Monocular Vision based Crowdsourced 3D Traffic Sign Positioning with Unknown Camera Intrinsics and Distortion Coefficients
This addresses the cost and scalability issues in mapping for autonomous vehicles by enabling crowdsourced updates without requiring precise camera calibration, though it is incremental as it builds on existing crowdsourced mapping approaches.
The paper tackles the problem of crowdsourced 3D traffic sign positioning without known camera intrinsics and distortion coefficients, achieving an average relative accuracy of 0.26 m and absolute accuracy of 1.38 m on the KITTI dataset using only a monocular camera and GPS.
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.