Vision-based Semantic Mapping and Localization for Autonomous Indoor Parking

TL;DR

This paper presents a real-time, vision-based semantic mapping and localization system for autonomous indoor parking, utilizing high-level landmarks, data association optimization, and visual markers to achieve accurate vehicle positioning.

Contribution

It introduces a novel approach combining semantic parking slot mapping, data association refinement, and visual fiducial markers for improved indoor localization accuracy.

Findings

Achieved 0.3m average localization accuracy at 10kph.

Developed a fully automatic semantic parking lot mapping system.

Validated performance on the TiEV autonomous driving platform.

Abstract

In this paper, we proposed a novel and practical solution for the real-time indoor localization of autonomous driving in parking lots. High-level landmarks, the parking slots, are extracted and enriched with labels to avoid the aliasing of low-level visual features. We then proposed a robust method for detecting incorrect data associations between parking slots and further extended the optimization framework by dynamically eliminating suboptimal data associations. Visual fiducial markers are introduced to improve the overall precision. As a result, a semantic map of the parking lot can be established fully automatically and robustly. We experimented the performance of real-time localization based on the map using our autonomous driving platform TiEV, and the average accuracy of 0.3m track tracing can be achieved at a speed of 10kph.