REAL

Evaluating the impact of point cloud downsampling on the robustness of Lidar-based object detection

Golarits, Marcell and Rózsa, Zoltán and Hamzaoui, Raouf and Allidina, Tanvir and Lu, Xin and Szirányi, Tamás (2024) Evaluating the impact of point cloud downsampling on the robustness of Lidar-based object detection. In: XI. Magyar Számítógépes Grafika és Geometria Konferencia. NJSZT, Budapest, pp. 126-133. ISBN 9789634219484

[img]
Preview
Text
GrafGeo_2024_paper_3_version.pdf - Published Version

Download (8MB) | Preview

Abstract

LiDAR-based 3D object detection relies on the relatively rich information captured by LiDAR point clouds. However, computational efficiency often requires the downsampling of these point clouds. This paper studies the impact of downsampling strategies on the robustness of a state-of-the-art object detector, namely PointPillars. We compare the performance of the approach under random sampling and farthest point sampling, evaluating the model’s accuracy in detecting objects across various downsampling ratios. The experiments were conducted on the popular KITTI dataset.

Item Type: Book Section
Subjects: Q Science / természettudomány > QA Mathematics / matematika
Q Science / természettudomány > QA Mathematics / matematika > QA75 Electronic computers. Computer science / számítástechnika, számítógéptudomány
Q Science / természettudomány > QA Mathematics / matematika > QA76 Computer software / programozás
SWORD Depositor: MTMT SWORD
Depositing User: MTMT SWORD
Date Deposited: 11 Sep 2024 11:00
Last Modified: 11 Sep 2024 11:00
URI: https://real.mtak.hu/id/eprint/204673

Actions (login required)

Edit Item Edit Item