| 1. |
- Bellone, Mauro, 1982, et al.
(författare)
-
Learning Traversability from Point Clouds in Challenging Scenarios
- 2018
-
Ingår i: IEEE Transactions on Intelligent Transportation Systems. - 1524-9050 .- 1558-0016. ; 19:1, s. 296-305
-
Tidskriftsartikel (refereegranskat)abstract
- This paper aims at evaluating the capabilities to detect road traversability in urban and extra-urban scenarios ofsupport vector machine-based classifiers that use local descriptors extracted from point cloud data. The evaluation of the proposed classifiers is carried out by using four different kernels and comparing five point descriptors obtained from geometric and appearance-based features. A comparison among the performance of descriptors individually has demonstrated that the normal vector-based descriptor achieves an accuracy of 88%, outperforming by about 6%–15% all the other considered ones. To further improve the interpretation capabilities, the space of features is augmented by merging the components of each point descriptor, reaching 92% classification accuracy. A set of test scenarios have been acquired during an extensive experimental campaign using an all-terrain vehicle. Tests on real data show high classification performance for road scenarios and rural environments; the generality of the method makes it applicable for different types of mobile robots including, but not limited to, autonomous vehicles.
|
|
| 2. |
- Caltagirone, Luca, 1983, et al.
(författare)
-
Fast LIDAR-based road detection using fully convolutional neural networks
- 2017
-
Ingår i: IEEE Intelligent Vehicles Symposium, Proceedings. ; , s. 1019-1024
-
Konferensbidrag (refereegranskat)abstract
- In this work, a deep learning approach has been developed to carry out road detection using only LIDAR data. Starting from an unstructured point cloud, top-view images encoding several basic statistics such as mean elevation and density are generated. By considering a top-view representation, road detection is reduced to a single-scale problem that can be addressed with a simple and fast fully convolutional neural network (FCN). The FCN is specifically designed for the task of pixel-wise semantic segmentation by combining a large receptive field with high-resolution feature maps. The proposed system achieved excellent performance and it is among the top-performing algorithms on the KITTI road benchmark. Its fast inference makes it particularly suitable for real-Time applications.
|
|
| 3. |
|
|
| 4. |
- Caltagirone, Luca, 1983, et al.
(författare)
-
LIDAR-Camera Fusion for Road Detection Using Fully Convolutional Neural Networks
- 2019
-
Ingår i: Robotics and Autonomous Systems. - : Elsevier BV. - 0921-8890. ; 111, s. 125-131
-
Tidskriftsartikel (refereegranskat)abstract
- In this work, a deep learning approach has been developed to carry out road detection by fusing LIDAR point clouds and camera images. An unstructured and sparse point cloud is first projected onto the camera image plane and then upsampled to obtain a set of dense 2D images encoding spatial information. Several fully convolutional neural networks (FCNs) are then trained to carry out road detection, either by using data from a single sensor, or by using three fusion strategies: early, late, and the newly proposed cross fusion. Whereas in the former two fusion approaches, the integration of multimodal information is carried out at a predefined depth level, the cross fusion FCN is designed to directly learn from data where to integrate information; this is accomplished by using trainable cross connections between the LIDAR and the camera processing branches. To further highlight the benefits of using a multimodal system for road detection, a data set consisting of visually challenging scenes was extracted from driving sequences of the KITTI raw data set. It was then demonstrated that, as expected, a purely camera-based FCN severely underperforms on this data set. A multimodal system, on the other hand, is still able to provide high accuracy. Finally, the proposed cross fusion FCN was evaluated on the KITTI road benchmark where it achieved excellent performance, with a MaxF score of 96.03%, ranking it among the top-performing approaches.
|
|
| 5. |
- Caltagirone, Luca, 1983, et al.
(författare)
-
Lidar–camera semi-supervised learning for semantic segmentation
- 2021
-
Ingår i: Sensors. - : MDPI AG. - 1424-8220. ; 21:14
-
Tidskriftsartikel (refereegranskat)abstract
- In this work, we investigated two issues: (1) How the fusion of lidar and camera data can improve semantic segmentation performance compared with the individual sensor modalities in a supervised learning context; and (2) How fusion can also be leveraged for semi-supervised learning in order to further improve performance and to adapt to new domains without requiring any additional labelled data. A comparative study was carried out by providing an experimental evaluation on networks trained in different setups using various scenarios from sunny days to rainy night scenes. The networks were tested for challenging, and less common, scenarios where cameras or lidars individually would not provide a reliable prediction. Our results suggest that semi-supervised learning and fusion techniques increase the overall performance of the network in challenging scenarios using less data annotations.
|
|
| 6. |
- Caltagirone, Luca, 1983, et al.
(författare)
-
Truck Platooning Based on Lead Vehicle Speed Profile Optimization and Artificial Physics
- 2015
-
Ingår i: IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC 2015. - 9781467365956 ; 2015 October, s. 394-399
-
Konferensbidrag (refereegranskat)abstract
- - Several approaches to truck platooning over varying road topographies are introduced, evaluated, and compared. A simple, stochastic optimization procedure was applied to the lead vehicle speed profiles (covering sections of 10 km), resulting in average lead vehicle fuel savings of around 15.4% relative to standard cruise control. Moreover, several models involving artificial physics were evaluated for the actual platooning, i.e. for the motion of the vehicles following the lead vehicle, with the aim of minimizing the total fuel consumption of the entire platoon. One such model, based on modified artificial gravity, was found to slightly outperform a more standard approach involving adaptive cruise control, while maintaining safety and coherence of the platoon.
|
|
