End-to-End Monocular Vanishing Point Detection Exploiting Lane Annotations

TL;DR

This paper presents an end-to-end monocular vanishing point detection method that leverages lane annotations to generate accurate VP labels, improving detection accuracy and aiding online camera calibration in automotive scenarios.

Contribution

It introduces a novel approach to automatically generate vanishing point labels from lane annotations, reducing manual effort and increasing detection accuracy.

Findings

Higher accuracy than manual annotation-based methods

Effective in online camera calibration for vehicles

Mitigates human annotation errors

Abstract

Vanishing points (VPs) play a vital role in various computer vision tasks, especially for recognizing the 3D scenes from an image. In the real-world scenario of automobile applications, it is costly to manually obtain the external camera parameters when the camera is attached to the vehicle or the attachment is accidentally perturbed. In this paper we introduce a simple but effective end-to-end vanishing point detection. By automatically calculating intersection of the extrapolated lane marker annotations, we obtain geometrically consistent VP labels and mitigate human annotation errors caused by manual VP labeling. With the calculated VP labels we train end-to-end VP Detector via heatmap estimation. The VP Detector realizes higher accuracy than the methods utilizing manual annotation or lane detection, paving the way for accurate online camera calibration.