Alejandro Barrera
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Alejandro Barrera has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Fernando García
Department of Systems Engineering and Automation, Universidad Carlos III de Madrid (UC3M), 28911 Leganes, Spain
5 shared publications - Carlos Guindel
Intelligent Systems Lab, Universidad Carlos III de Madrid, Leganés, Spain
3 shared publications - Armando Astudillo
Autonomous Mobility and Perception Laboratory (AMPL), Universidad Carlos III de Madrid, Madrid, Spain
2 shared publications - Jorge Beltran
Intelligent Robotics Lab, Universidad Rey Juan Carlos, 28942 Fuenlabrada, Spain
2 shared publications - Abdulla Al-Kaff
Autonomous Mobility and Perception Laboratory (AMPL), Departamento de Ingenieria de Sistemas y Automática, Universidad Carlos III de Madrid, 28911 Madrid, Spain
1 shared publication Carlos Guindel
1 shared publication
Latest Publications
- 13 December 2023
- Published by Springer Nature in Neural Computing and Applications
- Vol. 36 (7) , 3347-3356
DAttNet: monocular depth estimation network based on attention mechanisms
- 13 December 2023
- Published by Springer Nature in Neural Computing and Applications
- Vol. 36 (7) , 3347-3356
DAttNet: monocular depth estimation network based on attention mechanisms
- 1 January 2022
- Published by Springer Nature
- p. 345-353
Contrastive Learning for Simulation-to-Real Domain Adaptation of LiDAR Data
- 1 January 2022
- Published by Springer Nature
- p. 345-353
Contrastive Learning for Simulation-to-Real Domain Adaptation of LiDAR Data
- Open Access
- 30 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 160299-160316
BirdNet+: Two-Stage 3D Object Detection in LiDAR Through a Sparsity-Invariant Bird’s Eye View
Autonomous navigation relies upon an accurate understanding of the elements in the surroundings. Among the different on-board perception tasks, 3D object detection allows the identification of dynamic objects that cannot be registered by maps, being key for safe navigation. Thus, it often requires the use of LiDAR data, which is able to faithfully represent the scene geometry. However, although raw laser point clouds contain rich features to perform object detection, more compact representations such as the bird’s eye view (BEV) projection are usually preferred in order to meet the time requirements of the control loop. This paper presents an end-to-end object detection network based on the well-known Faster R-CNN architecture that uses BEV images as input to produce the final 3D boxes. Our regression branches can infer not only the axis-aligned bounding boxes but also the rotation angle, height, and elevation of the objects in the scene. The proposed network provides state-of-the-art results for car, pedestrian, and cyclist detection with a single forward pass when evaluated on the KITTI 3D Object Detection Benchmark, with an accuracy that exceeds 64% mAP 3D for the Moderate difficulty. Further experiments on the challenging nuScenes dataset show the generalizability of both the method and the proposed BEV representation against different LiDAR devices and across a wider set of object categories by being able to reach more than 30% mAP with a single LiDAR sweep and almost 40% mAP with the usual 10-sweep accumulation.
- 30 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 160299-160316
Open AccessBirdNet+: Two-Stage 3D Object Detection in LiDAR Through a Sparsity-Invariant Bird’s Eye View
Autonomous navigation relies upon an accurate understanding of the elements in the surroundings. Among the different on-board perception tasks, 3D object detection allows the identification of dynamic objects that cannot be registered by maps, being key for safe navigation. Thus, it often requires the use of LiDAR data, which is able to faithfully represent the scene geometry. However, although raw laser point clouds contain rich features to perform object detection, more compact representations such as the bird’s eye view (BEV) projection are usually preferred in order to meet the time requirements of the control loop. This paper presents an end-to-end object detection network based on the well-known Faster R-CNN architecture that uses BEV images as input to produce the final 3D boxes. Our regression branches can infer not only the axis-aligned bounding boxes but also the rotation angle, height, and elevation of the objects in the scene. The proposed network provides state-of-the-art results for car, pedestrian, and cyclist detection with a single forward pass when evaluated on the KITTI 3D Object Detection Benchmark, with an accuracy that exceeds 64% mAP 3D for the Moderate difficulty. Further experiments on the challenging nuScenes dataset show the generalizability of both the method and the proposed BEV representation against different LiDAR devices and across a wider set of object categories by being able to reach more than 30% mAP with a single LiDAR sweep and almost 40% mAP with the usual 10-sweep accumulation.
- 19 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 885-890
Visibility-Aware Adaptative Speed Planner for Human-like Navigation in Roundabouts
Autonomous driving demands the most reliable perception and navigation technologies. These systems should consider both the other agents in the road and the limitations of the on-board sensors. Knowing sensor limitations in real time allows not only to predict the movement of the other agents but also to robustly identify the free space in the road. This paper presents a novel approach that adapts the control of an autonomous vehicle to the real road circumstances in specifically challenging scenarios, i.e., roundabouts. The proposal provides a visibility map that helps the system to calculate collision-free trajectories and to adapt the control techniques to the traffic demands, selecting among comfortable or more ambitious configurations. Tests performed in real traffic have successfully assessed the suitability of the proposed solution.
- 19 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 885-890
Visibility-Aware Adaptative Speed Planner for Human-like Navigation in Roundabouts
Autonomous driving demands the most reliable perception and navigation technologies. These systems should consider both the other agents in the road and the limitations of the on-board sensors. Knowing sensor limitations in real time allows not only to predict the movement of the other agents but also to robustly identify the free space in the road. This paper presents a novel approach that adapts the control of an autonomous vehicle to the real road circumstances in specifically challenging scenarios, i.e., roundabouts. The proposal provides a visibility map that helps the system to calculate collision-free trajectories and to adapt the control techniques to the traffic demands, selecting among comfortable or more ambitious configurations. Tests performed in real traffic have successfully assessed the suitability of the proposed solution.
- Open Access
BirdNet+: End-to-End 3D Object Detection in LiDAR Bird's Eye View
On-board 3D object detection in autonomous vehicles often relies on geometry information captured by LiDAR devices. Albeit image features are typically preferred for detection, numerous approaches take only spatial data as input. Exploiting this information in inference usually involves the use of compact representations such as the Bird's Eye View (BEV) projection, which entails a loss of information and thus hinders the joint inference of all the parameters of the objects' 3D boxes. In this paper, we present a fully end-to-end 3D object detection framework that can infer oriented 3D boxes solely from BEV images by using a two-stage object detector and ad-hoc regression branches, eliminating the need for a post-processing stage. The method outperforms its predecessor (BirdNet) by a large margin and obtains state-of-the-art results on the KITTI 3D Object Detection Benchmark for all the categories in evaluation.
Open AccessBirdNet+: End-to-End 3D Object Detection in LiDAR Bird's Eye View
On-board 3D object detection in autonomous vehicles often relies on geometry information captured by LiDAR devices. Albeit image features are typically preferred for detection, numerous approaches take only spatial data as input. Exploiting this information in inference usually involves the use of compact representations such as the Bird's Eye View (BEV) projection, which entails a loss of information and thus hinders the joint inference of all the parameters of the objects' 3D boxes. In this paper, we present a fully end-to-end 3D object detection framework that can infer oriented 3D boxes solely from BEV images by using a two-stage object detector and ad-hoc regression branches, eliminating the need for a post-processing stage. The method outperforms its predecessor (BirdNet) by a large margin and obtains state-of-the-art results on the KITTI 3D Object Detection Benchmark for all the categories in evaluation.
- Open Access
Lane Detection and Classification using Cascaded CNNs
Lane detection is extremely important for autonomous vehicles. For this reason, many approaches use lane boundary information to locate the vehicle inside the street, or to integrate GPS-based localization. As many other computer vision based tasks, convolutional neural networks (CNNs) represent the state-of-the-art technology to indentify lane boundaries. However, the position of the lane boundaries w.r.t. the vehicle may not suffice for a reliable positioning, as for path planning or localization information regarding lane types may also be needed. In this work, we present an end-to-end system for lane boundary identification, clustering and classification, based on two cascaded neural networks, that runs in real-time. To build the system, 14336 lane boundaries instances of the TuSimple dataset for lane detection have been labelled using 8 different classes. Our dataset and the code for inference are available online.
Open AccessLane Detection and Classification using Cascaded CNNs
Lane detection is extremely important for autonomous vehicles. For this reason, many approaches use lane boundary information to locate the vehicle inside the street, or to integrate GPS-based localization. As many other computer vision based tasks, convolutional neural networks (CNNs) represent the state-of-the-art technology to indentify lane boundaries. However, the position of the lane boundaries w.r.t. the vehicle may not suffice for a reliable positioning, as for path planning or localization information regarding lane types may also be needed. In this work, we present an end-to-end system for lane boundary identification, clustering and classification, based on two cascaded neural networks, that runs in real-time. To build the system, 14336 lane boundaries instances of the TuSimple dataset for lane detection have been labelled using 8 different classes. Our dataset and the code for inference are available online.