Depth perception is pivotal in many fields, such as robotics and autonomous driving, to name a few. Consequently, depth sensors such as LiDARs rapidly spread in many applications. The 3D point clouds generated by these sensors must often be coupled with an RGB camera to understand the framed scene semantically. Usually, the former is projected over the camera image plane, leading to a sparse depth map. Unfortunately, this process, coupled with the intrinsic issues affecting all the depth sensors, yields noise and gross outliers in the final output. Purposely, in this paper, we propose an effective unsupervised framework aimed at explicitly addressing this issue by learning to estimate the confidence of the LiDAR sparse depth map and thus allowing for filtering out the outliers. Experimental results on the KITTI dataset highlight that our framework excels for this purpose. Moreover, we demonstrate how this achievement can improve a wide range of tasks.

Unsupervised confidence for LiDAR depth maps and applications / A. Conti, M. Poggi, F. Aleotti, S. Mattoccia. - ELETTRONICO. - (2022), pp. 8352-8359. (Intervento presentato al convegno IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022) tenutosi a Kyoto, Japan nel October 23–27, 2022) [10.1109/IROS47612.2022.9981654].

Unsupervised confidence for LiDAR depth maps and applications

A. Conti;M. Poggi;F. Aleotti;S. Mattoccia
2022

Abstract

Depth perception is pivotal in many fields, such as robotics and autonomous driving, to name a few. Consequently, depth sensors such as LiDARs rapidly spread in many applications. The 3D point clouds generated by these sensors must often be coupled with an RGB camera to understand the framed scene semantically. Usually, the former is projected over the camera image plane, leading to a sparse depth map. Unfortunately, this process, coupled with the intrinsic issues affecting all the depth sensors, yields noise and gross outliers in the final output. Purposely, in this paper, we propose an effective unsupervised framework aimed at explicitly addressing this issue by learning to estimate the confidence of the LiDAR sparse depth map and thus allowing for filtering out the outliers. Experimental results on the KITTI dataset highlight that our framework excels for this purpose. Moreover, we demonstrate how this achievement can improve a wide range of tasks.
2022
2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS),
8352
8359
Unsupervised confidence for LiDAR depth maps and applications / A. Conti, M. Poggi, F. Aleotti, S. Mattoccia. - ELETTRONICO. - (2022), pp. 8352-8359. (Intervento presentato al convegno IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022) tenutosi a Kyoto, Japan nel October 23–27, 2022) [10.1109/IROS47612.2022.9981654].
A. Conti, M. Poggi, F. Aleotti, S. Mattoccia
File in questo prodotto:
File Dimensione Formato  
2210.03118.pdf

accesso aperto

Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 1.77 MB
Formato Adobe PDF
1.77 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/902904
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 1
social impact