168 citations · 316 across the 18 of their papers we have counts for
22 papers · 1 filter
On the Metrics for Evaluating Monocular Depth Estimation
Akhil Gurram, Antonio M. Lopez
Monocular Depth Estimation (MDE) is performed to produce 3D information that can be used in downstream tasks such as those related to on-board perception for Autonomous Vehicles (A…
Unstructured Road Segmentation using Hypercolumn based Random Forests of Local experts
Prassanna Ganesh Ravishankar, Antonio M. Lopez, Gemma M. Sanchez
Monocular vision based road detection methods are mostly based on machine learning methods, relying on classification and feature extraction accuracy, and suffer from appearance, i…
Distributed Learning and Inference with Compressed Images
Sudeep Katakol, Basem Elbarashy, Luis Herranz +2
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 capt…
Active Learning for Deep Detection Neural Networks
Hamed H. Aghdam, Abel Gonzalez-Garcia, Joost van de Weijer +1
The cost of drawing object bounding boxes (i.e. labeling) for millions of images is prohibitively high. For instance, labeling pedestrians in a regular urban image could take 35 se…
Intention Recognition of Pedestrians and Cyclists by 2D Pose Estimation
Zhijie Fang, Antonio M. López
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…
Slanted Stixels: A way to represent steep streets
Daniel Hernandez-Juarez, Lukas Schneider, Pau Cebrian +6
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 re…
Temporal Coherence for Active Learning in Videos
Javad Zolfaghari Bengar, Abel Gonzalez-Garcia, Gabriel Villalonga +5
Autonomous driving systems require huge amounts of data to train. Manual annotation of this data is time-consuming and prohibitively expensive since it involves human resources. Th…
On Offline Evaluation of Vision-based Driving Models
Felipe Codevilla, Antonio M. López, Vladlen Koltun +1
Autonomous driving models should ideally be evaluated by deploying them on a fleet of physical vehicles in the real world. Unfortunately, this approach is not practical for the vas…
Joint Coarse-And-Fine Reasoning for Deep Optical Flow
Victor Vaquero, German Ros, Francesc Moreno-Noguer +2
We propose a novel representation for dense pixel-wise estimation tasks using CNNs that boosts accuracy and reduces training time, by explicitly exploiting joint coarse-and-fine re…
Metric Learning for Novelty and Anomaly Detection
Marc Masana, Idoia Ruiz, Joan Serrat +2
When neural networks process images which do not resemble the distribution seen during training, so called out-of-distribution images, they often make wrong predictions, and do so…
Is the Pedestrian going to Cross? Answering by 2D Pose Estimation
Zhijie Fang, Antonio M. López
Our recent work suggests that, thanks to nowadays powerful CNNs, image-based 2D pose estimation is a promising cue for determining pedestrian intentions such as crossing the road i…
Monocular Depth Estimation by Learning from Heterogeneous Datasets
Akhil Gurram, Onay Urfalioglu, Ibrahim Halfaoui +2
Depth estimation provides essential information to perform autonomous driving and driver assistance. Especially, Monocular Depth Estimation is interesting from a practical point of…
Slanted Stixels: Representing San Francisco's Steepest Streets
Daniel Hernandez-Juarez, Lukas Schneider, Antonio Espinosa +5
In this work we present a novel compact scene representation based on Stixels that infers geometric and semantic information. Our approach overcomes the previous rather restrictive…
From Virtual to Real World Visual Perception using Domain Adaptation -- The DPM as Example
Antonio M. Lopez, Jiaolong Xu, Jose L. Gomez +2
Supervised learning tends to produce more accurate classifiers than unsupervised learning in general. This implies that training data is preferred with annotations. When addressing…
A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images
David Vázquez, Jorge Bernal, F. Javier Sánchez +5
Colorectal cancer (CRC) is the third cause of cancer death worldwide. Currently, the standard approach to reduce CRC-related mortality is to perform regular screening in search for…
Procedural Generation of Videos to Train Deep Action Recognition Networks
César Roberto de Souza, Adrien Gaidon, Yohann Cabon +1
Deep learning for human action recognition in videos is making significant progress, but is slowed down by its dependency on expensive manual labeling of large video collections. I…
GPU-accelerated real-time stixel computation
Daniel Hernandez-Juarez, Antonio Espinosa, David Vázquez +2
The Stixel World is a medium-level, compact representation of road scenes that abstracts millions of disparity pixels into hundreds or thousands of stixels. The goal of this work i…
Embedded real-time stereo estimation via Semi-Global Matching on the GPU
Daniel Hernandez-Juarez, Alejandro Chacón, Antonio Espinosa +3
Dense, robust and real-time computation of depth information from stereo-camera systems is a computationally demanding requirement for robotics, advanced driver assistance systems…
Road Detection by One-Class Color Classification: Dataset and Experiments
Jose M. Alvarez, Theo Gevers, Antonio M. Lopez
Detecting traversable road areas ahead a moving vehicle is a key process for modern autonomous driving systems. A common approach to road detection consists of exploiting color fea…
Road Detection via On--line Label Transfer
José M. Álvarez, Ferran Diego, Joan Serrat +1
Vision-based road detection is an essential functionality for supporting advanced driver assistance systems (ADAS) such as road following and vehicle and pedestrian detection. The…
Hierarchical Adaptive Structural SVM for Domain Adaptation
Jiaolong Xu, Sebastian Ramos, David Vazquez +1
A key topic in classification is the accuracy loss produced when the data distribution in the training (source) domain differs from that in the testing (target) domain. This is bei…
Spatiotemporal Stacked Sequential Learning for Pedestrian Detection
Alejandro González, Sebastian Ramos, David Vázquez +2
Pedestrian classifiers decide which image windows contain a pedestrian. In practice, such classifiers provide a relatively high response at neighbor windows overlapping a pedestria…