Details
| Original language | English |
|---|---|
| Pages (from-to) | 255-263 |
| Number of pages | 9 |
| Journal | International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives |
| Volume | 43 |
| Issue number | B2-2021 |
| Publication status | Published - 28 Jun 2021 |
| Event | 2021 24th ISPRS Congress Commission II: Imaging Today, Foreseeing Tomorrow - Virtual, Online, France Duration: 5 Jul 2021 → 9 Jul 2021 |
Abstract
Collective perception of connected vehicles can sufficiently increase the safety and reliability of autonomous driving by sharing perception information. However, collecting real experimental data for such scenarios is extremely expensive. Therefore, we built a computational efficient co-simulation synthetic data generator through CARLA and SUMO simulators. The simulated data contain image and point cloud data as well as ground truth for object detection and semantic segmentation tasks. To verify the superior performance gain of collective perception over single-vehicle perception, we conducted experiments of vehicle detection, which is one of the most important perception tasks for autonomous driving, on this data set. A 3D object detector and a Bird's Eye View (BEV) detector are trained and then test with different configurations of the number of cooperative vehicles and vehicle communication ranges. The experiment results showed that collective perception can not only dramatically increase the overall mean detection accuracy but also the localization accuracy of detected bounding boxes. Besides, a vehicle detection comparison experiment showed that the detection performance drop caused by sensor observation noise can be canceled out by redundant information collected by multiple vehicles.
Keywords
- 3D Object Detection, Collective Perception, Data Fusion, Point Cloud, Semantic Segmentation, Simulation, Uncertainty Estimation
ASJC Scopus subject areas
- Computer Science(all)
- Information Systems
- Social Sciences(all)
- Geography, Planning and Development
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, Vol. 43, No. B2-2021, 28.06.2021, p. 255-263.
Research output: Contribution to journal › Conference article › Research › peer review
}
TY - JOUR
T1 - Comap
T2 - 2021 24th ISPRS Congress Commission II: Imaging Today, Foreseeing Tomorrow
AU - Yuan, Y.
AU - Sester, M.
PY - 2021/6/28
Y1 - 2021/6/28
N2 - Collective perception of connected vehicles can sufficiently increase the safety and reliability of autonomous driving by sharing perception information. However, collecting real experimental data for such scenarios is extremely expensive. Therefore, we built a computational efficient co-simulation synthetic data generator through CARLA and SUMO simulators. The simulated data contain image and point cloud data as well as ground truth for object detection and semantic segmentation tasks. To verify the superior performance gain of collective perception over single-vehicle perception, we conducted experiments of vehicle detection, which is one of the most important perception tasks for autonomous driving, on this data set. A 3D object detector and a Bird's Eye View (BEV) detector are trained and then test with different configurations of the number of cooperative vehicles and vehicle communication ranges. The experiment results showed that collective perception can not only dramatically increase the overall mean detection accuracy but also the localization accuracy of detected bounding boxes. Besides, a vehicle detection comparison experiment showed that the detection performance drop caused by sensor observation noise can be canceled out by redundant information collected by multiple vehicles.
AB - Collective perception of connected vehicles can sufficiently increase the safety and reliability of autonomous driving by sharing perception information. However, collecting real experimental data for such scenarios is extremely expensive. Therefore, we built a computational efficient co-simulation synthetic data generator through CARLA and SUMO simulators. The simulated data contain image and point cloud data as well as ground truth for object detection and semantic segmentation tasks. To verify the superior performance gain of collective perception over single-vehicle perception, we conducted experiments of vehicle detection, which is one of the most important perception tasks for autonomous driving, on this data set. A 3D object detector and a Bird's Eye View (BEV) detector are trained and then test with different configurations of the number of cooperative vehicles and vehicle communication ranges. The experiment results showed that collective perception can not only dramatically increase the overall mean detection accuracy but also the localization accuracy of detected bounding boxes. Besides, a vehicle detection comparison experiment showed that the detection performance drop caused by sensor observation noise can be canceled out by redundant information collected by multiple vehicles.
KW - 3D Object Detection
KW - Collective Perception
KW - Data Fusion
KW - Point Cloud
KW - Semantic Segmentation
KW - Simulation
KW - Uncertainty Estimation
UR - http://www.scopus.com/inward/record.url?scp=85116028629&partnerID=8YFLogxK
U2 - 10.5194/isprs-archives-XLIII-B2-2021-255-2021
DO - 10.5194/isprs-archives-XLIII-B2-2021-255-2021
M3 - Conference article
AN - SCOPUS:85116028629
VL - 43
SP - 255
EP - 263
JO - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
JF - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
SN - 1682-1750
IS - B2-2021
Y2 - 5 July 2021 through 9 July 2021
ER -