Monocular Vision based Crowdsourced 3D Traffic Sign Positioning with Unknown Camera Intrinsics and Distortion Coefficients

TL;DR

This paper presents a method for crowdsourced 3D traffic sign mapping using monocular vision without prior knowledge of camera parameters, achieving high accuracy on a public dataset.

Contribution

It introduces a novel approach to estimate 3D traffic sign positions without known camera intrinsics or distortion coefficients, reducing reliance on precise camera calibration.

Findings

Achieves 0.26 m relative positioning accuracy

Achieves 1.38 m absolute positioning accuracy

Validates on KITTI dataset with monocular camera and GPS

Abstract

Autonomous vehicles and driver assistance systems utilize maps of 3D semantic landmarks for improved decision making. However, scaling the mapping process as well as regularly updating such maps come with a huge cost. Crowdsourced mapping of these landmarks such as traffic sign positions provides an appealing alternative. The state-of-the-art approaches to crowdsourced mapping use ground truth camera parameters, which may not always be known or may change over time. In this work, we demonstrate an approach to computing 3D traffic sign positions without knowing the camera focal lengths, principal point, and distortion coefficients a priori. We validate our proposed approach on a public dataset of traffic signs in KITTI. Using only a monocular color camera and GPS, we achieve an average single journey relative and absolute positioning accuracy of 0.26 m and 1.38 m, respectively.