toggle visibility Search & Display Options
Select All    Deselect All << 1 2 3 4 5 6 7 8 9 10 >> [11–14]
List View
 | 
Citations
 | 
Details
  Records Links
Author M. Altillawi; S. Li; S.M. Prakhya; Z. Liu; Joan Serrat edit  doi
openurl 
  Title Implicit Learning of Scene Geometry From Poses for Global Localization Type Journal Article
  Year (down) 2024 Publication IEEE Robotics and Automation Letters Abbreviated Journal ROBOTAUTOMLET  
  Volume 9 Issue 2 Pages 955-962  
  Keywords Localization; Localization and mapping; Deep learning for visual perception; Visual learning  
  Abstract Global visual localization estimates the absolute pose of a camera using a single image, in a previously mapped area. Obtaining the pose from a single image enables many robotics and augmented/virtual reality applications. Inspired by latest advances in deep learning, many existing approaches directly learn and regress 6 DoF pose from an input image. However, these methods do not fully utilize the underlying scene geometry for pose regression. The challenge in monocular relocalization is the minimal availability of supervised training data, which is just the corresponding 6 DoF poses of the images. In this letter, we propose to utilize these minimal available labels (i.e., poses) to learn the underlying 3D geometry of the scene and use the geometry to estimate the 6 DoF camera pose. We present a learning method that uses these pose labels and rigid alignment to learn two 3D geometric representations ( X, Y, Z coordinates ) of the scene, one in camera coordinate frame and the other in global coordinate frame. Given a single image, it estimates these two 3D scene representations, which are then aligned to estimate a pose that matches the pose label. This formulation allows for the active inclusion of additional learning constraints to minimize 3D alignment errors between the two 3D scene representations, and 2D re-projection errors between the 3D global scene representation and 2D image pixels, resulting in improved localization accuracy. During inference, our model estimates the 3D scene geometry in camera and global frames and aligns them rigidly to obtain pose in real-time. We evaluate our work on three common visual localization datasets, conduct ablation studies, and show that our method exceeds state-of-the-art regression methods' pose accuracy on all datasets.  
  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 2377-3766 ISBN Medium  
  Area Expedition Conference  
  Notes ADAS Approved no  
  Call Number Admin @ si @ Serial 3857  
Permanent link to this record
 
 
Author Jose Luis Gomez; Gabriel Villalonga; Antonio Lopez edit  url
openurl 
  Title Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models Type Journal Article
  Year (down) 2023 Publication Sensors – Special Issue on “Machine Learning for Autonomous Driving Perception and Prediction” Abbreviated Journal SENS  
  Volume 23 Issue 2 Pages 621  
  Keywords Domain adaptation; semi-supervised learning; Semantic segmentation; Autonomous driving  
  Abstract Semantic image segmentation is a central and challenging task in autonomous driving, addressed by training deep models. Since this training draws to a curse of human-based image labeling, using synthetic images with automatically generated labels together with unlabeled real-world images is a promising alternative. This implies to address an unsupervised domain adaptation (UDA) problem. In this paper, we propose a new co-training procedure for synth-to-real UDA of semantic
segmentation models. It consists of a self-training stage, which provides two domain-adapted models, and a model collaboration loop for the mutual improvement of these two models. These models are then used to provide the final semantic segmentation labels (pseudo-labels) for the real-world images. The overall
procedure treats the deep models as black boxes and drives their collaboration at the level of pseudo-labeled target images, i.e., neither modifying loss functions is required, nor explicit feature alignment. We test our proposal on standard synthetic and real-world datasets for on-board semantic segmentation. Our
procedure shows improvements ranging from ∼13 to ∼26 mIoU points over baselines, so establishing new state-of-the-art results.		  
  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; no proj Approved no  
  Call Number Admin @ si @ GVL2023 Serial 3705  
Permanent link to this record
 
 
Author Idoia Ruiz; Joan Serrat edit  doi
openurl 
  Title Hierarchical Novelty Detection for Traffic Sign Recognition Type Journal Article
  Year (down) 2022 Publication Sensors Abbreviated Journal SENS  
  Volume 22 Issue 12 Pages 4389  
  Keywords Novelty detection; hierarchical classification; deep learning; traffic sign recognition; autonomous driving; computer vision  
  Abstract Recent works have made significant progress in novelty detection, i.e., the problem of detecting samples of novel classes, never seen during training, while classifying those that belong to known classes. However, the only information this task provides about novel samples is that they are unknown. In this work, we leverage hierarchical taxonomies of classes to provide informative outputs for samples of novel classes. We predict their closest class in the taxonomy, i.e., its parent class. We address this problem, known as hierarchical novelty detection, by proposing a novel loss, namely Hierarchical Cosine Loss that is designed to learn class prototypes along with an embedding of discriminative features consistent with the taxonomy. We apply it to traffic sign recognition, where we predict the parent class semantics for new types of traffic signs. Our model beats state-of-the art approaches on two large scale traffic sign benchmarks, Mapillary Traffic Sign Dataset (MTSD) and Tsinghua-Tencent 100K (TT100K), and performs similarly on natural images benchmarks (AWA2, CUB). For TT100K and MTSD, our approach is able to detect novel samples at the correct nodes of the hierarchy with 81% and 36% of accuracy, respectively, at 80% known class accuracy.  
  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; 600.154 Approved no  
  Call Number Admin @ si @ RuS2022 Serial 3684  
Permanent link to this record
 
 
Author Aura Hernandez-Sabate; Jose Elias Yauri; Pau Folch; Miquel Angel Piera; Debora Gil edit  doi
openurl 
  Title Recognition of the Mental Workloads of Pilots in the Cockpit Using EEG Signals Type Journal Article
  Year (down) 2022 Publication Applied Sciences Abbreviated Journal APPLSCI  
  Volume 12 Issue 5 Pages 2298  
  Keywords Cognitive states; Mental workload; EEG analysis; Neural networks; Multimodal data fusion  
  Abstract The commercial flightdeck is a naturally multi-tasking work environment, one in which interruptions are frequent come in various forms, contributing in many cases to aviation incident reports. Automatic characterization of pilots’ workloads is essential to preventing these kind of incidents. In addition, minimizing the physiological sensor network as much as possible remains both a challenge and a requirement. Electroencephalogram (EEG) signals have shown high correlations with specific cognitive and mental states, such as workload. However, there is not enough evidence in the literature to validate how well models generalize in cases of new subjects performing tasks with workloads similar to the ones included during the model’s training. In this paper, we propose a convolutional neural network to classify EEG features across different mental workloads in a continuous performance task test that partly measures working memory and working memory capacity. Our model is valid at the general population level and it is able to transfer task learning to pilot mental workload recognition in a simulated operational environment.  
  Address February 2022  
  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 IAM; ADAS; 600.139; 600.145; 600.118 Approved no  
  Call Number Admin @ si @ HYF2022 Serial 3720  
Permanent link to this record
 
 
Author Akhil Gurram; Ahmet Faruk Tuna; Fengyi Shen; Onay Urfalioglu; Antonio Lopez edit   pdf
doi  openurl
  Title Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision Type Journal Article
  Year (down) 2021 Publication IEEE Transactions on Intelligent Transportation Systems Abbreviated Journal TITS  
  Volume 23 Issue 8 Pages 12738-12751  
  Keywords  
  Abstract Depth information is essential for on-board perception in autonomous driving and driver assistance. Monocular depth estimation (MDE) is very appealing since it allows for appearance and depth being on direct pixelwise correspondence without further calibration. Best MDE models are based on Convolutional Neural Networks (CNNs) trained in a supervised manner, i.e., assuming pixelwise ground truth (GT). Usually, this GT is acquired at training time through a calibrated multi-modal suite of sensors. However, also using only a monocular system at training time is cheaper and more scalable. This is possible by relying on structure-from-motion (SfM) principles to generate self-supervision. Nevertheless, problems of camouflaged objects, visibility changes, static-camera intervals, textureless areas, and scale ambiguity, diminish the usefulness of such self-supervision. In this paper, we perform monocular depth estimation by virtual-world supervision (MonoDEVS) and real-world SfM self-supervision. We compensate the SfM self-supervision limitations by leveraging virtual-world images with accurate semantic and depth supervision and addressing the virtual-to-real domain gap. Our MonoDEVSNet outperforms previous MDE CNNs trained on monocular and even stereo sequences.  
  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; 600.118 Approved no  
  Call Number Admin @ si @ GTS2021 Serial 3598  
Permanent link to this record
 
 
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 (down) 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 Daniel Hernandez; Antonio Espinosa; David Vazquez; Antonio Lopez; Juan C. Moure edit   pdf
url  doi
openurl 
  Title 3D Perception With Slanted Stixels on GPU Type Journal Article
  Year (down) 2021 Publication IEEE Transactions on Parallel and Distributed Systems Abbreviated Journal TPDS  
  Volume 32 Issue 10 Pages 2434-2447  
  Keywords Daniel Hernandez-Juarez; Antonio Espinosa; David Vazquez; Antonio M. Lopez; Juan C. Moure  
  Abstract This article presents a GPU-accelerated software design of the recently proposed model of Slanted Stixels, which represents the geometric and semantic information of a scene in a compact and accurate way. We reformulate the measurement depth model to reduce the computational complexity of the algorithm, relying on the confidence of the depth estimation and the identification of invalid values to handle outliers. The proposed massively parallel scheme and data layout for the irregular computation pattern that corresponds to a Dynamic Programming paradigm is described and carefully analyzed in performance terms. Performance is shown to scale gracefully on current generation embedded GPUs. We assess the proposed methods in terms of semantic and geometric accuracy as well as run-time performance on three publicly available benchmark datasets. Our approach achieves real-time performance with high accuracy for 2048 × 1024 image sizes and 4 × 4 Stixel resolution on the low-power embedded GPU of an NVIDIA Tegra Xavier.  
  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; 600.124; 600.118 Approved no  
  Call Number Admin @ si @ HEV2021 Serial 3561  
Permanent link to this record
 
 
Author Jose Luis Gomez; Gabriel Villalonga; Antonio Lopez edit   pdf
url  openurl
  Title Co-Training for Deep Object Detection: Comparing Single-Modal and Multi-Modal Approaches Type Journal Article
  Year (down) 2021 Publication Sensors Abbreviated Journal SENS  
  Volume 21 Issue 9 Pages 3185  
  Keywords co-training; multi-modality; vision-based object detection; ADAS; self-driving  
  Abstract Top-performing computer vision models are powered by convolutional neural networks (CNNs). Training an accurate CNN highly depends on both the raw sensor data and their associated ground truth (GT). Collecting such GT is usually done through human labeling, which is time-consuming and does not scale as we wish. This data-labeling bottleneck may be intensified due to domain shifts among image sensors, which could force per-sensor data labeling. In this paper, we focus on the use of co-training, a semi-supervised learning (SSL) method, for obtaining self-labeled object bounding boxes (BBs), i.e., the GT to train deep object detectors. In particular, we assess the goodness of multi-modal co-training by relying on two different views of an image, namely, appearance (RGB) and estimated depth (D). Moreover, we compare appearance-based single-modal co-training with multi-modal. Our results suggest that in a standard SSL setting (no domain shift, a few human-labeled data) and under virtual-to-real domain shift (many virtual-world labeled data, no human-labeled data) multi-modal co-training outperforms single-modal. In the latter case, by performing GAN-based domain translation both co-training modalities are on par, at least when using an off-the-shelf depth estimation model not specifically trained on the translated images.  
  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; 600.118 Approved no  
  Call Number Admin @ si @ GVL2021 Serial 3562  
Permanent link to this record
 
 
Author Hannes Mueller; Andre Groeger; Jonathan Hersh; Andrea Matranga; Joan Serrat edit   pdf
url  doi
openurl 
  Title Monitoring war destruction from space using machine learning Type Journal Article
  Year (down) 2021 Publication Proceedings of the National Academy of Sciences of the United States of America Abbreviated Journal PNAS  
  Volume 118 Issue 23 Pages e2025400118  
  Keywords  
  Abstract Existing data on building destruction in conflict zones rely on eyewitness reports or manual detection, which makes it generally scarce, incomplete, and potentially biased. This lack of reliable data imposes severe limitations for media reporting, humanitarian relief efforts, human-rights monitoring, reconstruction initiatives, and academic studies of violent conflict. This article introduces an automated method of measuring destruction in high-resolution satellite images using deep-learning techniques combined with label augmentation and spatial and temporal smoothing, which exploit the underlying spatial and temporal structure of destruction. As a proof of concept, we apply this method to the Syrian civil war and reconstruct the evolution of damage in major cities across the country. Our approach allows generating destruction data with unprecedented scope, resolution, and frequency—and makes use of the ever-higher frequency at which satellite imagery becomes available.  
  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; 600.118 Approved no  
  Call Number Admin @ si @ MGH2021 Serial 3584  
Permanent link to this record
 
 
Author Cesar de Souza; Adrien Gaidon; Yohann Cabon; Naila Murray; Antonio Lopez edit   pdf
doi  openurl
  Title Generating Human Action Videos by Coupling 3D Game Engines and Probabilistic Graphical Models Type Journal Article
  Year (down) 2020 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 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
Select All    Deselect All << 1 2 3 4 5 6 7 8 9 10 >> [11–14]
List View
 | 
Citations
 | 
Details
toggle visibility
Save Citations:
Export Records: