Road Surface Estimation and Obstacle Detection using Fisheye Stereo Camera and Monocular Depth Estimation

DOI Web Site

Bibliographic Information

Other Title
  • 魚眼ステレオカメラと単眼深度推定を用いた路面平面推定と障害物検出
Published
2024
DOI
  • 10.1299/jsmermd.2024.1a1-p09
Publisher
The Japan Society of Mechanical Engineers

Description

<p>In this study, we propose a method for road surface estimation and obstacle detection using a fisheye stereo camera. In obstacle detection using stereo cameras, obstacles are detected based on distance information obtained through stereo matching. However, due to processing load, this cannot be done quickly. And obstacle detection methods using deep learning cannot accommodate obstacles that are not included in the training data. Therefore, we first detect obstacles on the road surface using the relative depth obtained from monocular depth estimation. Then, by focusing only on the obstacle regions for distance measurement, we aim to quickly detect all obstacles. Experiments demonstrate the ability to detect only obstacles and the high processing speed.</p>

Journal

Keywords

Details 詳細情報について

Report a problem

Back to top