth and semantic information coming from heterogeneous datasets. In order to illustrate the benefits of our approach, we combine KITTI depth and Cityscapes semantic segmentation datasets, outperforming state-of-the-art results on monocular depth estimation.  
  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 (up) ISBN Medium  
  Area Expedition Conference  
  Notes ADAS; 600.124; 600.118 Approved no  
  Call Number Admin @ si @ GUH2019 Serial 3306  
Permanent link to this record
 
 
Author Fei Yang; Luis Herranz; Joost van de Weijer; Jose Antonio Iglesias; Antonio Lopez; Mikhail Mozerov edit   pdf
url  doi
openurl 
  Title Variable Rate Deep Image Compression with Modulated Autoencoder Type Journal Article
  Year 2020 Publication IEEE Signal Processing Letters Abbreviated Journal SPL  
  Volume 27 Issue Pages 331-335  
  Keywords  
  Abstract Variable rate is a requirement for flexible and adaptable image and video compression. However, deep image compression methods (DIC) are optimized for a single fixed rate-distortion (R-D) tradeoff. While this can be addressed by training multiple models for different tradeoffs, the memory requirements increase proportionally to the number of models. Scaling the bottleneck representation of a shared autoencoder can provide variable rate compression with a single shared autoencoder. However, the R-D performance using this simple mechanism degrades in low bitrates, and also shrinks the effective range of bitrates. To address these limitations, we formulate the problem of variable R-D optimization for DIC, and propose modulated autoencoders (MAEs), where the representations of a shared autoencoder are adapted to the specific R-D tradeoff via a modulation network. Jointly training this modulated autoencoder and the modulation network provides an effective way to navigate the R-D operational curve. Our experiments show that the proposed method can achieve almost the same R-D performance of independent models with significantly fewer parameters.  
  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 (up) ISBN Medium  
  Area Expedition Conference  
  Notes LAMP; ADAS; 600.141; 600.120; 600.118 Approved no  
  Call Number Admin @ si @ YHW2020 Serial 3346  
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 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 (up) ISBN Medium  
  Area Expedition Conference  
  Notes LAMP; ADAS; 600.118; 600.120 Approved no  
  Call Number Admin @ si @ VWL2020 Serial 3405  
Permanent link to this record
 
 
Author Gabriel Villalonga; Antonio Lopez edit   pdf
doi  openurl
  Title Co-Training for On-Board Deep Object Detection Type Journal Article
  Year 2020 Publication IEEE Access Abbreviated Journal ACCESS  
  Volume Issue Pages 194441 - 194456  
  Keywords  
  Abstract Providing ground truth supervision to train visual models has been a bottleneck over the years, exacerbated by domain shifts which degenerate the performance of such models. This was the case when visual tasks relied on handcrafted features and shallow machine learning and, despite its unprecedented performance gains, the problem remains open within the deep learning paradigm due to its data-hungry nature. Best performing deep vision-based object detectors are trained in a supervised manner by relying on human-labeled bounding boxes which localize class instances (i.e. objects) within the training images. Thus, object detection is one of such tasks for which human labeling is a major bottleneck. In this article, we assess co-training as a semi-supervised learning method for self-labeling objects in unlabeled images, so reducing the human-labeling effort for developing deep object detectors. Our study pays special attention to a scenario involving domain shift; in particular, when we have automatically generated virtual-world images with object bounding boxes and we have real-world images which are unlabeled. Moreover, we are particularly interested in using co-training for deep object detection in the context of driver assistance systems and/or self-driving vehicles. Thus, using well-established datasets and protocols for object detection in these application contexts, we will show how co-training is a paradigm worth to pursue for alleviating object labeling, working both alone and together with task-agnostic domain adaptation.  
  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 (up) ISBN Medium  
  Area Expedition Conference  
  Notes ADAS; 600.118 Approved no  
  Call Number Admin @ si @ ViL2020 Serial 3488  
Permanent link to this record
 
 
Author Yi Xiao; Felipe Codevilla; Akhil Gurram; Onay Urfalioglu; Antonio Lopez edit   pdf
url  doi
openurl 
  Title Multimodal end-to-end autonomous driving Type Journal Article
  Year 2020 Publication IEEE Transactions on Intelligent Transportation Systems Abbreviated Journal TITS  
  Volume Issue Pages  
  Keywords  
  Abstract A crucial component of an autonomous vehicle (AV) is the artificial intelligence (AI) is able to drive towards a desired destination. Today, there are different paradigms addressing the development of AI drivers. On the one hand, we find modular pipelines, which divide the driving task into sub-tasks such as perception and maneuver planning and control. On the other hand, we find end-to-end driving approaches that try to learn a direct mapping from input raw sensor data to vehicle control signals. The later are relatively less studied, but are gaining popularity since they are less demanding in terms of sensor data annotation. This paper focuses on end-to-end autonomous driving. So far, most proposals relying on this paradigm assume RGB images as input sensor data. However, AVs will not be equipped only with cameras, but also with active sensors providing accurate depth information (e.g., LiDARs). Accordingly, this paper analyses whether combining RGB and depth modalities, i.e. using RGBD data, produces better end-to-end AI drivers than relying on a single modality. We consider multimodality based on early, mid and late fusion schemes, both in multisensory and single-sensor (monocular depth estimation) settings. Using the CARLA simulator and conditional imitation learning (CIL), we show how, indeed, early fusion multimodality outperforms single-modality.  
  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 (up) ISBN Medium  
  Area Expedition Conference  
  Notes ADAS Approved no  
  Call Number Admin @ si @ XCG2020 Serial 3490  
Permanent link to this record
Select All    Deselect All << 1 2 3 4 5 6 7 8 9 10 >> [11–13]
List View
 | 
Citations
 | 
Details
toggle visibility
Save Citations:
Export Records: