Publication: Mono-DCNet: Monocular 3D Object Detection via Depth-based Centroid Refinement and Pose Estimation
carlosiii.embargo.liftdate | 2024-07-19 | |
carlosiii.embargo.terms | 2024-07-19 | |
dc.affiliation.dpto | UC3M. Departamento de Ingeniería de Sistemas y Automática | es |
dc.affiliation.grupoinv | UC3M. Grupo de Investigación: Laboratorio de Sistemas Inteligentes | es |
dc.contributor.author | Astudillo Olalla, Armando | |
dc.contributor.author | Al Kaff, Abdulla Hussein Abdulrahman | |
dc.contributor.author | García Fernández, Fernando | |
dc.date.accessioned | 2023-03-02T11:11:02Z | |
dc.date.issued | 2022-07-19 | |
dc.description | Proceeding of 2022 IEEE Intelligent Vehicles Symposium (IV), (33rd IEEE IV), 04-09 June 2022, Aachen, Germany. | en |
dc.description.abstract | 3D object detection is a well-known problem for autonomous systems. Most of the existing methods use sensor fusion techniques with Radar, LiDAR, and Cameras. However, one of the challenges is to estimate the 3D shape and location of the adjoining vehicles from a single monocular image without other 3D sensors; such as Radar or LiDAR. To solve the lack of the depth information, a novel method for 3D vehicle detection is presented. In this work, instead of using the whole depth map and the viewing angle (allocentric angle), only the depth mask of each object is used to refine the projected centroid and estimate its egocentric angle directly. The performance of the proposed method is tested and validated using the KITTI dataset, obtaining similar results to other state-of-the-art methods for Monocular 3D Object Detection. | en |
dc.description.sponsorship | This work has been supported by the Madrid Government (Comunidad de Madrid-Spain) under the Multiannual Agreement with UC3M (“Fostering Young Doctors Research”, APBI-CMUC3M), and in the context of the V PRICIT (Research and Technological Innovation Regional Programme). Also, We gratefully acknowledge the support of NVIDIA Corporation with the donation of the GPUs used for this research. | en |
dc.description.status | Publicado | es |
dc.format.extent | 5 | |
dc.identifier.bibliographicCitation | 2022 IEEE Intelligent Vehicles Symposium (IV). IEEE. Pp. 664-669. | en |
dc.identifier.doi | https://doi.org/10.1109/IV51971.2022.9827373 | |
dc.identifier.isbn | 978-1-6654-8821-1 | |
dc.identifier.publicationfirstpage | 664 | |
dc.identifier.publicationlastpage | 669 | |
dc.identifier.publicationtitle | 2022 IEEE Intelligent Vehicles Symposium (IV) | en |
dc.identifier.uri | https://hdl.handle.net/10016/36723 | |
dc.identifier.uxxi | CC/0000034081 | |
dc.language.iso | eng | en |
dc.publisher | IEEE | en |
dc.relation.eventdate | 04-09 June 2022 | en |
dc.relation.eventnumber | 33 | |
dc.relation.eventplace | Aachen, Alemania | |
dc.relation.eventtitle | IEEE Intelligent Vehicles Symposium (IV) | en |
dc.rights | ©2022 IEEE. | en |
dc.rights.accessRights | embargoed access | en |
dc.subject.eciencia | Robótica e Informática Industrial | es |
dc.subject.other | Image segmentation | en |
dc.subject.other | Three-dimensional displays | en |
dc.subject.other | Laser radar | en |
dc.subject.other | Power demand | en |
dc.subject.other | Shape | en |
dc.subject.other | Intelligent vehicles | en |
dc.subject.other | Pose estimation | en |
dc.title | Mono-DCNet: Monocular 3D Object Detection via Depth-based Centroid Refinement and Pose Estimation | en |
dc.type | conference proceedings | * |
dc.type.hasVersion | AM | * |
dspace.entity.type | Publication |
Files
Original bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- DCNet_IV_2022_ps.pdf
- Size:
- 398.38 KB
- Format:
- Adobe Portable Document Format