Deterministic Guided LiDAR Depth Map Completion

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Krauss, Bryan, Schroeder, Gregory, Gustke, Marko, Hussein, Ahmed
Formato: Preprint
Publicado: 2021
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929559187750912
author Krauss, Bryan
Schroeder, Gregory
Gustke, Marko
Hussein, Ahmed
author_facet Krauss, Bryan
Schroeder, Gregory
Gustke, Marko
Hussein, Ahmed
contents Accurate dense depth estimation is crucial for autonomous vehicles to analyze their environment. This paper presents a non-deep learning-based approach to densify a sparse LiDAR-based depth map using a guidance RGB image. To achieve this goal the RGB image is at first cleared from most of the camera-LiDAR misalignment artifacts. Afterward, it is over segmented and a plane for each superpixel is approximated. In the case a superpixel is not well represented by a plane, a plane is approximated for a convex hull of the most inlier. Finally, the pinhole camera model is used for the interpolation process and the remaining areas are interpolated. The evaluation of this work is executed using the KITTI depth completion benchmark, which validates the proposed work and shows that it outperforms the state-of-the-art non-deep learning-based methods, in addition to several deep learning-based methods.
format Preprint
id arxiv_https___arxiv_org_abs_2106_07256
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Deterministic Guided LiDAR Depth Map Completion
Krauss, Bryan
Schroeder, Gregory
Gustke, Marko
Hussein, Ahmed
Computer Vision and Pattern Recognition
Accurate dense depth estimation is crucial for autonomous vehicles to analyze their environment. This paper presents a non-deep learning-based approach to densify a sparse LiDAR-based depth map using a guidance RGB image. To achieve this goal the RGB image is at first cleared from most of the camera-LiDAR misalignment artifacts. Afterward, it is over segmented and a plane for each superpixel is approximated. In the case a superpixel is not well represented by a plane, a plane is approximated for a convex hull of the most inlier. Finally, the pinhole camera model is used for the interpolation process and the remaining areas are interpolated. The evaluation of this work is executed using the KITTI depth completion benchmark, which validates the proposed work and shows that it outperforms the state-of-the-art non-deep learning-based methods, in addition to several deep learning-based methods.
title Deterministic Guided LiDAR Depth Map Completion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2106.07256