Bibliographic data

Document DE102022214330A1 (Pages: 11)

Bibliographic data Document DE102022214330A1 (Pages: 11)
INID Criterion Field Contents
54 Title TI [DE] Verfahren zur Erzeugung mindestens einer Ground Truth aus der Vogelperspektive
71/73 Applicant/owner PA Robert Bosch Gesellschaft mit beschränkter Haftung, 70469, Stuttgart, DE
72 Inventor IN Guo, Ze, 14199, Berlin, DE ; Tananaev, Denis, 71067, Sindelfingen, DE
22/96 Application date AD Dec 22, 2022
21 Application number AN 102022214330
Country of application AC DE
Publication date PUB Jul 20, 2023
33
31
32		 Priority data PRC
PRN
PRD		 DE
102022200503
20220118
51 IPC main class ICM G06V 20/56 (2022.01)
51 IPC secondary class ICS G06V 10/70 (2022.01)
G06V 20/70 (2022.01)
IPC additional class ICA
IPC index class ICI
Cooperative patent classification CPC G01S 17/86
G01S 17/89
G01S 17/931
G06N 20/00
G06T 17/05
G06T 2207/10028
G06T 2207/20036
G06T 5/20
G06T 7/10
G06T 7/73
G06T 7/80
G06V 10/26
G06V 10/764
G06V 10/803
G06V 10/82
G06V 20/56
MCD main class MCM G06V 20/56 (2022.01)
MCD secondary class MCS G06V 10/70 (2022.01)
G06V 20/70 (2022.01)
MCD additional class MCA
57 Abstract AB [DE] Die Erfindung betrifft ein Verfahren zur Generierung mindestens einer Darstellung (1) aus der Vogelperspektive, wobei das Verfahren mindestens die folgenden Schritte umfasst:a) Durchführen einer Sensordaten-Punktwolkenverdichtung (2),b) Durchführen einer Punktwolkenfilterung in einer Kameraperspektive,c) Durchführen einer Objektvervollständigung,d) Durchführen einer Vogelperspektiven-Segmentierung (3) und Generierung einer Höhenkarte (4).
56 Cited documents identified in the search CT
56 Cited documents indicated by the applicant CT
56 Cited non-patent literature identified in the search CTNP CAO, P., et al.: Multi-view frustum pointnet for object detection in autonomous driving. In: 2019 IEEE International Conference on Image Processing (ICIP). IEEE, 2019. S. 3896-3899. doi: 10.1109/ICIP.2019.8803572 n;
IMAD, M., Doukhi, O., Lee, D.-J.: Transfer learning based semantic segmentation for 3D object detection from point cloud. In: Sensors, 2021, 21. Jg., Nr. 12, S. 1-15. doi: 10.3390/s21123964 n;
MEYER, G. P., et al.: Sensor fusion for joint 3d object detection and semantic segmentation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops. 2019. S. 1-8. [online abrufbar über https://openaccess.thecvf.com/content_CVPRW_2019/papers/WAD/Meyer_Sensor_Fusion_for_Joint_3D_Object_Detection_and_Semantic_Segmentation_CVPRW_2019_paper.pdf] n;
QI, C. R., et al.: Offboard 3d object detection from point cloud sequences. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021. S. 6134-6144. [online abrufbar über https://openaccess.thecvf.com/content/CVPR2021/papers/Qi_Offboard_3D_Object_Detection_From_Point_Cloud_Sequences_CVPR_2021_paper.pdf] n;
WEN, L.-H., Jo, K.-H.: Fast and accurate 3D object detection for lidar-camera-based autonomous vehicles using one shared voxel-based backbone. In: IEEE access, 2021, 9. Jg., S. 22080-22089. doi: 10.1109/ACCESS.2021.3055491 n;
YANG, Z., et al.: Ipod: Intensive point-based object detector for point cloud. In: arXiv preprint arXiv:1812.05276, 2018. S. 1-9. doi: 10.48550/arXiv.1812.05276 n
56 Cited non-patent literature indicated by the applicant CTNP
Citing documents Determine documents
Sequence listings
Search file IPC ICP G06V 10/70
G06V 20/56
G06V 20/70